ACM Transactions on

Multimedia Computing, Communications, and Applications (TOMM)

Latest Articles

Sparse Representation-Based Semi-Supervised Regression for People Counting

Label imbalance and the insufficiency of labeled training samples are major obstacles in most methods for counting people in images or videos. In this... (more)

Caching Online Video: Analysis and Proposed Algorithm

Online video presents new challenges to traditional caching with over a thousand-fold increase in number of assets, rapidly changing popularity of assets and much higher throughput requirements. We propose a new hierarchical filtering algorithm for caching online video HiFi. Our algorithm is designed to optimize hit rate, replacement rate and cache... (more)

Multimodal Retrieval with Diversification and Relevance Feedback for Tourist Attraction Images

In this article, we present a novel framework that can produce a visual description of a tourist... (more)

Mixtape: Using Real-Time User Feedback to Navigate Large Media Collections

In this work, we explore the increasing demand for novel user interfaces to navigate large media collections. We implement a geometric data structure to store and retrieve item-to-item similarity information and propose a novel navigation framework that uses vector operations and real-time user... (more)

Securing Speech Noise Reduction in Outsourced Environment

Cloud data centers (CDCs) are becoming a cost-effective method for processing and storage of multimedia data including images, video, and audio. Since... (more)

Interactive Film Recombination

In this article, we discuss an innovative media entertainment application called Interactive Movietelling. As an offspring of Interactive Storytelling applied to movies, we propose to integrate narrative generation through artificial intelligence (AI) planning with video processing and modeling to construct filmic variants starting from the baseline content. The integration is possible thanks to content description using semantic attributes pertaining to intermediate-level concepts shared between video processing and planning levels. The output is a recombination of segments taken from the input movie performed so as to convey an alternative plot. User tests on the prototype proved how... (more)

Complexity Correlation-Based CTU-Level Rate Control with Direction Selection for HEVC

Rate control is a crucial consideration in high-efficiency video coding (HEVC). The estimation of model parameters is very important for coding tree... (more)

Modeling and Analysis of Power Consumption in Live Video Streaming Systems

This article develops an aggregate power consumption model for live video streaming systems, including many-to-many systems. In many-to-one streaming... (more)

When Smart Devices Interact With Pervasive Screens: A Survey

The meeting of pervasive screens and smart devices has witnessed the birth of screen-smart device interaction (SSI), a key enabler to many novel... (more)

O-Mopsi: Mobile Orienteering Game for Sightseeing, Exercising, and Education

Location-based games have been around already since 2000 but only recently when PokemonGo came to markets it became clear that they can reach wide popularity. In this article, we perform a literature-based analytical study of what kind of issues location-based game design faces, and how they can be solved. We study how to use and verify the... (more)

Performance Analysis of Game Engines on Mobile and Fixed Devices

Mobile gaming is an emerging concept wherein gamers are using mobile devices, like smartphones and tablets, to play best-seller games. Compared to... (more)


[October 2017]


We invite highly qualified scientists to submit proposals for 2018-19 ACM TOMM Special Issues. Each Special Issue is in the responsibility of the Guest Editors. Proposals are accepted until December 31st, 2017. They should be prepared according to the instructions outlined below, and sent by e-mail to the Information Director Stefano Berretti ([email protected]) and the Editor in Chief of ACM TOMM Alberto del Bimbo ([email protected]). More information about the proposals submission can be found in the CfP.


[June 2017]

The Impact Factor for the year 2016 is now available. ACM TOMM increased its IF from 0.982 to 2.250 being now the second ranked journal in the area of Multimedia. Thank you to all the EB members, authors, reviewers and readers for this excellent results.

Special Issue on " Multi-modal Understanding of Social, Affective and Subjective Attributes of Data". Cfp . Submission deadline Oct. 1st 2017

Special Issue on "Deep Learning for Intelligent Multimedia Analytics". Cfp. Submission deadline Oct. 15 2017

[April 2017]

Special Issue on  "QoE Management for Multimedia Services". Cfp Submission deadline May 15, 2017 Extended to June 15, 2017

[April 2017]

Call for Nominations for TOMM Nicolas D. Georganas Best Paper Award 2017

The Editor-in-Chief of ACM TOMM invites nominations for the ACM TOMM Nicolas D. Georganas Best Paper. Deadline for nominations of papers published in ACM TOMM from January 2016 to December 2016, is June 15th, 2017. See the call for nomination  cfn

[February 2017]

Upcoming special issues:

- "Delay-Sensitive Video Computing in the Cloud". Cfp   Submission deadline  Aug. 20, 2017

- "QoE Management for Multimedia Services". Cfp Submission deadline May 15, 2017

- "Representation, Analysis and Recognition of 3D Humans" Call for papers 

[January 2017]

ACM TOMM AE guidelines have been added

[December 2016]

ACM TOMM Special Issue on "Delay-Sensitive Video Computing in the Cloud". Cfp Submission deadline Nov. 30, 2016 Extended to Dec. 30, 2016

[November 2016]

- ACM TOMM Special Issue on "Deep Learning for Mobile Multimedia". Cfp  Submission deadline Oct15, 2016 Extended to Nov. 25, 2016

- Special Section on "Multimedia Computing and Applications of Socio-Affective Behaviors in the Wild"Cfp Submission deadline Oct. 31, 2016 Extended to Nov. 25, 2016

- Special Section on "Multimedia Understanding via Multimodal Analytics". Cfp Submission deadline Oct. 31, 2016 Extended to Nov. 25, 2016


[September 2016]


The 2016 ACM Transactions on Multimedia Computing, Communications and Applications (TOMM) Nicolas D. Georganas Best Paper Award is provided to the paper “Cross-Platform Emerging Topic Detection and Elaboration from Multimedia Streams” (TOMM vol. 11, Issue 4) by Bing-Kun Bao, Changsheng Xu, Weiqing Min and Mohammod Shamim Hossain. 

Dr. Cheng-Hsin Hsu has been nominated the ACM TOMM Associate Editor of the Year for 2016! Congratulations to Cheng-Hsin!

[August 2016]

Call for Nominations for TOMM Nicolas D. Georganas Best Paper Award

The Editor-in-Chief of ACM TOMM invites nominations for the ACM TOMM Nicolas D. Georganas Best Paper. Deadline for nominations of papers published in ACM TOMM from January 2015 to December 2015, is September 10th, 2016. See the cfn

[June 2016]

Forthcoming Special Issues in 2017

We received 11 competitive proposals this year, and we had limited slots available, so it was a very tough decision. At the end, the following four SI proposals have been selected and scheduled as follows:

- "Deep Learning for Mobile Multimedia". Cfp  Submission deadline Oct. 15, 2016 Extended to Oct. 31, 2016

- "Representation, Analysis and Recognition of 3D Human". Cfp   Submission deadline Jan. 15, 2017 Extended to Feb. 15, 2017 

Two Special Section have been also accepted and scheduled for publication in 2017:

- "Multimedia Computing and Applications of Socio-Affective Behaviors in the Wild". Cfp Submission deadline Oct. 31, 2016

- "Multimedia Understanding via Multimodal Analytics". Cfp Submission deadline Oct. 31, 2016

[June 2016]

Forthcoming Special Issues in 2016

"Trust Management for Multimedia Big Data" - Publication date August 2016

"Multimedia Big Data: Networking" - Publication date November 2016

[February 2016]

Advisory Board

We have created the ACM TOMM Advisory Board to support the Editor in Chief in the definition and implementation of strategies with no editorial duties. The following colleagues have been appointed as members of the ACM TOMM Advisory Board: Prof. Wen Gao,  Peking University, Prof. Arnold Smeulders, University of Amsterdam, Prof. Nicu Sebe, University of Trento. 

[January 2016]

New Assistant Information Director

Starting on January 1st 2016, Marco Bertini will be in charge of Assistant Information Director of ACM TOMM. 

[January 2016]

New Information Director         Starting on January 1st 2016, Stefano Berretti will be in charge of Information Director of ACM TOMM.  

[January 2016]

New Editor-in-Chief

After the end of the second term of Ralf Steinmetz, Alberto Del Bimbo from the University of Florence will be the next TOMM Editor-in-Chief starting on January 1st 2016. 

ACM TOMM Nicolas D. Georgans Best Paper Award 2015

The award goes to the article "A Quality of Experience Model for Haptic Virtual Environments” (TOMM vol.10, Issue 3) by Abdelwahab Hamam, Abdulmotaleb El Saddik and Jihad Alja'am. Congratulations!

ACM TOMM Associate Editor of the Year 2015 Award

The award goes Pradeep Atrey from State University of New York, USA for his excellent work for the journal. Congratulations!

CfP: Special Issue "Multimedia Big Data: Networking"

Please consider submitting to the second special issue in next years special issue series. Call for Papers


CfP: Special Issue "Trust Management for Multimedia Big Data"

Next year, TOMM will feature a special issue series on "Multimedia Big Data". First topic will be "Trust Management". Extended Deadline: October 15th! Call for Papers


Call for Nominations TOMM Editor-in-Chief

After two terms of the current EiC Ralf Steinmetz, the search committee started the search for a new Editor-in-Chief. Call for Nominations


New ACM submission templates

The new ACM submission templates are online. Please use the most recent link on the authors' guide to find the files.


About TOMM


A peer-reviewed, quarterly archival journal in print and digital form, TOMM consists primarily of research papers of lasting importance and value in the field of multimedia computing, communications and applications. 

News archive
Forthcoming Articles
Adaptive Fractional-Pixel Motion Estimation Skipped Algorithm for Efficient HEVC Motion Estimation

High Efficiency Video Coding (HEVC) efficiently addresses the storage and transmit problems of the high definition videos, especially for the 4K videos. The variable-size Prediction Units (PUs) based Motion Estimation (ME) contributes significant compression rate to the HEVC encoder, while it also generates huge computation load. Meanwhile, the huge computation load becomes a choke point for the HEVC encoder to be widespreadly adopted in the multimedia systems. In this paper, an adaptive fractional-pixel ME skipped scheme is proposed for low complexity HEVC ME. First of all, based on the property of the variable-size PUs based ME process and the video content partition relationship among variable-size PUs, all inter PU modes are classified into the root-type PU modes and children-types PU modes. Then, according to the ME result of the root-type PU mode, the fractional-pixel ME of the children-type PU modes is adaptively skipped. Simulation results show that compared to the original ME in HEVC reference software, the proposed algorithm reduces an average of 63.22% ME encoding time, meanwhile, the encoding efficiency performance is maintained.

Deep Bi-directional Cross-triplet Embedding for Online Clothing Shopping

In this paper, we address two practical problems for online clothing shopping: 1) What do I look like when wearing this clothing on? 2) What accessories shall I buy to pair this item? Our system contains two main parts: clothing trying on and accessories recommendation. Different from existing shopping websites presenting clothing almost uniformly on skinny models on the clean background, our clothing trying on module shows what ordinary people look like when wearing the clothing on street. Moreover, we recommend representative and diverse accessories to pair this item according to daily costume matching on social media, and provide the exact or similar items in online shops. These two sub-modules are mainly unitedly implemented through a bi-directional shop-to-street and street-to-shop clothing retrieval framework by deep feature embedding. There are three main challenges of cross-domain clothing retrieval task. First is to learn the discrepancy (e.g., background, pose, illumination) between street domain and shop domain clothing. Second, both intra-domain and cross-domain similarity need to be considered during feature embedding. Third, there are large biases between the number of matched and non-matched street and shop pairs. To solve these challenges, in this paper, we propose a deep bi-directional cross-triplet embedding algorithm by extending the start-of-the-art triplet embedding into cross-domain retrieval scenario. The extensive experimental evaluations well demonstrate the effectiveness of the proposed cross domain clothing retrieval framework and how it facilitates the clothing trying on and accessories recommendation applications.

Learning Label Preserving Binary Codes for Multimedia Retrieval: A General Approach

Learning-based hashing has received a great deal of research attentions in the past few years for its great potential in fast and accurate similarity search among huge volumes of multimedia data. In this paper, we present a novel multimedia hashing framework, termed as Label Preserving Multimedia Hashing (LPMH) for multimedia similarity search. In LPMH, a general optimization method is used to learn the joint binary codes of multiple media types by explicitly preserving the semantic label information. Compared with existing hashing methods, which are typically developed under and thus restricted to some specific objective functions, the proposed optimization strategy is not tied to any specific loss function, and can easily incorporate bit balance constraints to produce well-balanced binary codes. Specifically, our formulation leads to a set of Binary Integer Programming (BIP) problems that have exact solutions both with and without the bit balance constraints. These problems can be solved extremely fast and the solution can easily scale up to large-scale datasets. In the hash function learning stage, the boosted decision trees algorithm is utilized to learn multiple media-specific hash functions that can map heterogeneous data sources into a homogeneous Hamming space for cross-media retrieval. We have comprehensively evaluated the proposed method using a range of large-scale datasets in both single-media and cross-media retrieval tasks. The experimental results demonstrate that LPMH is competitive against state-of-the-art methods in both speed and accuracy.

Robust Multi-variate Temporal (RMT) Features of Multi-variate Time Series

Many applications generate and/or consume multi-variate temporal data and experts often lack the means to adequately and systematically search for and interpret multi-variate observations. In this paper, we first observe that multi-variate time series often carry localized multi-variate temporal features that are robust against noise. We then argue that these multi-variate temporal features can be extracted by simultaneously considering, at multiple scales, temporal characteristics of the time-series along with external knowledge, including variate relationships, known a priori. Relying on these observations, we develop data models and algorithms to detect robust multi-variate temporal (RMT) features that can be indexed for efficient and accurate retrieval and can be used for supporting data exploration and analysis tasks. Experiments confirm that the proposed RMT algorithm is highly effective and efficient in identifying robust multi-scale temporal features of multi-variate time series.

Early Recognition of 3D Human Actions

Action recognition is an important research problem of Human Motion Analysis (HMA). In recent years, 3D observation based action recognition is receiving increasing interest in the multimedia and computer vision communities, due to recent advent of the cost-effective sensors, such as depth camera Kinect. This work takes one step further, focusing on early recognition of ongoing 3D human actions, which is beneficial for a large variety of time-critical applications, e.g. gesture based human machine interaction, somatosensory game, etc. Our goal is to infer the class label information of 3D human actions with partial observation of temporally incomplete action executions. By considering 3D action data as multivariate time series (m.t.s.) synchronized to a shared common clock (frames), we propose a stochastic process called Dynamic Marked Point Process (DMP) to model the 3D action as temporal dynamic patterns, where both timing and strength information are captured. To achieve even better earliness and accuracy of recognition, we also explore the temporal dependency patterns between feature dimensions. A probabilistic suffix tree is constructed to represent sequential patterns among features in terms of Variable order Markov Model (VMM). Our approach and several baselines are evaluated on four 3D human action datasets. Extensive results show that our approach achieves superior performance for early recognition of 3D human actions.

Emotion Recognition Using Multiple Kernel Learning Towards E-learning Applications

Personalized elearning models tailor learning resource according to learning needs of learners. Adaptive Hypermedia Architecture (AHA), is a successful implementation of the personalized elearning model which uses learning outcomes as personalization parameter to adapt to learning experience of learners. However, besides learning outcomes, emotions of the learner which can have much influence on memory and problem solving is completely neglected in the AHA model. This paper presents Adaptive Educational Hypermedia (AEH) model, known as Expert Elearning System (EES), which is built on top of the AHA to incorporate facial emotion recognition framework. The emotion recognition framework here in, denoted as MKLDT-WFA, is realized by training simple Multiple Kernel Learning (MKL) with Weighted Kernel Alignment (WFA) in a Decision Tree (DT) classifier. The MKLDT-WFA framework has two merits over classical SimpleMKL. First, the WFA component preserves only relevant kernel weights to improve discrimination for emotion classes. Secondly, training in the DT eliminates misclassification issues associated with off-the-shelf SimpleMKL classifiers. The suggested framework has been evaluated on different emotion databases. Results of evaluation reveal good performances for emotion recognition and it is potential to improve personalization in the AEH models

Game Categorization for Deriving QoE-Driven Video Encoding Configuration Strategies for Cloud Gaming

Cloud gaming has been recognized as a promising shift in the online game industry, with the aim of implementing the on demand service concept that has achieved market success in other areas of digital entertainment such as movies and TV shows. The concepts of cloud computing are leveraged to render the game scene as a video stream which is then delivered to players in real-time. The main advantage of this approach is the capability of delivering high-quality graphics games to any type of end user device, however at the cost of high bandwidth consumption and strict latency requirements. A key challenge faced by cloud game providers lies in conguring the video encoding parameters so as to maximize player Quality of Experience (QoE) while meeting bandwidth availability constraints. In this paper we tackle one aspect of this problem by addressing the following research question: Is it possible to improve service adaptation based on information about the characteristics of the game being streamed? To answer this question two main challenges need to be addressed: the need for different QoE-driven video encoding (re-)conguration strategies for different categories of games, and how to determine a relevant game categorization to be used for assigning appropriate conguration strategies. We investigate these problems by conducting two subjective laboratory studies with a total of 80 players and three different games. Results indicate that different strategies should likely be applied for different types of games, and show that existing game classications are not necessarily suitable for differentiating game types in this context. We thus further analyze objective video metrics of collected game play video traces as well as player actions per minute and use this as input data for clustering of games into two clusters. Subjective results verify that different video encoding conguration strategies may be applied to games belonging to different clusters.

Image Captioning with Deep Bidirectional LSTMs and Multi-Task Learning

Generating a novel and descriptive caption of an image is drawing increasing interests in computer vision, natural language processing and multimedia communities. In this work, we propose an end-to-end trainable deep bidirectional LSTM (Bi-LSTM(Long-Short Term Memory)) model to address the problem. By combining a deep convolutional neural network (CNN) and two separate LSTM networks, our model is capable of learning long term visual-language interactions by making use of history and future context information at high level semantic space. We also explore deep multimodal bidirectional models, in which we increase the depth of nonlinearity transition in different way to learn hierarchical visual-language embeddings. Data augmentation techniques such as multi-crop, multi-scale and vertical mirror are proposed to prevent overfitting in training deep models. To understand how our models "translate'' image to sentence, we visualize and qualitatively analyze the evolution of Bi-LSTM internal states over time. The effectiveness and generality of proposed models are evaluated on four benchmark datasets: Flickr8K, Flickr30K, MSCOCO and Pascal1K datasets. We demonstrate that Bi-LSTM models achieve state-of-the-art results on both caption generation and image-sentence retrieval even without integrating additional mechanism (e.g. object detection, attention model etc.). Our experiments also proves that multi-task learning is beneficial to increase model generality and gain performance. We also demonstrate our transfer learning performance of Bi-LSTM model significantly outperforms previous methods on Pascal1K dataset.

Combining Facial Parts For Learning Gender, Ethnicity and Emotional State Based on RGB-D Information

With the success of emerging RGB-D cameras such as the Kinect sensor, com- bining the shape (depth) and texture information to improve the quality of recognition became a trend among computer vision researchers. In this work, we address the problem of face classification in the context of RGB images and depth data. Inspired by the psychological results for human face perception, this paper focuses on (i) finding out which facial parts are most effective at making the difference for some social aspects of face perception (gender, ethnicity and emotion state), (ii) determining the optimal decision by combining the decision rendered by the individual parts, and (iii) extracting the promising features from RGB-D faces in order to exploit all the potential that this data provide. Experimental results on EurecomKinect Face and CurtinFaces databases show that the proposed approach improves the recognition quality in many use cases.

Visual Background Recommendation for Dance Performances Using Deep Matrix Factorization

The stage background is one of the most important features for a dance performance as it helps to create the scene and atmosphere. In conventional dance performances, the background images are usually selected or designed by professional stage designers according to the theme and the style of the dance. In new media dance performances, the stage effects are usually generated by media editing software. Selecting or producing a dance background is quite challenging, and is generally carried out by skilled technicians. The goal of the research reported in this paper is to ease this process. Instead of searching for background images from the sea of available resources, dancers are recommended images they are more likely to use. This paper proposes the idea of a novel system to recommend images based on content-based social computing. The core part of the system is a probabilistic prediction model to predict a dancer's interests in candidate images through social platforms. Different from traditional collaborative filtering models or content-based models, the model proposed in this paper effectively combines a dancer's social behaviors (rating action, click action, etc.) with the visual content of the images shared by the dancer using deep matrix factorization (DMF). With the help of such a system, dancers can select from the recommended images and set them as the backgrounds of their dance performances through a media editor. According to the experiment results, the proposed DMF model outperforms the previous methods, and when the dataset is very sparse, the proposed DMF model shows more significant results.

Gait Recognition from Motion Capture Data

Gait recognition from motion capture data, as a pattern classification discipline, can be improved by the use of machine learning. This paper contributes to the state-of-the-art with two statistical approaches for extracting robust gait features directly from raw data: (1)~a~modification of Linear Discriminant Analysis with Maximum Margin Criterion and (2)~a~combination of Principal Component Analysis and Linear Discriminant Analysis. Experiments on the CMU MoCap database show that these methods outperform thirteen other relevant methods in terms of the distribution of biometric templates in respective feature spaces expressed in a number of class separability coefficients and classification metrics. Results also indicate a high portability of learned features, that means, we can learn what aspects of walk people generally differ in and extract those as general gait features. Recognizing people without needing group-specific features is convenient as particular people might not always provide annotated learning data. As a contribution to reproducible research, our evaluation framework and database have been made publicly available. This research makes motion capture technology directly applicable for human recognition.

A Unified Framework for Multi-Modal Isolated Gesture Recognition

In this paper, we focus on isolated gesture recognition and explore different modalities by involving RGB stream, depth stream and saliency stream for inspection. Our goal is to push the boundary of this realm even further by proposing a unified framework which exploits the advantages of multi-modality fusion. Specifically, a spatial-temporal network architecture based on consensus-voting has been proposed to explicitly model the long term structure of the video sequence and to reduce estimation variance when confronted with comprehensive inter-class variations. In addition, a 3D depth-saliency convolutional network is aggregated in parallel to capture subtle motion characteristics. Extensive experiments are done to analyze the performance of each component and our proposed approach achieves the best results on two public benchmarksChaLearn IsoGD and RGBD-HuDaAct, outperforming the closest competitor by a margin of over 10% and 15% respectively. We will release our codes to facilitate future research.

A Discriminatively Learned CNN Embedding for Person Re-identification

In this paper, we revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i.e.,verification and identification models. The two models have their respective advantages and limitations due to different loss functions. In this paper, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a siamese network that simultaneously computes the identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two input images and whether they belong to the same identity. Our network learns a discriminative embedding and a similarity measurement at the same time, thus taking full usage of the re-ID annotations. Our method can be easily applied on different pre-trained networks. Albeit simple, the learned embedding improves the state-of-the-art performance on two public person re-ID benchmarks. Further, we show our architecture can also be applied to image retrieval. The code is available at

DeepSearch: A fast image search framework for mobile devices

Content-based image retrieval (CBIR) is one of the most important applications of computer vision. Recent years have witnessed many important advances in the development of CBIR systems, especially Convolutional Neural Networks (CNNs) and other deep learning techniques. On the other hand, current CNN-based CBIR systems suffer from high computational complexity of CNNs. This problem becomes more severe as mobile applications become more and more popular. Current mainstream is to deploy the entire CBIR systems on server side while the client side only serves as an image provider. This architecture may increase computational burden on server side, which needs to process thousands of requests per second. Moreover, sending images have the potential of personal information leakage. As the need of mobile search expands, concerns about privacy are growing. In this paper, we propose a fast image search framework, named DeepSearch, which makes complex image search based on CNNs feasible on mobile phone. To implement the huge computation of CNN models, we present a tensor Block Term Decomposition method (BTD) to accelerate the CNNs involving in object detection and feature extraction. The extensive experiments on ImageNet dataset and Alibaba Large-scale Image Search Challenge (ALISC) dataset show that the proposed accelerating method BTD can significantly speed up the CNN models, and further makes CNN-based image search practical on common smart phone.

Egocentric Hand Detection Via Dynamic Region Growing

Egocentric videos, which mainly record the activities carried out by the users of the wearable cameras, have drawn much research attentions in recent years. Due to its lengthy content, a large number of ego-related applications have been developed to abstract the captured videos. As the users are accustomed to interacting with the target objects using their own hands while their hands usually appear within their visual fields during the interaction, an egocentric hand detection step is involved in tasks like gesture recognition, action recognition and social interaction understanding. In this work, we propose a dynamic region growing approach for hand region detection in egocentric videos, by jointly considering hand-related motion and egocentric cues. We first determine seed regions that most likely belong to the hand, by analyzing the motion patterns across successive frames. The hand regions can then be located by extending from the seed regions, according to the scores comuted for the adjacent superpixels. These scores are derived from four egocentric cues: contrast, location, position consistency and appearance continuity. We discuss how to apply the proposed method in real-life scenarios, where multiple hands irregularly appear and disappear from the videos. Experimental results on public datasets show that the proposed method achieves superior performance compared with the state-of-the-art methods, especially in complicated scenarios.

Implicit Emotion Communication: EEG Classification and Haptic Feedback

Today, interpersonal digital communication systems do not have an intuitive and natural way of communicating emotion, which in turn affects the degree to which we can emotionally connect and interact with one another while separated by distance. In answer to this problem, a natural, intuitive and implicit emotion communication system is proposed to recognize emotions using an electroencephalogram (EEG) signal at the transmitter end and display tactile sensation at the receiver side. The proposed system comprises two components: an emotion recognition subsystem that utilizes hemisphere asymmetry-based EEG signals analysis for emotion classification and a haptic jacket to display the apparent tactile sensation (named tactile gestures) at the receiver side. Emotions are modeled in terms of valence (positive/negative emotions) and arousal (intensity of the emotion). Furthermore, an authoring tool is utilized to created custom tactile gestures that can elicit specific emotional reactions. Performance analysis shows that the proposed EEG subject-dependent emotion recognition model with Free Asymmetry features allows for more flexible feature generation schemes than existing algorithms and attains an average accuracy of 92.5\% for valence and 96.5\% for arousal, vastly outperforming previous generation schemes in high feature space. As for the tactile feedback, a tactile gesture authoring tool and a haptic jacket are developed to design custom tactile gestures that can intensify emotional reactions in terms of valence and arousal. A usability study demonstrated that subject-independent emotion transmission through tactile gestures effectively communicated the arousal dimension of an emotion but was not as effective for valence. Consistency in subject dependent responses for both valence and arousal suggest that personalized tactile gestures would be more effective.

Texture and Geometry Scattering Representation based Facial Expression Recognition in 2D+3D Videos

Facial Expression Recognition (FER) is one of the most important topics in the domain of computer vision and pattern recognition and it has attracted increasing attention for its scientific challenges and application potentials. In this paper, we propose a novel and effective approach to FER using multi-model 2D and 3D videos, which encodes both static and dynamic cues by scattering convolution network. Firstly, a shape based detection method is introduced to locate the start and the end of an expression in videos, segment its onset, apex, and offset states, and sample the important frames for emotion analysis. Secondly, the frames in Apex of 2D videos are represented by scattering, conveying static texture details. Those of 3D videos are processed in a similar way, but to highlight static shape details, several geometric maps in terms of multiple order differential quantities, i.e. Normal Maps (NOM) and Shape Index Maps (SIM), are generated as the input of scattering, instead of original smooth facial surfaces. Thirdly, the average of neighboring samples centred at each key texture frame or shape map evenly distributed in Onset, is computed, and the scattering features extracted from all the average samples of 2D and 3D videos are then concatenated to capture dynamic texture and shape cues respectively. Finally, Support Vector Machine (SVM) is adopted to measure the similarity of individual features in either 2D or 3D modality, and all the scores are combined for multi-modal decision making to predict the expression label. Thanks to the scattering descriptor, the proposed approach not only encodes distinct local texture and shape variations of different expressions as by several milestone operators, such as SIFT, HOG, etc., but also captures subtle information hidden in high frequencies in both channels, which is quite crucial to better distinguish expressions that are easily confused. The validation is conducted on the BU-4DFE database, and the state of the art one accuracy is reached, indicating its competency for this issue.

Online Early-Late Fusion Based on Adaptive HMM for Sign Language Recognition

In sign language recognition with multi-modal data, the sign word can be represented by multi-modal features, for which there exist intrinsic property and mutually complementary relationship among them. To fully explore those relationships for sign language recognition, we propose an online early-late fusion method based on adaptive HMM. In terms of the intrinsic property, we discover that inherent latent change states of each sign are not only related to the number of key gestures and body poses, but also related to their translation relationships. We propose an adaptive HMM (Hidden Markov Model) method to obtain the hidden state number of each sign with affinity propagation clustering. For complementary relationship, we propose an online early-late fusion scheme. The early fusion (feature fusion) targets on preserving useful information to achieve a better complementary score while the late fusion (score fusion) uncovers the significance of those features and aggregates them in a weighting manner. For different queries, the fusion weight is inversely proportional to the area under the curve of the normalized query score list for each feature. Different from classical fusion methods, our fusion method is query-adaptive. The whole fusion process is effective and efficient. Experiments verify the effectiveness on the signer-independent SLR (Sign Language recognition) with large vocabulary. Either compared on different dataset sizes or to different SLR models, our method demonstrates consistent and promising performance.

Delay-Aware Quality Optimization in Cloud-Assisted Video Streaming System

Cloud-assisted video streaming has emerged as new paradigm to optimize multimedia content distribution over the Internet. This paper investigates the problem of streaming cloud-assisted real-time video to multiple destinations (e.g., cloud video conferencing, multi-player cloud gaming, etc.) over lossy communication networks. The user diversity and network dynamics result in the delay differences among multiple destinations. This research proposes Differentiated cloud-Assisted VIdeo Streaming (DAVIS) framework, which proactively leverages such delay differences in video coding and transmission optimization. First, we analytically formulate the optimization problem of joint coding and transmission to maximize received video quality. Second, we develop a quality optimization framework that integrates the video representation selection and FEC (Forward Error Correction) packet interleaving. The proposed DAVIS is able to effectively perform differentiated quality optimization for multiple destinations by taking advantage of the delay differences in cloud-assisted video streaming system. We conduct the performance evaluation through extensive experiments with the Amazon EC2 instances and Exata emulation platform. Evaluation results show that DAVIS outperforms the reference cloud-assisted streaming solutions in video quality and delay performance.

Joint Estimation of Age and Expression by Combining Scattering and Convolutional Networks

This paper tackles the problem of joint estimation of human age and facial expression. This problem is important yet challenging because expressions can alter the face appearance in a similar manner to human aging. Unlike previous approaches dealing with the two tasks independently, we propose a jointly trained convolutional neural network (CNN) model that unifies the ordinal regression and multi-class classification in a single framework to tackle this problem. We demonstrate experimentally that our method performs more favorably against state-of-the-art approaches.

Multimodal Multiplatform Social Media Event Summarization

Social media platforms are turning into important news sources for users since they provide real-time information with a wide range of perspectives. However, high volume, dynamism, noise and redundancy exhibited by social media data create difficulties for users in comprehending the entire content. Recent works emphasize on summarizing the content of either a single social media platform or of a single modality (either textual or visual). However, each platform has its own unique characteristics and user base, which brings to light different aspects of real-world events. This makes it critical as well as challenging to combine textual and visual data from different platforms. In this article, we propose summarization of real-word events with data stemming from different platforms and multiple modalities. We present the use of Markov Random Fields based similarity measure to link content across multiple platforms. This measure also enables the linking of content across time which is useful for tracking the evolution of long-running events. For the final content selection, summarization is modeled as a subset selection problem. To handle the complexity of the optimal subset selection, we propose the use of submodular objectives. Facets such as coverage, novelty and significance are modeled as submodular objectives in a multimodal social media setting. We conduct a series of quantitative and qualitative experiments to illustrate the effectiveness of our approach compared to alternative methods.

Structure-aware Multi-modal Feature Fusion for RGB-D Scene Classification and Beyond

While convolutional neural networks (CNN) have been excellent for object recognition, the greater spatial variability in scene images typically mean that the standard full-image CNN features are suboptimal for scene classification. In this paper, we investigate a framework allowing greater spatial flexibility, in which the Fisher vector (FV) encoded distribution of local CNN features, obtained from a multitude of region proposals per image, is considered instead. The CNN features are computed from an augmented pixel-wise representation comprising multiple modalities of RGB, HHA and surface normals, as extracted from RGB-D data. More significantly, we make two postulates: (1) component sparsity --- that only a small variety of region proposals and their corresponding FV GMM components contribute to scene discriminability, and (2) modal non-sparsity --- that features from all modalities are encouraged to co-exist. In our proposed feature fusion framework, these are implemented through regularization terms that apply group lasso to GMM components and exclusive group lasso across modalities. By learning and combining regressors for both proposal-based FV features and global CNN features, we are able to achieve state-of-the-art scene classification performance on the SUNRGBD Dataset and NYU Depth Dataset V2. Moreover, we further apply our feature fusion framework on action recognition task to demonstrate that our framework can be generalized for other multi-modal well-structured features. In particular, for action recognition, we enforce inter-part sparsity to choose more discriminative body parts, and inter-modal non-sparsity to make informative features from both appearance and motion modalities to co-exist. Experimental results on JHMDB and MPII Cooking datasets show that our feature fusion is also very effective for action recognition, achieving very competitive performance compared with the state-of-the-art.


Publication Years 2005-2017
Publication Count 551
Citation Count 3053
Available for Download 550
Downloads (6 weeks) 3434
Downloads (12 Months) 29426
Downloads (cumulative) 250749
Average downloads per article 456
Average citations per article 6
First Name Last Name Award
El Saddik Abdulmotaleb ACM Distinguished Member (2010)
ACM Senior Member (2008)
Ruzena R Bajcsy ACM Distinguished Service Award (2003)
ACM AAAI Allen Newell Award (2001)
ACM Fellows (1996)
Susanne Boll ACM Senior Member (2012)
Surendar Chandra ACM Senior Member (2009)
Kuan-Ta Chen ACM Senior Member (2015)
Matthew L Cooper ACM Distinguished Member (2016)
ACM Senior Member (2010)
Jon Crowcroft ACM Fellows (2002)
Alberto Del Bimbo ACM Distinguished Member (2016)
Claudio A. Feijoo ACM Senior Member (2009)
Wen Gao ACM Fellows (2013)
Shahram Ghandeharizadeh ACM Software System Award (2008)
Soheil Ghiasi ACM Senior Member (2015)
Giorgio Giacinto ACM Senior Member (2010)
Andreas Girgensohn ACM Distinguished Member (2008)
Michael L Gleicher ACM Distinguished Member (2011)
Tracy Anne Hammond ACM Senior Member (2015)
Lynda Hardman ACM Distinguished Member (2014)
ACM Senior Member (2013)
Xian-Sheng Hua ACM Distinguished Member (2015)
ACM Senior Member (2009)
Tiejun Huang ACM Senior Member (2013)
Ramesh C Jain ACM Fellows (2003)
Wessel Kraaij ACM Distinguished Member (2017)
ACM Senior Member (2007)
James Kurose ACM Fellows (2001)
Ming Li ACM Fellows (2006)
Saverio Mascolo ACM Senior Member (2009)
Tao Mei ACM Distinguished Member (2016)
ACM Senior Member (2012)
Filippo Menczer ACM Distinguished Member (2013)
Saraju P. Mohanty ACM Senior Member (2010)
Klara Nahrstedt ACM Fellows (2012)
Nuria Oliver ACM Distinguished Member (2015)
ACM Senior Member (2013)
Dan R Olsen ACM Fellows (2006)
Beng Chin Ooi ACM Fellows (2011)
Ming Ouhyoung ACM Senior Member (2007)
Sethuraman Panchanathan ACM Senior Member (2009)
Joel Jose Rodrigues ACM Senior Member (2011)
Keith Ross ACM Fellows (2012)
Lawrence A Rowe ACM Fellows (1998)
Yong Rui ACM Distinguished Member (2009)
ACM Senior Member (2006)
Michael Rung-Tsong Lyu ACM Fellows (2015)
Henning Schulzrinne ACM Fellows (2014)
David Ayman Shamma ACM Distinguished Member (2016)
ACM Senior Member (2011)
Prashant J Shenoy ACM Distinguished Member (2009)
ACM Senior Member (2006)
Frank Shipman ACM Distinguished Member (2009)
Shervin Shirmohammadi ACM Senior Member (2017)
Ralf Steinmetz ACM Fellows (2001)
Richard Szeliski ACM Fellows (2008)
Bart Thomee ACM Senior Member (2016)
Donald F Towsley ACM Fellows (1997)
Matthew A Turk ACM Senior Member (2007)
Benjamin W. Wah ACM Fellows (2004)
Shuicheng Yan ACM Distinguished Member (2016)
HongJiang Zhang ACM Fellows (2007)
Hui Zhang ACM Fellows (2005)
Lei Zhang ACM Senior Member (2011)
Michelle Zhou ACM Distinguished Member (2009)
ACM Senior Member (2007)
Roger Zimmermann ACM Distinguished Member (2017)

First Name Last Name Paper Counts
Changsheng Xu 15
Tatseng Chua 14
Shuicheng Yan 14
Mohamed Hefeeda 14
Mohan Kankanhalli 10
Weitsang Ooi 10
Klara Nahrstedt 10
Pradeep Atrey 8
Chenghsin Hsu 8
Tao Mei 7
James She 7
Gheorghita Ghinea 7
Roger Zimmermann 7
Ralf Steinmetz 6
Qi Tian 6
Carsten Griwodz 6
Pål Halvorsen 6
Yong Rui 6
Shervin Shirmohammadi 5
Namunu Maddage 5
Svetha Venkatesh 5
Abdulmotaleb El Saddik 5
Pablo César 5
Mohammad Hossain 5
Abdulmotaleb El Saddik 5
Meng Wang 5
Balakrishnan Prabhakaran 5
Shihfu Chang 5
Hari Sundaram 5
Jitao Sang 5
Ming Cheung 5
Changwen Chen 5
Jiangchuan Liu 4
Dick Bulterman 4
Xiansheng HUA 4
Zongpeng Li 4
Shipeng Li 4
Richang Hong 4
Alberto Del Bimbo 4
Shueng Chan 4
Wolfgang Effelsberg 4
Ramesh Jain 4
Oluwakemi Ademoye 4
Gabriel Muntean 4
Prashant Shenoy 3
Marcel Worring 3
Laurencetianruo Yang 3
Géraldine Morin 3
Romulus Grigoraş 3
Séamus McLoone 3
Eckehard Steinbach 3
Tomás Ward 3
Zhengjun Zha 3
Nabil Sarhan 3
Jinhui Tang 3
Rongrong Ji 3
WeiQi Yan 3
Alan Hanjalic 3
Zheng Yan 3
Ruzena Bajcsy 3
Jiwu Huang 3
Wenwu Zhu 3
Si Liu 3
Songqing Chen 3
Yong Rui 3
Alexandru Iosup 3
Michael Zink 3
Robert Deng 3
Shervin Shirmohammadi 3
Chuan Wu 3
Baochun Li 3
Kien Hua 3
Niall Murray 3
Luming Zhang 3
Ketan Mayer-Patel 3
Gregorij Kurillo 3
Munchoon Chan 2
Yuru Lin 2
Xiaofei He 2
Stephan Kopf 2
Matthias Baldauf 2
Nicu Sebe 2
Wanmin Wu 2
Gerald Friedland 2
Steven Hoi 2
Huanbo Luan 2
Houqiang Li 2
Rahul Potharaju 2
Vincent Oria 2
Liang Zhou 2
Zhikui Chen 2
Hongjiang ZHANG 2
Jongeun Cha 2
Vamsidhar Gaddam 2
Ragnar Langseth 2
Min Song 2
Michael Gleicher 2
Chusong Chen 2
Yiping Hung 2
Brett Adams 2
Hendrik Knoche 2
Robert Kinicki 2
Zhenyu Yang 2
Hefei Ling 2
Xiangyu Wang 2
Xu Cheng 2
Shiqiang Yang 2
Xi Zhou 2
Ahsan Arefin 2
Susanne Boll 2
Qingchen Zhang 2
Geoff West 2
Bing Wang 2
Don Towsley 2
Gwendal Simon 2
Indranil Gupta 2
Ramesh Jain 2
Aisling Kelliher 2
Lawrence Rowe 2
Linjun Yang 2
Xue Li 2
Venugopal Vasudevan 2
Michael Pearce 2
Mohan Kankanhalli 2
Bin Cheng 2
Yiliang Zhao 2
Hanqing Lu 2
Michael Houle 2
Jichao Sun 2
Daniel Gatica-Perez 2
Francesco De Natale 2
Pascal Frossard 2
Yipeng Zhou 2
Yeongju Lee 2
Ming Li 2
Haizhou Li 2
Kasim Candan 2
Xiaoshan Yang 2
Xiaobai Liu 2
Xin Zhang 2
Yifang Yin 2
Jiebo Luo 2
Bineng Zhong 2
Simon Moncrieff 2
Chongwah Ngo 2
Xi Shao 2
Zhenwei Zhao 2
Derek Eager 2
Shuqiao Zhao 2
Fuhao Zou 2
Arijit Sur 2
Rui Yang 2
Meng Wang 2
Peiyu Lin 2
Chongwah Ngo 2
Christian Timmerer 2
Yuansong Qiao 2
Zechao Li 2
Wolfgang Kellerer 2
Jie Yang 2
Jun Ye 2
Jesse Jin 2
Bo Shen 2
Mohamad Eid 2
Azzedine Boukerche 2
Jamesze Wang 2
Dag Johansen 2
Ajay Gopinathan 2
Stefan Wilk 2
Tianzhu Zhang 2
Surendar Chandra 2
Keqiu Li 2
Gang Hua 2
Bogdan Carbunar 2
Michael Needham 2
David Shamma 2
Deng Cai 2
Jia Li 2
Liang Chen 2
Xun Yang 2
Andreas Girgensohn 2
Lynn Wilcox 2
Mark Claypool 2
Wei Cheng 2
Jinjun Chen 2
Chunying Huang 2
Kuanta Chen 2
Wuchi Feng 2
Zhi Wang 2
Rynson Lau 2
Kiana Calagari 2
Sabu Emmanuel 2
Jiwu Huang 2
Siqi Shen 2
Guojun Qi 2
Jiunlong Huang 2
Min Xu 2
Stephen Gulliver 2
Xiaopeng Li 2
Hai Jin 2
Sebastien Mondet 2
Ming Yan 2
Peng Cui 2
Lawrence Rowe 2
Bohao Chen 1
Jyh Jang 1
Bingkun Bao 1
Philipp Schaber 1
Christoph Wesch 1
Petri Vuorimaa 1
Mohammad Motamedi 1
Xiao Ke 1
Andre Beck 1
Paichet Ng 1
Kangeun Jeon 1
Jiwu Huang 1
Shelley Buchinger 1
Renan Cattelan 1
Noel Massey 1
Jidi Zhao 1
Peter Fröhlich 1
Edel Jennings 1
Shivakant Mishra 1
Emily Provost 1
Fangxiang Feng 1
Ibrar Ahmad 1
Yi Yang 1
Julio Valdés 1
Olivier Meur 1
Giorgos Karafotias 1
Akiko Teranishi 1
Georgios Korres 1
Peter Schmidt 1
Zeno Albisser 1
Bharat Bhargava 1
Pablo Nunnez 1
Shahin Shayandeh 1
Minoru Nakayama 1
João Cangussu 1
Marcus Nyström 1
Chihyi Chiu 1
Yinghua Li 1
Boran Yang 1
Jianxun Liu 1
Wei Lei 1
Meikang Qiu 1
Lei Shu 1
Tony Sun 1
Xiangjun Li 1
Shuvendu Rana 1
Shenghua Zhong 1
Charith Perera 1
David Scruton 1
Alan Blackwell 1
Girija Chetty 1
Hayley Hung 1
Huaxin Xu 1
Chongwah Ngo 1
Samia Bouyakoub 1
Xuwen Yu 1
Marco Botta 1
Davide Cavagnino 1
Victor Pomponiu 1
Hong Shen 1
Dan Olsen 1
Dong Liu 1
Yichuan Wang 1
Tingan Lin 1
Yijuan Lu 1
Yiqun Li 1
Dan Gelb 1
Wuchang Feng 1
Ed Kaiser 1
Evangelos Georganas 1
Dacheng Tao 1
Sibaji Gaj 1
Hari Gupta 1
Benjamin Wah 1
Chihyi Chiu 1
Yisheng Xu 1
Nimesha Ranasinghe 1
Ankita Lathey 1
Qianqian Hu 1
Xiaofei He 1
Hareesh Ravi 1
Arige Subramanyam 1
Jiangchuan Liu 1
Ming Ouhyoung 1
Maxim Claeys 1
Steven Latré 1
Hui Xu 1
Zhenhui Yuan 1
Shengzhong Feng 1
Mao Ye 1
Feng Qiu 1
Jiebo Luo 1
Chinchen Chang 1
Thanh Dang 1
Hui Tang 1
Axel Carlier 1
Øystein Landsverk 1
Tao Mei 1
Ramakrishnan Kalpathi 1
Xiaolan Fu 1
Daviddagan Feng 1
Jianming Lv 1
Dongyu Liu 1
Jinhui Tang 1
Lynda Hardman 1
Alfio Ferrara 1
Qiang Chen 1
Xiangyu Chen 1
Anupama Mallik 1
Santanu Chaudhury 1
Luntian Mou 1
Jyh Jang 1
Hwangnam Kim 1
Seungho Yoo 1
Homer Chen 1
Razvan Pascanu 1
Yoshua Bengio 1
Rossano Schifanella 1
Filippo Menczer 1
Chun Chen 1
Bin Xu 1
Giuseppe Lisanti 1
Svebor Karaman 1
Iacopo Masi 1
Sailesh Bharati 1
Divyashri Bhat 1
Saverio Mascolo 1
Jun Wang 1
Dimitris Agrafiotis 1
Anthony Steed 1
David Roberts 1
Stephen TURNER 1
Chika Oshima 1
Yi Chen 1
Sushil Jajodia 1
Rui Li 1
Tiago Rodrigues 1
Maike Erdmann 1
Takahiro Hara 1
Yeehong Yang 1
Yintzu Lin 1
I Liu 1
Laura Toni 1
Mohsen Langroodi 1
Zhenhuan Gao 1
Qing Lei 1
John Lui 1
Maria Pimentel 1
Nina Hall 1
Joe Tullio 1
Frank Bentley 1
Johnny Shen 1
Diana Bental 1
Ioannis Mimtsoudis 1
Mike Gartrell 1
Wei Chen 1
Chunghua Chu 1
Yelin Kim 1
Ebroul Izquierdo 1
Khimya Khetarpal 1
Jun Zhang 1
Meng Wang 1
Dinh Phung 1
Renato Verdugo 1
Shahram Ghandeharizadeh 1
David Geerts 1
Martina Sasse 1
Pochiang Lin 1
Rainer Groh 1
Oleg Komogortsev 1
Yohan Jin 1
Sebastian Pannasch 1
Dapeng Wu 1
Cong Liu 1
Jingdong Wang 1
Maryam Amiri 1
Hussein Al Osman 1
Fan Wu 1
Qingquan Zhu 1
Kun Wang 1
Chihfan Hsu 1
Yijing Jiang 1
Yaujim Yip 1
Bruno Silva 1
Yan Liu 1
Guangjie Han 1
Shenglong Zou 1
Abu Rahman 1
Ying Yang 1
Zhipeng Chen 1
Rossano Gaeta 1
Abdelkader Belkhir 1
Christoph Rensing 1
Grenville Armitage 1
Wengang Zhou 1
Ramesh Jain 1
Donald Tanguay 1
Michael Goss 1
Edward Chang 1
Shihchuan Chiu 1
Brian Whitman 1
Viswanathan Swaminathan 1
Noah Snavely 1
Yunhua Deng 1
Sanguok Kum 1
Ingrid Visentini 1
Wenjun(Kevin) Zeng 1
Liangliang Cao 1
Xinglei Zhu 1
Tore Endestad 1
Paul Vigmostad 1
Aditya Kanetkar 1
Yong Wang 1
Xindi Shang 1
Dongni Ren 1
Abdel Al Tamimi 1
Panpan Niu 1
Shuqiang Jiang 1
Ping An 1
Ralf Steinmetz 1
Zhiyu Wang 1
Yugang Jiang 1
Haiwei Dong 1
Vasileios Papapanagiotou 1
Wengang Zhou 1
Ashkan Yazdani 1
Claudio Feijóo 1
Quan Sheng 1
Xin Zhao 1
Chaoyi Pang 1
Zengfu Wang 1
Alexander Loui 1
Nuria Oliver 1
Andrew Sung 1
Mengyu Qiao 1
Danny Kilis 1
Pavel Korshunov 1
Xiangyu Chen 1
Kazi Alam 1
Yun Ye 1
Jinxia Liu 1
Hairong Liu 1
Bo Fu 1
Dick Epema 1
Sina Jafarpour 1
Roelof Van Zwol 1
Yihan Pu 1
Michael Mandel 1
Mengdi Xu 1
Mubarak Shah 1
Abdulsalam Yassine 1
Eckehard Steinbach 1
Massimo Piccardi 1
Yang Cong 1
Jacky Chan 1
Weihua Zhuang 1
Florian Vandecasteele 1
Jonathan Doherty 1
Gary Wolverton 1
Stephen Davies 1
David Bull 1
David Ott 1
Peter Phillips 1
Yoonjoon Lee 1
Jirong Wen 1
Rich Edgecomb 1
Lingyu Duan 1
Shiping Chen 1
Mahmoud Hashemi 1
Euiseok Kim 1
Marius Tennøe 1
Shaohui Mei 1
Zhiyong Wang 1
Mingyi He 1
Ye Wang 1
Tieying Zhang 1
Ork Rooij 1
Yuru Lin 1
Heng Qi 1
Wenyu Qu 1
Laura Teodosio 1
Augusto Celentano 1
Gaurav Harit 1
Tiejun Huang 1
Gianluigi Ciocca 1
Shunyun Hu 1
Hui Wang 1
Lexing Xie 1
Yihsuan Yang 1
Douglas Eck 1
Rahul Sukthankar 1
Can Wang 1
Burak Çizmeci 1
Kun Zeng 1
Jayakrishnan Nair 1
Taku Komura 1
Minhson Dao 1
Vasileios Mezaris 1
Laurencetianruo Yang 1
Rajat Chakraborty 1
Paul McKevitt 1
Cong Wang 1
Amr Rizk 1
Thomas Zinner 1
Jason Moore 1
Ziad Sakr 1
Andrew Duchowski 1
Arzu Çöltekin 1
Carlo Colombo 1
Manoranjan Dash 1
Kazushi Nishimoto 1
Norihiro Hagita 1
Thinh Nguyen 1
Dian Tjondronegoro 1
Bir Bhanu 1
Kotaro Nakayama 1
Anlei Dong 1
Joseph Peters 1
Tzicker Chiueh 1
Yoav Etsion 1
Hui Li 1
Chitra Madhwacharyula 1
Duansheng Chen 1
Yijie Lu 1
Bruno Guilherme 1
Yousef Sharrab 1
Pasi Fränti 1
Liwei He 1
Cha Zhang 1
Giang Nguyen 1
Fulvio Babich 1
Alan Ip 1
Francesca Vatta 1
Ulf Myrestam 1
Xiaofei Liao 1
Zheng Zhang 1
Gunnar Harboe 1
Renfei Wang 1
Xitong Li 1
Xiaolin Li 1
James Williamson 1
Yogesh Rawat 1
Biao Zhu 1
Feng Xia 1
Nizar Sakr 1
Emil Petriu 1
Priyanka Singh 1
Ishwarya Thirunarayanan 1
Michael Riegler 1
Simone Santini 1
Phillipa Gill 1
Ram Dantu 1
Kalpathi Ramakrishnan 1
Boris Velichkovsky 1
Yue Zhang 1
Jens Helmert 1
Zhuo Wei 1
Kui Ren 1
Conghuan Ye 1
Jinyang Gao 1
Sheng Wang 1
Taotao Wu 1
Wang Miao 1
Geyong Min 1
Haozhe Wang 1
Danielle Sauer 1
Ragnhild Eg 1
Dahming Chiu 1
Sina Wetzel 1
Marc Davis 1
Alberto Piacenza 1
Marc Cavazza 1
Abukari Yakubu 1
Hongbo Zhang 1
Ivica Rimac 1
Klamer Schutte 1
Wessel Kraaij 1
Duc Dang-Nguyen 1
Giulia Boato 1
Luciana Pontello 1
Mingliang Zhou 1
Jianping Fan 1
Doug Williams 1
Marian Ursu 1
Inger Lindstedt 1
Vilmos Zsombori 1
Bin Cheng 1
Sixuan Ma 1
Junqi Deng 1
Xiping Hu 1
Florence Adegeye 1
Stefan Suette 1
Nick Taylor 1
Xiaojie Wang 1
Rachel Heck 1
Batu Truong 1
Qianni Zhang 1
Chidansh Bhatt 1
Fawaz Alsulaiman 1
Juan Silva 1
Nishant Agarwal 1
Scandar Copti 1
Sigrun Eskeland 1
Frank Shipman 1
Wenbo He 1
Pablo Corro 1
Hungkhoon Tan 1
Guojun Qi 1
Anirban Mahanti 1
Brian Bailey 1
Kang Li 1
Mohammad Alsmirat 1
Musab Al-Hadrusi 1
Chenhan Xu 1
Liangping Ma 1
Chienchung Shen 1
Yao Liu 1
Lei Guo 1
Guang Yang 1
Mario Gerla 1
Sunil Prabhakar 1
Shanyu Tang 1
Shivendra Shivani 1
Tommy Nilsson 1
Jukka Nurminen 1
Jihad Alja'Am 1
Huajie Cui 1
Jonathan Foote 1
Amiel Heyde 1
Xin Liu 1
Xiangdong Zhou 1
Austin Abrams 1
Harlyn Baker 1
Mankwan Shan 1
Xiangwen Chen 1
Steven Seitz 1
Elisabeth André 1
Jin Yuan 1
Eric Battenberg 1
Minghua Chen 1
Jon Crowcroft 1
Hao Fu 1
Cláudiorosito Jung 1
Amorntip Prayoonwong 1
Konstantin Miller 1
Zhijie Shen 1
Wei Wu 1
Shuang Wang 1
Honggang Hu 1
Dan Miao 1
Yan Lu 1
Xuelong Li 1
Christos Diou 1
Steve Uhlig 1
Brian Lee 1
Courtenay Cotton 1
Vyas Sekar 1
Jian Li 1
Xifeng Gao 1
Zhigang Deng 1
Zhenhua Qu 1
Tim Bauman 1
Chiapin Wang 1
Seungho Lim 1
Kyuho Park 1
Hui Zhao 1
Tien Dinh 1
Bengchin Ooi 1
ShaoJie Tang 1
Liwei Kuang 1
Kai Qiu 1
Saleh Almowuena 1
Ming Zhang 1
Mian Dong 1
Ole Granmo 1
Jørgen Michaelsen 1
Frank Eliassen 1
Jianzhong Sun 1
Liping Zhang 1
Dick Epema 1
Andreas Lund 1
Damien Marshall 1
Chabane Djeraba 1
Da Luo 1
Bernard Mérialdo 1
Michael Lyu 1
Ramazan Ayguun 1
Sebastiaan Meijer 1
Nina Bhatti 1
Lusong Li 1
Ioannis Kompatsiaris 1
Rodrigo Laiola Guimarães 1
Ekaterina Gonina 1
Penporn Koanantakool 1
Mikael Baillif 1
Jiangchuan Liu 1
Flora Li 1
John Boreczky 1
Víctor Valdés 1
Yucyuan Liou 1
Yongtao Hu 1
Jan Kautz 1
Mohammad Pakravan 1
Ying Zhang 1
Kuanwen Chen 1
Ailong Wang 1
Laura Natali 1
Khaled Diab 1
Wojciech Matusik 1
Remco Veltkamp 1
Jian Dong 1
Jun Tan 1
Minte Sun 1
Hoda Roodaki 1
Suya You 1
Ahmed Hamza 1
Shanghong Zhao 1
Shuicheng Yan 1
Genliang Guan 1
Cuixia Ma 1
Xinxi Wang 1
Yi Wang 1
Guangda Li 1
James Wyllie 1
Maryvonne Miquel 1
Sethuraman Panchanathan 1
Nicola Conci 1
David Suter 1
K Candan 1
Luca Aiello 1
Yue Gao 1
Hongxun Yao 1
Shulong Tan 1
Jiajun Bu 1
Ashkan Sobhani 1
Jason Grant 1
Xiao Xu 1
Christoph Bachhuber 1
Kien Hua 1
Xiaonan Luo 1
Xingang Liu 1
Jan Kleinrouweler 1
Sergio Cabrero 1
Phuoc Tran-Gia 1
Piotr Wiśniewski 1
Dan Simovici 1
Stanislas Lew 1
Thierry Urruty 1
Lester Loschky 1
Paul Sharkey 1
Chuanjun Li 1
Siqing Zheng 1
James Walkerdine 1
Shengwei Li 1
Henning Schulzrinne 1
Weiying Ma 1
Sunand Tullimas 1
Guoping Qiu 1
Chehua Yeh 1
Brian Barsky 1
Yehia Elkhatib 1
Ioannis Arapakis 1
Luoqi Liu 1
Shengyang Chen 1
Francisco Luque 1
Iris Galloso 1
Tongyu Zhan 1
João Gomes 1
Wei Liu 1
Rodrigo De Oliveira 1
Ramesh Jain 1
Khechai Sim 1
Yan Huang 1
Jungsan Lee 1
Qingzhong Liu 1
Laura Sesma-Sanchez 1
Sonia Porta 1
Reinier Van Leuken 1
Bingbing Ni 1
Song Ci 1
Wanmin Wu 1
Shu Shi 1
Sigurd Ljodal 1
Hwaijung Hsu 1
Richard Pazzi 1
Shengfeng Qin 1
Lexing Xie 1
David Hsu 1
Zheng Lu 1
Mary Buchanan 1
Walter Bender 1
Brian Smith 1
Narasimha Reddy 1
Laura Bratton 1
Goffredo Haus 1
Stefano Montanelli 1
Yadong Mu 1
Meng Wang 1
Shin'ichi Satoh 1
Gaurav Bhatnagar 1
Zibin Wang 1
Simone Bianco 1
Weiming Hu 1
Zhongfei Zhang 1
Mohamad Rabbath 1
Moses Pawar 1
Huiping Guo 1
Jim Kurose 1
Fabrício Benevenuto 1
Dimitrios Rafailidis 1
Weiqing Min 1
Alberto Blanc 1
Eilwoo Baik 1
Amit Pande 1
Fabrizio Guerrini 1
Shahid Akhtar 1
Yongfei Zhang 1
Bo Li 1
Farouk Messaoudi 1
Lahari Sengupta 1
Jim Crawford 1
Phani Kotharu 1
Helmut Hlavacs 1
Marco D'Orlando 1
César Teixeira 1
Rudinei Goularte 1
Ian Kegel 1
Andra Leurdijk 1
Luiz Soares 1
Guy Romano 1
Fei Hao 1
Geyong Min 1
Victor Leung 1
Edith Ngai 1
Idris Ibrahim 1
Hongxin Zhang 1
Robert Malkin 1
Datong Chen 1
Yang Yang 1
Xiguo Ma 1
Sameer Samarth 1
Eakta Jain 1
Friederike Eyssel 1
Jun Gao 1
Paula Navarrete 1
Liqi Shi 1
Jinsoo Kim 1
Wen Gao 1
Mark Coates 1
Kianoosh Mokhtarian 1
Kenneth Holmqvist 1
Niklas Carlsson 1
Xiaotao Liu 1
Rahul Chaudhari 1
Yandong Tang 1
Vineet Gokhale 1
Howard Leung 1
Ruchira Naskar 1
Xiansheng Hua 1
Lorenzo Seidenari 1
Claudio Baecchi 1
Haiyang Wang 1
Giuseppe Cofano 1
Anh Nguyen-Ngoc 1
Andrzej Beben 1
Lijun Yin 1
Nishan Canagarajah 1
Norman Murray 1
Nicolas Georganas 1
Junhu Wei 1
Wentong Cai 1
Junehwa Song 1
Liangtien Chia 1
Byunghee Jung 1
Virgílio Almeida 1
Jussara Almeida 1
Ramon Aparicio-Pardo 1
Kartik Gopalan 1
Dror Feitelson 1
Sergio Benini 1
Riccardo Leonardi 1
Giorgio Giacinto 1
Pedro Holanda 1
Jianting Guo 1
Yong Rui 1
Hangzai Luo 1
Maureen Thomas 1
Crysta Metcalf 1
Elaine Huang 1
Carlo Fantozzi 1
Yukwong Kwok 1
Kaikai Liu 1
Stuart Whyte 1
Richard Han 1
Qin Lv 1
Ruifan Li 1
Balasubramanian Raman 1
Meng Wang 1
Yenyu Lin 1
Liang Lin 1
Leon Pan 1
Garimella Sivaram 1
Suchendra Bhandarkar 1
Charles Krasic 1
Susmit Bagchi 1
Rong Cao 1
Junlin Ouyang 1
Hua Zhong 1
Zheng Yan 1
Zhiwen Yu 1
Yibin Li 1
Gang Chen 1
Nei Kato 1
Seungmin Rho 1
Yulei Wu 1
Wuchi Feng 1
Denny Stohr 1
Tsunghan Tsai 1
Zhan Ma 1
Mario Proença 1
Richardtianbai Ma 1
Saeed Aghaee 1
Michael Lew 1
Mohammad Hoque 1
Matti Siekkinen 1
Weiqi Luo 1
James Elder 1
Yi Chen 1
Abhidnya Deshpande 1
Trent Boulter 1
Xiansheng Hua 1
Christian Poellabauer 1
Yungyu Chuang 1
Kingshy Goh 1
Malcolm Slaney 1
Philip Chou 1
Lauro Snidaro 1
Wenhsiang Tsai 1
Pablo Serrano 1
Rodrigo Schramm 1
Helena Nunes 1
Chihhao Chiu 1
Guangtao Zhai 1
Wenping Wang 1
Zhengyu Deng 1
Chengwu Chen 1
Tianzhu Zhang 1
Hongying Yang 1
Ke Chen 1
Yosiyuki Takahasi 1
Kuowei Wu 1
Thanassis Rikakis 1
Joonwon Lee 1
Qingfang Zheng 1
Frederic Thouin 1
Parag Agarwal 1
Alejandro Jaimes 1
Junwen Wu 1
Mohan Trivedi 1
Javed Khan 1
Jonathan Walpole 1
Li Jie 1
Xing Jin 1
Bin Song 1
Honggang Wang 1
Chinghsien Hsu 1
Zenggang Xiong 1
Zhan Qin 1
Jingbo Yan 1
Cong Wang 1
Keke Gai 1
Zhong Ming 1
Jinhui Tang 1
Kenichi Suzuki 1
Feng Liu 1
Wei Chen 1
Chingling Fan 1
Muzhou Xiong 1
Suneeta Agarwal 1
Neeraj Kumar 1
Adelelu Jia 1
Thomas Haenselmann 1
Chuohao Yeo 1
Ioannis Ivrissimtzis 1
Sasu Tarkoma 1
Feng Wang 1
Ning Liu 1
Yirong Zhuang 1
Marco Grangetto 1
Lorenzo Bovio 1
Jianke Zhu 1
Derek Bunn 1
Hongjiang Zhang 1
Houqiang Li 1
Tom Malzbender 1
Munmun De Choudhury 1
Waipun Yiu 1
Naghmeh Khodabakhshi 1
Zhengchuan Chen 1
Yan Yan 1
Xianjun Hu 1
Ke Li 1
Qiong Wu 1
Pierre Boulanger 1
Yao Hu 1
Tarek Elgamal 1
Krzysztof Templin 1
Yanqiang Lei 1
Yingqing Xu 1
Longyu Zhang 1
Waichong Chia 1
Gareth Tyson 1
Shaoyan Sun 1
Bart Thomée 1
Benjamin Rainer 1
Eleni Kroupi 1
Haibo Li 1
Yang Yang 1
Quan Fang 1
Xue Li 1
Xuening Liu 1
Bo Li 1
Bashar Qudah 1
Susanne Boll 1
Jonathan Weir 1
Hongmei Liu 1
Hui Feng 1
Frederick Li 1
Lewis Li 1
Arantxa Villanueva 1
Victoria Ponz 1
Amit Sachan 1
Yanwei Liu 1
Espen Helgedagsrud 1
Henrik Alstad 1
Asgeir Mortensen 1
Deyu Chen 1
Maximilian Ott 1
Harish Katti 1
Xuanjia Qiu 1
Xiaosong Lou 1
Zhijie Shen 1
Hai Jin 1
Ryan Spicer 1
Yanming Shen 1
K Wijayaratne 1
Polle Zellweger 1
José MartíNez 1
Bo Geng 1
Albert Banchs 1
Prabin Bora 1
Zheng Yan 1
Ke Gu 1
Xiaokang Yang 1
Ellen Do 1
Shengsheng Qian 1
Piotr Didyk 1
Jingdong Wang 1
Xuyong Yang 1
Qi Wang 1
Lei Pang 1
Mulin Chen 1
Stefano Petrangeli 1
Filip De Turck 1
Jean Vesin 1
Junliang Xing 1
Manoj Prasad 1
Tracy Hammond 1
Hanwang Zhang 1
Yue Gao 1
Alaa Halawani 1
Wei Jiang 1
Hui Zhang 1
Branka Lakic 1
Henrique Da Silva 1
Mauro Cherubini 1
Arthur Money 1
John Kassebaum 1
Rafael Cabeza 1
Bo Wang 1
Jinqiao Wang 1
Abu Rahman 1
Ulrich Newmann 1
Pooja Agarwal 1
Felix Yu 1
Vincent Charvillat 1
Mikkel Næss 1
Junliang Xing 1
Kai Hwang 1
Tatsheng Chua 1
Kanav Kahol 1
Priyamvada Tripathi 1
Troy McDaniel 1
Daqing Zhang 1
Markus Schedl 1
Silvana Castano 1
Anne Arigon 1
Luca Ludovico 1
Jing Liu 1
Peter Knees 1
Ali El Essaili 1
Bo Zhang 1
Francesco De Natale 1
Yunfei Chen 1
Jongtack Jung 1
Jianguo Jiang 1
Simone Milani 1
Patrick Flynn 1
Nicolas Alt 1
Baojie Fan 1
Lianqing Liu 1
Haibin Yu 1
Edip Demirbilek 1
Hanhui Li 1
Hassan Omar 1
Peng Li 1
Karel Vandenbroucke 1
Dimitri Schuurman 1
Steven Verstockt 1
Stefano D'Aronco 1
Linxie Tang 1
Jinhui Tang 1
Luca De Cicco 1
Piotr Krawiec 1
Dario Comanducci 1
Suiping Zhou 1
Ron Shacham 1
Tiecheng Liu 1
John Kender 1
Suhuai Luo 1
Stefanos Antaris 1
Karine Pires 1
Jinhan Park 1
Yowjian Lin 1
Gang Peng 1
Lan Huang 1
Dan Tsafrir 1
Nicola Adami 1
Philipp Gysel 1
Jixiang Du 1
Jialin Peng 1
Hao Zhang 1
Maaike De Boer 1
Xupeng Lin 1
Yonghong Tian 1
Menglin Jiang 1
Mingju Wu 1
Gerald Kunzmann 1
Xuanhui Wang 1
Dong Xu 1
Ou Wu 1
Shingchern You 1
Yuching Lin 1
Subhabrata Bhattacharya 1
Fairouz Hussein 1
Yunsheng Yang 1
Jean Grégoire 1
Subhasis Chaudhuri 1
Edmond Ho 1
Kaoru Ota 1
Sergio Mena 1
Parisa Pouladzadeh 1
Tiberio Uricchio 1
Andrea Ferracani 1
Marco Bertini 1
Cong Zhang 1
Jordi Batalla 1
Nacim Ihadaddene 1
Paul Dickerson 1
Herngyow Chen 1
Surong Wang 1
Srisakul Thakolsri 1
Elaine Chew 1
Adrien Joly 1
Shojiro Nishio 1
Yang Li 1
Yu Zhang 1
Shihchia Huang 1
Jaling Wu 1
Prasant Mohapatra 1
Tyler Ballast 1
Shannon Chen 1
Juha Vierinen 1
Philippe Mulhem 1
Julie Porteous 1
Soheil Ghiasi 1
Luca Piras 1
João Cardoso 1
Olga Goussevskaia 1
Adlen Ksentini 1
Radu Mariescu-Istodor 1
Yuli Gao 1
Ana Silva 1
Peijia Zheng 1
Philippe Bertin 1
Jinye Peng 1
Julia Sussner 1
Lex Stein 1
Mingjie Jiao 1
Sergio Canazza 1
Wenyan Hu 1
Min Liang 1
Fraser Blackmun 1
Meiyii Lim 1
Seshadri Venkatagiri 1
Ross Maciejewski 1
Michael Wallick 1
Howard Wactlar 1
Herman Engelbrecht 1
John Shea 1
Shihyao Lin 1
Konstantin Pogorelov 1
Changnian Zhang 1
Wenkuang Kuo 1
Weiwei Xu 1
Shengmin Liu 1
Jaegeuk Kim 1
Feng Liu 1
Prakash Kolan 1
Chris Bleakley 1
Bo Yang 1
Jack Jansen 1
Hsinmin Wang 1
Robert Rieger 1
Ashvin Goel 1
James Clark 1
Hao Qin 1
Xingzi Wen 1
Francisco Herrera 1
Shangguang Wang 1
Ao Zhou 1
Fangchun Yang 1
Fang Xu 1
Meihui Zhang 1
Wei Wang 1
Haibo Chen 1
Kianlee Tan 1
Maha Abdallah 1
Wanchun Dou 1
Zhangyu Chang 1
Jun Mi 1
Xiangyang Xue 1
Mika Tuomola 1
Terence Wright 1
Niccolò Pretto 1
Elizabeth Papadopoulou 1
M Williams 1
Junho Ahn 1
John Oommen 1
Hengtao Shen 1
Mauricio Orozco 1
John Gilmore 1
Sanjeev Koppal 1
Thomas De Lange 1
Xue Liu 1
Saraju Mohanty 1
Miguel Nussbaum 1
Yinpeng Chen 1
Dawoon Jung 1
Yuri Ivanov 1
William Seager 1
Mark Corner 1
Frédéric Boudon 1
Wei Wei 1
Zheng Guo 1
Yong Wei 1
Tsungnan Lin 1
Yowon Jeong 1
Ingmar Franke 1
Chonggang Wang 1
Ruyan Wang 1
Jun Liu 1
Yongdong Wu 1
Fanyu Bu 1
Xiangbo Shu 1
Jiajia Liu 1
Hirotaka Ujikawa 1
Chunhua Hu 1
Jia Hu 1
Mengbai Xiao 1
Xin Li 1
Zhenhua Li 1
Alexander Hauptmann 1
Medy Sanadidi 1
Carl Hogsden 1
Mika Aalto 1
Abdelwahab Hamam 1
Matthew Cooper 1
Fadi Dornaika 1
Derjiunn Deng 1
Cees Snoek 1
Lingjyh Chen 1
Viktor Eide 1
Jianfei Cai 1
Huahui Wu 1
Yicheng Tu 1
Joel Rodrigues 1
Mi Jing 1
Matthew White 1
Long Vu 1
Jin Liang 1
Dhiraj Joshi 1
Pietro Pala 1
Wanlei Zhao 1
S Chan 1
Marek Meyer 1
Mingfang Weng 1
Chenghsin Hsu 1
Mark Hendrikx 1
Yantao Zheng 1
Robert Pless 1
W Culbertson 1
Lifeng Sun 1
Matthew Turk 1
Richard Szeliski 1
Zixia Huang 1
Xianglong Liu 1
Yadong Mu 1
Bo Lang 1
Xinmei Tian 1
Haakon Riiser 1
Paul Patras 1
Lei Cao 1
Haojun Wu 1
Weita Chu 1
Yizhou Yu 1
Xiangyang Wang 1
Minghsuan Yang 1
Zhong Zhou 1
Liquan Shen 1
Liqiang Nie 1
Qinghua Huang 1
Haitao Li 1
Tianzhu Zhang 1
Song Tan 1
Jeroen Famaey 1
Nishanth Sastry 1
Carlos Martin 1
Robert Walz 1
Karsten Schwan 1
Joeri Van Der Velden 1
Jongseung Park 1
Irwin Sobel 1
Beitao Li 1
Lei Zhang 1
Rainer Lienhart 1
Michael Driscoll 1
Kurt Keutzer 1
Gian Foresti 1
Yalin Lee 1
Heng Liu 1
Tanima Dutta 1
Jingxi Xu 1
Alvin Junus 1
Hanwang Zhang 1
Xiongkuo Min 1
Adam Wolisz 1
Chihwei Lin 1
Shenchi Chen 1
Zhaoyang Zhang 1
Beomjoo Seo 1
Weiming Zhang 1
Nenghai Yu 1
Jingjing Fu 1
Maria Merani 1
Chen Zhao 1
Bisheng Chen 1
Ligang Zheng 1
Lexing Xie 1
Mansoor Ebrahim 1
Anastasios Delopoulos 1
Weisi Lin 1
Touradj Ebrahimi 1
Guillermo Cisneros 1
Zhihan Lv 1
Hao Yin 1
Chuang Lin 1
Mário Freire 1
Paulo Monteiro 1
Harry Agius 1
Michelle Zhou 1
Yunqing Shi 1
Zhengding Lu 1
Mikel Ariz 1
Tam Nguyen 1
Kazuya Sakai 1
Wei Guan 1
Shafiq Réhman 1
Murat Russell 1
Sen Wang 1
Daniel Ellis 1
Pedro Inácio 1
Dong Xu 1
Caiming Zhang 1
Qiang Chen 1
Weishinn Ku 1
Shujie Liu 1
Roy Campbell 1
Brian Lee 1
Junshi Huang 1
Anoop Rajagopal 1
Qiufang Fu 1
Xueqi Cheng 1
Weisong Shi 1
Wolfgang Klas 1
Hiranmay Ghosh 1
Q Wu 1
Wen Gao 1
Dirk Staehle 1
Jihoon Ryoo 1
Jiali Li 1
Xiangnan Kong 1
Haiqiang Zuo 1
Philipp Sandhaus 1
Sukkyu Lee 1
Joan Biel 1
Jiebo Luo 1
Xiaotong Yuan 1
Giancarlo Calvagno 1
Hao Hu 1
Shuai Wang 1
Huijie Fan 1
Huaici Zhao 1
Zhuo Su 1
Loyao Yeh 1
Kevin Curran 1
Andrzej Chydziñski 1
John Rae 1
Busung Lee 1
Dorothy Rachovides 1
Senching Cheung 1
Sakirearslan Ay 1
Keith Ross 1
Yanjiang Yang 1
Prabhu Natarajan 1
Dilip Krishnappa 1
Tongtao Zhang 1
Håkon Stensland 1
Magnus Stenhaug 1
Raoul Rivas 1
Mohan Kankanhalli 1
Yongjin Liu 1
Yong Rui 1
Francis Lau 1
Zhenhua Li 1
Fei Li 1
Anne Tchounikine 1

Affiliation Paper Counts
Austrian Institute of Technology 1
Orange Labs 1
Singapore University of Technology and Design 1
Laboratoire d'Automatique, Genie Informatique et Signal 1
Indian Institute of Technology Rajasthan 1
Guangdong University of Petrochemical Technology 1
University of Wales Trinity Saint David 1
FHS St. Gallen University of Applied Sciences 1
Microsoft Technology Centers 1
IBM Canada Ltd. 1
IBM China Company Limited 1
CSIRO Data61 1
NYU Tandon School of Engineering 1
National Taichung University of Science and Technology 1
Universite Paris Sorbonne - Paris IV 1
Deakin University 1
Karolinska University Hospital 1
Agder University College 1
Baerum Hospital 1
University of Coimbra 1
University of Surrey 1
Indiana University 1
University of Canberra 1
National Taiwan Normal University 1
University of Delaware 1
North Georgia College & State University 1
National Taiwan Ocean University 1
University of Massachusetts Boston 1
National University of Defense Technology China 1
National Central University Taiwan 1
University of Missouri System 1
Sam Houston State University 1
University of Tokyo 1
Guangzhou University 1
University of Teesside 1
Center For Research And Technology - Hellas 1
University of Nebraska - Lincoln 1
Clemson University 1
National Chengchi University 1
Institute for Research in IT and Random Systems 1
University of Rochester 1
University of Edinburgh 1
Universidad de Granada 1
University of the Basque Country 1
State University of Londrina 1
New Mexico Institute of Mining and Technology 1
TELECOM ParisTech 1
Cancer Registry of Norway Institute of Population-Based Cancer Research 1
The University of North Carolina Wilmington 1
Dalian Maritime University 1
Kent State University 1
EURECOM Ecole d'Ingenieurs & Centre de Recherche en Systemes de Communication 1
Cisco Systems 1
Institut Dalle Molle D'intelligence Artificielle Perceptive 1
California State University Los Angeles 1
Indian Institute of Technology Roorkee 1
Japan National Institute of Information and Communications Technology 1
Pontifical Catholic University of Rio de Janeiro 1
Eindhoven University of Technology 1
Saarland University 1
York University Canada 1
University of Kuwait 1
Yarmouk University 1
University of Peshawar 1
HEC School of Management 1
Tata Consultancy Services India 1
General Hospital of People's Liberation Army 1
ITMO University 1
University of Qatar 1
Adobe Systems Incorporated 1
Samsung Electronics, India Software Operations Ltd. 1
Hebei Academy of Sciences 1
Hunan University of Commerce 1
British Broadcasting Corporation 1
Sybase Inc. 1
Laboratoire de Biometrie et Biologie Evolutive, Villeurbanne 1
Bowie State University 1
Sungkyul Christian University 1
National Institute of Technology Kurukshetra 1
Kansas State University 1
China Telecommunications 1
Thapar University 1
Advanced Telecommunications Research Institute International (ATR) 1
Guangdong Polytechnic Normal University 1
Royal Institute of Technology 1
University of Ontario Institute of Technology 1
MIT Media Laboratory 1
Henan University 1
Uppsala University 1
Northumbria University 1
Institute of High Performance Computing, Singapore 1
Johns Hopkins University 1
Yale University 1
National Kaohsiung Marine University Taiwan 1
Google Inc. 1
National Changhua University of Education 1
Cornell University 1
Malmo University 1
Chung Hua University 1
Waterford Institute of Technology 1
Tohoku University 1
Hong Kong Polytechnic University 1
University of Massachusetts Dartmouth 1
Silesian Polytechnic University, Gliwice 1
University of California , Merced 1
National Research Council Canada 1
University of Minnesota Duluth 1
Harvard University 1
Cairo University 1
Florida Institute of Technology 1
University of Kent 1
Hohai University 1
King's College London 1
Auburn University 1
Air Force Research Laboratory Information Directorate 1
Open University 1
Incheon National University 1
University of Windsor 1
University of Zurich 1
INRIA Institut National de Rechereche en Informatique et en Automatique 1
Ca' Foscari University of Venice 1
China Agricultural University 1
Federal University of Bahia 1
Federal University of Sao Carlos 1
Zhejiang Wanli University 1
Hong Kong Baptist University 1
Eastman Kodak Company 1
Muroran Institute of Technology 1
University of Washington, Seattle 1
University of Pittsburgh 1
University of Bielefeld 1
University of Kentucky 1
Carleton University 1
Fuzhou University 1
Hongik University 1
National University of Tainan Taiwan 1
Nankai University 1
Vienna University of Technology 1
University of South Carolina 1
South Dakota School of Mines & Technology 1
VMware, Inc 2
Indraprastha Institute of Information Technology Delhi 2
Sunway University 2
Kodak Research Laboratories 2
University of Stellenbosch 2
Ohio State University 2
Warsaw University of Technology 2
University of Modena and Reggio Emilia 2
Indian Institute of Technology, Kharagpur 2
Feng Chia University 2
University College Dublin 2
University of Houston 2
Federal University of Rio Grande do Sul 2
The University of North Carolina at Charlotte 2
National Chung Cheng University 2
Utrecht University 2
Australian National University 2
IBM Almaden Research Center 2
University of Adelaide 2
Telecom Research Center Vienna 2
Washington University in St. Louis 2
Goldsmiths, University of London 2
Queensland University of Technology 2
RMIT University 2
Japan Advanced Institute of Science and Technology 2
Technical University of Berlin 2
University of Reading 2
University of Milan - Bicocca 2
Oldenburger Forschungs- Und Entwicklungsinstitut fur Informatik-Werkzeuge Und -Systeme 2
University of Antwerp 2
Yuan Ze University 2
University of Waterloo 2
National Cheng Kung University 2
University of Nottingham 2
Florida International University 2
INSA Lyon 2
Instituto de Telecomunicacoes 2
Xi'an Jiaotong University 2
Indian Institute of Technology (Banaras Hindu University) 2
Alpen-Adria-Universit├Ąt Klagenfurt 2
Leiden University 2
Netherlands Organisation for Applied Scientific Research - TNO 2
University of Oldenburg 2
Communication University of China 2
Johannes Kepler University Linz 2
University of Durham 2
Massachusetts Institute of Technology 2
Pace University 2
National Chi Nan University 2
University of Tehran 2
Nippon Telegraph and Telephone Corporation 2
University Michigan Ann Arbor 2
Roehampton University 2
Stevens Institute of Technology 2
Sharif University of Technology 2
Lund University 2
The University of Georgia 2
University of Regina 2
Texas State University-San Marcos 2
Swinburne University of Technology 2
Tokyo Institute of Technology 2
University of Cagliari 2
International Computer Science Institute 2
University of Sciences and Technology Houari Boumediene 2
Institut National de la Recherche Scientifique 2
DoCoMo Communications Laboratories Europe GmbH 2
National Institute of Telecommunications, Poland 2
Universidad Carlos III de Madrid 3
University of Electronic Science and Technology of China 3
Hebrew University of Jerusalem 3
University of Sao Paulo 3
University of Salford 3
Fudan University 3
University of Wurzburg 3
Oregon State University 3
Indian Institute of Technology, Bombay 3
University of Saskatchewan 3
Institute of Acoustics Chinese Academy of Sciences 3
IBM Thomas J. Watson Research Center 3
University of Trieste 3
Singapore Management University 3
Georgia Institute of Technology 3
Binghamton University State University of New York 3
University of Alabama in Huntsville 3
Chongqing University of Posts and Telecommunications 3
East China Normal University 3
University of Notre Dame 3
Xi'an Institute of Optics and Precision Mechanics Chinese Academy of Sciences 3
Lancaster University 3
Osaka University 3
University of North Texas 3
South China University of Technology 3
Hunan University of Science and Technology 3
University of Sydney 3
University of Udine 3
University of Vienna 3
Stony Brook University 3
Universidad Autonoma de Madrid 3
Polytechnic Institute of Bari 3
Research Organization of Information and Systems National Institute of Informatics 3
University of California, Riverside 3
Queen's University Belfast 3
University of California, San Diego 3
Shandong University 3
Umea University 3
Saint Francis Xavier University 3
Indian Institute of Technology, Delhi 3
University of Eastern Finland 3
Communaute d'Universites et d'Etablissements Lille Nord de France 3
Qatar Computing Research institute 3
Simula Research Laboratory 4
University of Beira Interior 4
University of Texas at San Antonio 4
Korea University 4
University of Illinois 4
China University of Geosciences, Wuhan 4
Brigham Young University 4
University of Montreal 4
Telefonica 4
The University of British Columbia 4
University of Newcastle, Australia 4
State University of New York at Albany 4
National Taipei University of Technology 4
King Saud University 4
Indian Institute of Science, Bangalore 4
Liaoning Normal University 4
Harbin Institute of Technology 4
University of Bristol 4
University of Ulster 4
National Chiayi University 4
Queen Mary, University of London 4
University of Connecticut 4
Shanghai University 4
University of California, Los Angeles 4
University of California, Santa Barbara 4
University of Alberta 4
Nanjing University 4
University of Padua 5
McGill University 5
Telecom Bretagne 5
University of Brescia 5
Aristotle University of Thessaloniki 5
University of Toronto 5
Texas A and M University 5
New Jersey Institute of Technology 5
University of Technology Sydney 5
Shanghai Jiaotong University 5
The University of North Carolina at Chapel Hill 5
University of Exeter 5
Technical University of Madrid 5
Pontificia Universidad Catolica de Chile 5
University of Milan 5
University of Queensland 5
University of Wisconsin Madison 5
University of Colorado at Boulder 6
Pennsylvania State University 6
Northwestern Polytechnical University China 6
University of California, Irvine 6
Purdue University 6
Indian Institute of Technology, Guwahati 6
Worcester Polytechnic Institute 6
National Chiao Tung University Taiwan 6
Beijing University of Posts and Telecommunications 6
National Tsing Hua University 6
Technical University of Dresden 6
University College London 6
Microsoft Corporation 6
Inha University, Incheon 6
Institute of Computing Technology Chinese Academy of Sciences 6
New York University Abu Dhabi 6
Huaqiao University 7
Nanjing University of Post and TeleCommunications 7
Nanjing University of Science and Technology 7
University of Turin 7
University of Florida 7
Peking University 7
University of Trento 7
University of Winnipeg 7
George Mason University 7
Athlone Institute of Technology 7
Shenyang Institute of Automation Chinese Academy of Sciences 7
Dublin City University 7
Ghent University 7
University of Calgary 8
University of Amsterdam 8
Chinese University of Hong Kong 8
Wayne State University 8
University of California, Davis 8
Microsoft Research 8
University of Cambridge 9
The University of Hong Kong 9
Carnegie Mellon University 9
National University of Ireland, Maynooth 9
HP Labs 9
Heriot-Watt University, Edinburgh 9
University at Buffalo, State University of New York 9
Center for Mathematics and Computer Science - Amsterdam 9
Xidian University 9
University of Mannheim 10
Dalian University of Technology 10
Universite de Toulouse 10
Yahoo Research Labs 10
Korea Advanced Institute of Science & Technology 10
Federal University of Minas Gerais 10
FX Palo Alto Laboratory 10
Beihang University 10
Shenzhen University 11
Swiss Federal Institute of Technology, Lausanne 11
Aalto University 11
Portland State University 11
University of Central Florida 11
Technical University of Munich 12
Brunel University London 12
University of Southern California 12
University of Texas at Dallas 13
Academia Sinica Taiwan 13
Delft University of Technology 13
Curtin University of Technology, Perth 13
Motorola 13
University of Florence 13
University of Massachusetts Amherst 14
Institute of Automation Chinese Academy of Sciences 14
Technical University of Darmstadt 14
Zhejiang University 15
Hefei University of Technology 15
Nanyang Technological University 16
City University of Hong Kong 17
University of California, Berkeley 17
Columbia University 19
National Taiwan University 19
Institute for Infocomm Research, A-Star, Singapore 19
Sun Yat-Sen University 20
Huazhong University of Science and Technology 21
Tsinghua University 21
University of Science and Technology of China 22
Arizona State University 24
Hong Kong University of Science and Technology 24
University of Illinois at Urbana-Champaign 25
University of Oslo 27
Microsoft Research Asia 32
Chinese Academy of Sciences 34
Simon Fraser University 34
University of Ottawa, Canada 39
National University of Singapore 126

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)

Volume 13 Issue 4, October 2017
Volume 13 Issue 3s, August 2017 Special Section on Deep Learning for Mobile Multimedia and Special Section on Best Papers from ACM MMSys/NOSSDAV 2016
Volume 13 Issue 3, August 2017
Volume 13 Issue 2, May 2017
Volume 13 Issue 1, January 2017

Volume 12 Issue 5s, December 2016 Special Section on Multimedia Big Data: Networking and Special Section on Best Papers From ACM MMSYS/NOSSDAV 2015
Volume 12 Issue 4s, November 2016 Special Section on Trust Management for Multimedia Big Data and Special Section on Best Papers of ACM Multimedia 2015
Volume 12 Issue 4, August 2016
Volume 12 Issue 3, June 2016
Volume 12 Issue 2, March 2016

Volume 12 Issue 1s, October 2015 Special Issue on Smartphone-Based Interactive Technologies, Systems, and Applications and Special Issue on Extended Best Papers from ACM Multimedia 2014
Volume 12 Issue 1, August 2015
Volume 11 Issue 4, April 2015
Volume 11 Issue 2s, February 2015 Special Issue on MMSYS 2014
Volume 11 Issue 3, January 2015

Volume 11 Issue 2, December 2014
Volume 11 Issue 1s, September 2014 Special Issue on Multiple Sensorial (MulSeMedia) Multimodal Media : Advances and Applications
Volume 11 Issue 1, August 2014
Volume 10 Issue 4, June 2014
Volume 10 Issue 3, April 2014
Volume 10 Issue 2, February 2014
Volume 10 Issue 1s, January 2014 Special issue of best papers of ACM MMSys 2013 and ACM NOSSDAV 2013

Volume 10 Issue 1, December 2013
Volume 9 Issue 1s, October 2013 Special Sections on the 20th Anniversary of ACM International Conference on Multimedia, Best Papers of ACM Multimedia 2012
Volume 9 Issue 4, August 2013
Volume 9 Issue 3, June 2013
Volume 9 Issue 2, May 2013
Volume 9 Issue 1, February 2013

Volume 8 Issue 4, November 2012
Volume 8 Issue 3s, September 2012 Special section of best papers of ACM multimedia 2011, and special section on 3D mobile multimedia
Volume 8 Issue 2S, September 2012 Special Issue on Multimedia Security
Volume 8 Issue 3, July 2012
Volume 8 Issue 2, May 2012
Volume 8 Issue 1S, February 2012 Special Issue on P2P Streaming
Volume 8 Issue 1, January 2012

Volume 7 Issue 4, November 2011
Volume 7S Issue 1, October 2011 Special section on ACM multimedia 2010 best paper candidates, and issue on social media
Volume 7 Issue 3, August 2011
Volume 7 Issue 2, February 2011
Volume 7 Issue 1, January 2011

Volume 6 Issue 4, November 2010
Volume 6 Issue 3, August 2010
Volume 6 Issue 2, March 2010
Volume 6 Issue 1, February 2010

Volume 5 Issue 4, October 2009
Volume 5 Issue 3, August 2009

Volume 5 Issue 2, November 2008
Volume 5 Issue 1, October 2008
Volume 4 Issue 4, October 2008
Volume 4 Issue 3, August 2008
Volume 4 Issue 2, May 2008
Volume 4 Issue 1, January 2008

Volume 3 Issue 4, December 2007
Volume 3 Issue 3, August 2007
Volume 3 Issue 2, May 2007
Volume 3 Issue 1, February 2007

Volume 2 Issue 4, November 2006

Volume 2 Issue 3, August 06
Volume 2 Issue 2, May 2006
Volume 2 Issue 1, February 2006
Volume 1 Issue 4, November 2005
Volume 1 Issue 3, August 2005
Volume 1 Issue 2, May 2005
Volume 1 Issue 1, February 2005
All ACM Journals | See Full Journal Index

Search TOMM
enter search term and/or author name