Publications

Share         

White Paper
  • Deep Learning Algorithms with Applications to Video Analytics for A Smart City: A Survey
    ​Li Wang, Gang Wang

    Abstract: Deep learning has recently achieved very promising results in a wide range of areas such as computer vision, speech recognition and natural language processing. It aims to learn hierarchical representations of data by using deep architecture models. In a smart city, a lot of data (e.g. videos captured from many distributed sensors) need to be automatically processed and analyzed. In this paper, we review the deep learning algorithms applied to video analytics of smart city in terms of different research topics: object detection, object tracking, face recognition and image classification.



Conference Journal Publications
Visual Object Search
  • Object Instance Search in Videos via Spatio-Temporal Trajectory Discovery
    Jingjing Meng, Junsong Yuan, Jiong Yang, Gang Wang, Yap-Peng Tan, IEEE Transactions on Multimedia, 2016

  • Query-Adaptive Logo Search using Shape-Aware Descriptors
    Sreyasee Das Bhattacharjee, Junsong Yuan, Yap-Peng Tan, Lingyu Duan, ACMMULTIMEDIA 2015

  • Tagging the Shoe Images by Semantic Attributes
    Huijing ZHAN, Sheng LI and Alex KOT, 2015 IEEE International Conference on Digital Signal Processing (DSP)

  • Deep Hashing for Compact Binary Codes Learning
    Venice Erin Liong, Jiwen Lu, Gang Wang, Pierre Moulin, Jie Zhou, 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015)

  • Feature Weighting in Visual Product Recognition
    Wen Zhang, Kim-Hui Yap, Da-Jiang Zhang, Zhenwei Miao, 2015 IEEE International Symposium on Circuits and Systems (ISCAS)

  • Hybrid Feature-Based Wallpaper Visual Search
    Kim-Hui Yap, Zhenwei Miao, 2015 IEEE International Symposium on Circuits and Systems (ISCAS)

  • Complementary Feature Extraction for Branded Handbag Recognition
    Yan Wang, Sheng Li, and Alex C. Kot, 2014 IEEE International Conference on Image Processing (ICIP)

  • Mobile product recognition with efficient bag-of-phrase visual Search
    Dajiang Zhang, Kim-Hui Yap and Sinduja Subbhuraam, 2014 International Symposium on Communications, Control, and Signal Processing (ISCCSP) ​

  • Context-Aware Discovery of Visual Co-occurre​nce Patterns
    Hongxing Wang, Junsong Yuan, Ying Wu, IEEE Transactions on Image Processing (TIP), Vol. 23(2014), Issue 4, pp.1805 - 1819, April 2014

  • Category-Separating Strategy for Branded Handbag Recognition
    Yan Wang, Sheng Li, Alex C. Kot, 2014 International Symposium on Communications, Control, and Signal Processing (ISCCSP)

  • isual Pattern Discovery in Image andVideo Data: A Brief Survey
    Hongxing Wang, Gangqiang Zhao, Junsong Yuan, Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery (WIREs DMKD), Vol.4 (2014), Issue 1, pp.24 – 37, January/February 2014

  • Object instance search in videos
    Jingjing Meng, Junsong Yuan, Gang Wang, Jianbo Xu, 2013 9th International Conference on Information, Communications and Signal Processing (ICICS)

  • Randomized Visual Phrases for Object Search
    Yuning Jiang, Jingjing Meng & Junsong Yuan, 2012 IEEE Computer Vision and Pattern Recognition (CVPR)

  • Rapid Object Search Engine for Contextual Advertisement​
    Yuning Jiang, Junsong Yuan & Jingjing Meng,2012 ACM Multimedia Conference (ACMMM),(demo paper)



  • Compact Descriptors for Visual Search
  • ​Mobile Media Communication, Processing, and Analysis: a review of recent advances​
    Wen Gao, Ling-Yu Duan, Jun Sun, Junsong Yuan, Yonggang Wen, Yap-Peng Tan, Jianfei Cai, Alex C. Kot, 2013 IEEE International Symposium on Circuits and Systems (ISCAS), pp.869~872

  • Compact Descriptors for Mobile Visual Search and MPEG CDVS Standardization
    Ling-Yu Duan, Feng Gao, Jie Chen, Jie Lin, Tiejun Huang , 2013 IEEE International Symposium on Circuits and Systems (ISCAS), pp.885~888

  • ​Robust Fisher Codes for Large Scale Image Retrieval
    Jie Lin, Ling-Yu Duan, Tiejun Huang, Wen Gao, 2013 International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp.1513~1517

  • On the Interoperability of Local Descriptors Compression
    Jie Chen, Ling-Yu Duan, Jie Lin, Rongrong Ji, Tiejun Huang, Wen Gao, 2013 International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp.1518~1522

  • Location Discriminative Vocabulary Coding for Mobile Landmark Search
    Rongrong Ji, Ling-Yu Duan, Jie Chen, Hongxun Yao, Junsong Yuan, Yong Rui, Wen Gao , International Journal of Computer Vision, Vol.96, Issue 3: 290~314, July 2011

  • Learning Compact Visual Descriptor for Low Bit Rate Mobile Landmark Search
    Rongrong Ji, Ling-Yu Duan, Jie Chen, Hongxun Yao, Tiejun Huang, Wen Gao, Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI 2011), pp.2456~2463


  • Visual Object Segmentation
  • Recurrent Attentional Networks for Saliency Detection
    Jason Kuen, Zhenhua Wang, and Gang Wang, CVPR, 2016

  • Group Saliency Propagation for Large Scale and Quick Image Co-Segmentation Koteswar Rao Jerripothula, Jianfei Cai, Junsong Yuan, 2015 IEEE International Conference on Image Processing (ICIP)

  • Quality Guided Handbag Segmentation
    Yan WANG, Sheng LI and Alex KOT, 2015 IEEE International Conference on Digital Signal Processing (DSP)

  • On Multiple Image Group Cosegmentation(Best Student Paper Honorable Mention Award)
    Fanman Meng, Jianfei Cai, Hongliang Li, 2014 Asian Conference on Computer Vision (ACCV)​

  • Automatic Image Co-segmentation Using Geometric Mean Saliency
    Koteswar Rao Jerripothula, Jianfei Cai, Fanman Meng, Junsong Yuan, 2014 IEEE International Conference on Image Processing (ICIP)

  • Object-level image segmentation using low level cues
    H. Zhu, J. Zheng, J. Cai, and N. M. Thalmann , IEEE Transactions on Image Processing,Volume 22, Issue 10, pp.4019 -4027,June 2013

  • Interactive object segmentation from multi-view images​
    T. Nguyen, J. Cai, J. Zheng; J. Li ,Journal of Visual Communications and Image Representation, Volume 24, Issue 4, pp. 477 - 485, May 2013

  • Robust interactive image segmentation using convex active contours
    T. Nguyen, J. Cai, J. Zhang and J. Zheng , IEEE Transactions on Image Processing (TIP), vol. 21, no. 8, pp.3734-3743, Aug 2012

  • User-friendly interactive image segmentation through unified combinatorial user inputs​
    W. Yang, J. Cai, J. Zheng, J. Luo, IEEE Transactions on Image Processing, vol. 19, no. 9, pp. 2470-2479, Sept. 2010.


  • Visual Anomaly Detection
  • Video Anomaly Search in Crowded Scenes via Spatio-Temporal Motion Context
    Yang Cong, Junsong Yuan & Yandong Tang, IEEE Transactions on Information Forensics & Security, Volume 8, Issue 10, pp. 1590 - 1599, July 2013

  • Abnormal Event Detection in Crowded Scenes using Sparse Representation
    Yang Cong, Junsong Yuan & Ji Liu, Pattern Recognition,Volume 46, Issue 7, pp.1851 - 1864, July2013

  • Max-Margin Structured Output Regression for Spatio-T​emporal Action Localization
    Tran Du; Junsong Yuan, 2012 Advanes in Neural Information Processing Systems (NIPS)

  • Sparse Reconstruction Cost for Abnormal Event Detection
    Yang Cong, Junsong Yuan & Ji Liu, 2011 IEEE Computer Vision and Pattern Recognition (CVPR)

  • Optimal Spatio-Temporal Path Discovery for Video Event Detection
    Du Tran; Junsong Yuan, 2011 IEEE Computer Vision and Pattern Recognition (CVPR)


  • Visual Scene Understanding
  • DAG-Recurrent Neural Networks For Scene Labeling
    Bing Shuai, Zhen Zuo, Gang Wang and Bing Wang, CVPR, 2016

  • Scene Parsing with Integration of Parametric and Non-parametric Models
    Shuai Bing, Zhen Zuo, Gang Wang, and Bing Wang, accepted in IEEE Transactions on Image Processing


  • Face Recognition
  • Classwise Sparse and Collaborative Patch Representation for Face Recognition
    Jian Lai, Xudong Jiang, IEEE Transactions On Image Processing, Vol. 25, No. 7, July 2016

  • Sparse and Dense Hybrid Representation via Dictionary Decomposition for Face Recognition
    Xudong Jiang, Jian Lai, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 37, No. 5, May 2015

  • LBP-Based Edge-Texture Features for Object Recognition
    Amit Satpathy, Xudong Jiang, How-Lung Eng, IEEE Transactions On Image Processing, Vol. 23, No. 5, May 2014

  • Human Detection by Quadratic Classification on Subspace of Extended Histogram of Gradients
    Amit Satpathy, Xudong Jiang, How-Lung Eng, IEEE Transactions On Image Processing, Vol. 23, No. 1, January 2014

  • Large Margin Multi-Metric Learning for Face and Kinship Verification in the Wild
    Junlin Hu, Jiwen Lu, Junsong Yuan, Yap-Peng Tan, 2014 Asian Conference on Computer Vision (ACCV)

  • Discriminative Deep Metric Learning for Face Verification in the Wild
    Junlin Hu, Jiwen Lu, Yap-Peng Tan, 2014 IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)

  • Noise-Resistant Local Binary Pattern With an Embedded Error-Correction Mechanism
    Jianfeng Ren, Xudong Jiang, Junsong Yuan, IEEE Transactions On Image Processing, Vol. 22, No. 10, October 2013

  • Robust Feature Set Matching for Partial Face Recognition
    Renliang Weng, Jiwen Lu, Junlin Hu, Gao Yang, Yap-Peng Tan, 2013 IEEE International Conference on Computer Vision (ICCV)​

  • Robust Partial Face Recognition Using Instance-to-Class Distance
    Junlin Hu, Jiwen Lu, Yap-Peng Tan, 2013 IEEE Visual Communications and Image Processing (VCIP)

  • Multi-View ordinal ranking for facial age estimation
    Renliang Weng, Jiwen Lu, Gao Yang, Yap-Peng Tan, 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

  • Modular Weighted Global Sparse Representationfor Robust Face Recognition
    Jian Lai, Xudong Jiang, IEEE Signal Processing Letters, Vol. 19, No. 9, September 2012


  • Deep Learning
  • ​​Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks Jinghua Wang, Zhenhua Wang, Dacheng Tao, Simon See, Gang Wang, 2016 European Conference on Computer Vision (ECCV)

  • Visual Product Search for Fashion Domain: From Hand-crafted features to Deep Learning
    Huijing Zhan, Yan Wang, Abrar H. Abdulnabi, Sheng Li, Dennis Sng, Alex C. Kot,Simon See, Princess Maha Chakri Sirindhorn Congress Interdisciplinary Approach to Sustainable Research and Developments (INRIT 2015)

  • Integrating Parametric and Non-parametric Models For Scene Labeling
  • Bing Shuai, Gang Wang, Zhen Zuo, Bing Wang, Lifan Zhao, 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015) 

  • Multi-Manifold Deep Learning for Image Set Classification
    Jiwen Lu , Gang Wang, Weihong Deng, Pierre Moulin, Jie Zhou, 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015)

  • Learning Discriminative Hierarchical Features for Object Recognition
    Zhen Zuo, Gang Wang, IEEE Signal Processing Letters, Vol.21 (2014), Issue 9, pp.1159 - 1163, January 2014

  • Learning Discriminative and Shareable Features for Scene Classification
    Zhen Zuo, Gang Wang, Bing Shuai, Lifan Zhao, Qingxiong Yang, Xudong Jiang, 2014 European Conference on Computer Vision (ECCV)

  • Recognizing trees at a distance with discriminative deep feature learning
    Zhen Zuo, Gang Wang,9th International Conference on Information, Communications and Signal Processing (ICICS 2013)


  • Image Classification
  • Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks
    Zhen Zuo, Bing Shuai, Gang Wang, Xiao Liu, Xingxing Wang and Bing Wang, accepted in IEEE Transactions on Image Processing

  • Learning Semantic Visual Dictionaries: A new Method For Local Feature Encoding
    Bing SHUAI, Zhen ZUO and Gang WANG, 2015 IEEE International Conference on Digital Signal Processing (DSP)

  • Exploiting Privileged Information from Web Data for Image Categorization​
    Wen Li, Li Niu, Dong Xu, 2014 European Conference on Computer Vision (ECCV)

  • Learning Weighted Geometric Pooling for Image Classification
    Chaoqun Weng, Hongxing Wang, Junsong Yuan, 2013 IEEE International Conference on Image Processing(ICIP)


  • Visual Tracking
  • Tracklet Association by Online Target-Specific Metric Learning and Coherent Dynamics Estimation
    Bing Wang, Gang Wang, Kap Luk Chan, and Li Wang, accepted in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

  • Real-time part-based visual tracking via adaptive correlation filters
    Ting Liu, Gang Wang, Qingxiong Yang, 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015)

  • Visual Tracking via Temporally Smooth Sparse Coding
    Ting Liu, Gang Wang, Li Wang, Kap Luk Chan; IEEE Signal Processing Letters

  • Visual Tracking using Learned Color Features
    Ting Liu, Rahul Rama Varior, Gang Wang; IEEE Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015

  • Video Tacking using Learned Hierarchical Features
    Li Wang, Ting Liu, Gang Wang, Kap Luk Chan and Qingxiong Yang; IEEE Transactions on Image Processing 2015


  • Multimedia
  • Adaptive Configuration of Cloud Video Transcoding
    Ming Yang, Jianfei Cai, Weiwen Zhang, Yonggang Wen, Chuan Heng Foh, 2015 IEEE International Symposium on Circuits and Systems (ISCAS)

  • Joint Learning For Image-Based Handbag Recommendation​
    Yan Wang, Sheng Li, Alex Kot, 2015 IEEE International Conference on Multimedia and Expo (ICME)


  • Content Management in Media Cloud: QoE-Driven Approach and Cost-Efficient Perspective
    Weiwen Zhang, Yonggang Wen, Guanyu Gao, 2014 International Conference on Cloud Computing Research and Innovation (ICCCRI)

  • Toward Transcoding as a Service in a Multimedia Cloud: Energy-Efficient Job-Dispatching Algorithm
    Weiwen Zhang, Yonggang Wen, Jianfei Cai, Dapeng Oliver Wu, IEEE Transactions on Vehicular Techonology, Volume 63, Issue 5, Pages 2002, March 2014


  • Action Recognition
  • Multimodal Multipart Learning for Action Recognition in Depth Videos
    Amir Shahroudy, Tian-Tsong Ng, Qingxiong Yang, and Gang Wang, accepted in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

  • NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
    Amir Shahroudy, Jun Liu, Tian-Tsong Ng, and Gang Wang, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

  • Multi-modal Feature Fusion for Action Recognition in {RGB-D} Sequences
    Amir Shahroudy, Gang Wang , Tian Tsong Ng, 2014 International Symposium on Communications, Control, and Signal Processing (ISCCSP)


  • Data Mining
  • Topic Exploration in Spatio-Temporal Document Collections​
    Kaiqi Zhao, Lisi Chen, Gao Cong, 2016 ACM SIGMOD/PODS Conference​​​​

  • Mining New Business Opportunities: Identifying Trend related Products by Leveraging Commercial Intents from Microblogs​
    Jinpeng Wang, Wayne Xin Zhao, Haitian Wei, Hongfei Yan, Xiaoming Li, Conference on Empirical Methods in Natural Language Processing (EMNLP 2013) ​​


  • Database System
  • Efficient Algorithms for Answering the m-Closest Keywords Query
    Tao Guo, Xin Cao, Gao Cong, 2015 Proceedings of the ACM SIGMOD International Conference on Management of Data (SIGMOD)


  • Sentiment Analysis
  • One Seed to Find Them All: Mining Opinion Features via Association
    Zhen Hai, Kuiyu Chang, & Gao Cong, Proceedings of the 21st ACM international conference on Information and knowledge management (CIKM 2012)


  • Video Coding
  • Cost Optimal Video Transcoding In Media Cloud: Insights From User Viewing Pattern
    Guanyu Gao, Weiwen Zhang, Yonggang Wen, Zhi Wang, Wenwu Zhu, Yap Peng Tan, 2014 IEEE International Conference on Multimedia & Expo (ICME)


  • Forensics
  • Image Splicing Localization Based on Blur Type Inconsistency
    Khosro Bahrami, Alex Kot, 2015 IEEE International Symposium ​on Circuits and Systems (ISCAS)

  • Blurred Image Splicing Localization by Exposing Blur Type Inconsistency
    Bahrami K., Kot, A.C., Leida Li, Haoliang Li, IEEE Transactions on Information Forensics and Security, Volume 10, Issue 5, Pages999 - 1009, May 2015


  • Others
  • Exploring Local and Overall Ordinal Information for Robust Feature Description
    Zhenhua Wang, Bin Fan, Gang Wang and Fuchao Wu, accepted in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016

  • A Low Complexity Interest Point Detector​
    Jie Chen, Ling-Yu Duan, Feng Gao, Jianfei ​Cai , Kot, A.C., Tiejun Huang, IEEE Signal Processing Letters, Volume 22 (2014), Issue 2, Pages 172 - 176, February 2015

  • Exploiting Low-rank Structure from Latent Domains for Domain Generalization
    Xu Zheng, Wen Li, Li Niu, Dong Xu, 2014 European Conference on Computer Vision (ECCV)

  • ​​​​​ Multi-feature Spectral Clustering with Minimax Optimization
    Hongxing Wang, Chaoqun Weng, Junsong Yuan, 2014 IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)

  • Hierarchical Sparse Coding based on Spatial Pooling and Multi-feature Fusion
    Chaoqun Weng, Hongxing Wang, Junsong Yuan,2013 IEEE International Conference on Multimedia Expo (ICME)​
  • ​​