• [Hot] We are recruiting Ph. D students, Post-Docs and Research faculties in the field of computational neuroscience. Please contact us (yhtian AT pku dot edu dot cn)!
• [Hot] The Portal of Video Analysis Contest in conjunction with the National Graduate Contest on Smart-City Technology and Creative Design

Member News:

• Our team wins the The Second-Class Award for National Technology Innovation Award, China, in 2017! Prof. Tiejun Huang, Prof. Yonghong Tian, and Dr.  Yaowei Wang are listed as the first, second, and fifth in the awarded project.
• Prof. Yonghong Tian is appointed to the Associate Editor of the IEEE Multimedia Magazine since 2018!
• Prof. Yonghong Tian is appointed to the adjunct professor of Huazhong University of Science and Technology since 2018!
• Prof. Yonghong Tian is appointed to the Associate Editor of the IEEE Transactions on Circuits and Systems for Video Technology since 2018!
• Prof. Yonghong Tian is appointed to the Steering Committee Member of the IEEE International Conference on Multimedia & Expo. since 2018!
• Prof. Yonghong Tian is appointed to Co-Editor-in-Chief of the International Journal of Multimedia Data Engineering and Management (IJMDEM) since August 2017!
• Our team wins the 2016 Excellent Patent Award by the State Intellectual Property Office of China! Prof. Yonghong Tian, Dr. Mengling Jiang, and Prof. Tiejun Huang are listed as the first, second, and third inventors in the awarded patent.
• Our team wins the first prize of the 2015 Technology Innovation Award by Chinese Institute of Electronics! Prof. Yonghong Tian, Prof. Tiejun Huang, Dr.  Yaowei Wang and Prof. Wen Gao are listed as the first, second, fifth and sixth winners in the awarded project.
• “Per-sample Multiple Kernel Approach for Visual Concept Learning”, co-authored by Jingjing Yang, Yuanning Li, Yonghong Tian*, Ling-yu Duan and Wen Gao, has been selected as the winner of the 2015 EURASIP Best Paper Award for the EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING.
• Prof. Yonghong Tian is appointed to TPC Co-chair of IEEE MIPR 2018! Welcome to submission!
• Prof. Yonghong Tian is appointed to Associate Editor of IEEE Access since March 2017.
• Mr. Peixi Peng and Mrs. Shu Fang have passed their Ph. D dissertations. Congratulation!
• Prof. Tiejun Huang is awarded by National Science Foundation for Distinguished Young Scholars in August 2014.
• Prof. Yonghong Tian is appointed to Guest Editor of IEEE Transactions on Multimedia (2015), IEEE Multimedia Magazine (2016), International Journal of Multimedia Data Engineering and Management (2016) and International Journal of Semantic Computing (2016).
• Prof. Yonghong Tian is appointed to Associate Editor of IEEE Transactions on Multimedia since August 2014!
• Prof. Yonghong Tian is appointed to Associate Editor of the International Journal of Multimedia Data Engineering and Management (IJMDEM) since July 2015!
• Prof. Yonghong Tian is appointed to TPC Co-chair of IEEE ISM 2015! Welcome to submission!
• Prof. Yonghong Tian is appointed to TPC Co-chair of IEEE ICME 2015! Welcome to submission!
• Our team is organizing the First IEEE International Conference on Multimedia Big Data (BigMM). Prof. Tiejun Huang is appointed to General Co-chair, while Prof. Yonghong Tian is appointed to TPC Co-chair! Welcome to submission!
• Dr.Jia Li has been assigned as Associate Professor in Beihang University from July 2014.
• Dr. Luntian Mou has been assigned as a Lecture in Beijing University of Technology from July 2014.
• Dr.Jia Li, graduated from our  group, gained Chinese Academy of Sciences outstanding doctoral thesis and the  outstanding doctoral thesis in Beijing City.

Recent Publication News:

• “Digital Retina: Revolutionizing the Camera Systems for the Smart City”, authored by Wen Gao, Yonghong Tian^*, Jian Wang, has been accepted for publication in SCIENTIA SINICA Informationis, Mar 2018.
• “PA-Search: Predicting Units Adaptive Motion Search for Surveillance Video Coding”, authored by Yonghong Tian^*, iaying Yan, Siwei Dong, Tiejun Huang, has been accepted for publication in Computer Vision and Image Understanding, Feb 2018.
• “Spike Coding for Dynamic Vision Sensors”, authored by Zhichao Bi, Siwei Dong, Yonghong Tian^*, Tiejun Huang, has been accepted for publication in IEEE Data Compression Conference (DCC) 2018 as the regular paper.
• “Rate-Performance-Loss Optimization for Inter-frame Deep Feature Coding from Videos”, authored by Lin Ding, Yonghong Tian^*, Hongfei Fan, Yaowei Wang, Tiejun Huang, has been accepted for publication in IEEE Transactions on Image Processing, Aug 2017. This is our first paper on deep feature coding.
• “Learning long-term dependencies for action recognition with a biologically-inspired deep network”, authored by Yemin Shi, Yonghong Tian^*, Yaowei Wang, Tiejun Huang, has been accepted for publication in ICCV 2017.
• “Exploiting Multi-Grain Ranking Constraints for Precisely Searching Visually-similar Vehicles”, authored by Ke Yan, Yonghong Tian^*, Yaowei Wang, Wei Zeng, Tiejun Huang, has been accepted for publication in ICCV 2017.
• “Joint Semantic and Latent Attribute Modelling for Cross-Class Transfer Learning”, authored by Peixi Peng, Yonghong Tian^*, Tao Xiang, Yaowei Wang, Massimiliano Pontil, Tiejun Huang, has been accepted for publication in IEEE Transactions on Pattern Analysis and Machine Intelligence, Jun 2017.
• “Sequential Deep Trajectory Descriptor for Action Recognition with Three-stream CNN”, authored by Yemen Shi, Yonghong Tian^*, Yaowei Wang, Tiejun Huang, has been accepted for publication in IEEE Transactions on Multimedia, Feb 2017.
• “Spike Camera and Its Coding Methods”, authored by Siwei Dong, Tiejun Huang and Yonghong Tian, has been accepted for publication in Data Compression Conference 2017.
• “Learning Discriminative Subspaces on Random Contrasts for Image Saliency Analysis”, authored by Shu Fang, Jia Li^*, Yonghong Tian^*, Tiejun Huang, Xiaowu Chen, has been accepted for publication in IEEE Transactions on Neural Networks and Learning Systems, May 2017.
• “Towards human-like and transhuman perception in AI 2.0: a review”, authored by Yonghong Tian^*, Xilin Chen, Hongkai Xiong, Hongliang Li, Lirong Dai, Jing Chen, Junliang Xing, Jing Chen, Xihong Wu, Weimin Hu, Yu Hu, Tiejun Huang, Wen Gao, has been accepted for publication in Frontiers of Information Technology & Electronic Engineering, Jan 2017.
• “Joint learning of Semantic and Latent Attributes”, co-authored by Peixi Peng, Yonghong Tian^*, Yaowei Wang, Tao Xiang, Tiejun Huang, has been accepted for publication in European Conference on Computer Vision 2016.
• “Unsupervised Cross-Dataset Transfer Learning for Person Re-identification”, co-authored by Peixi Peng, Tao Xiang, Yaowei Wang, Massimiliano Pontil, Shaogang Gong, Tiejun Huang, Yonghong Tian* has been accepted for publication in IEEE Conf. Computer Vision and Pattern Recognition 2016.
• “Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles”, co-authored by Hongye Liu, Yonghong Tian*, Yaowei Wang, Lu Pang, Tiejun Huang has been accepted for publication in IEEE Conf. Computer Vision and Pattern Recognition 2016.
• “Measuring Visual Surprise Jointly from Intrinsic and Extrinsic Contexts for Image Saliency Estimation”, co-authored by Jia Li, Yonghong Tian*, Xiaowu Chen, and Tiejun Huang has been accepted for publication in International Journal of Computer Vision, at Feb 15, 2016.
• “Learning Discriminative Subspaces on Random Contrasts for Image Saliency Analysis”, co-authored by Shu Fang, Jia Li^*, Yonghong Tian^*, Tiejun Huang and Xiaowu Chen, has been accepted by IEEE Transactions on Neural Networks and Learning Systems, at Jan 22, 2016.
• “Fixed-point Gaussian Mixture Model for Analysis-Friendly Surveillance Video Coding“, co-authored by Wei Chen, Yonghong Tian^*, Yaowei Wang and Tiejun Huang, has been accepted by Computer Vision and Image Understanding, at Sep 21, 2015.
• “Image Saliency Estimation via Random Walk Guided by Informativeness and Latent Signal Correlations“, co-authored by Jia Li, Shu Fang, Yonghong Tian∗, Tiejun Huang, Xiaowu Chen, has been accepted by Signal Processing: Image Communication, at May 21, 2015. (code)
• “Finding the Secret of Image Saliency in the Frequency Domain“, co-authored by Jia Li, Lingyu Duan, Xiaowu Chen, Tiejun Huang, and Yonghong Tian, has been accepted by IEEE Transactions on Pattern Recognition and Machine Intelligence, at April 10, 2015.
• “Learning Deep Trajectory Descriptor for Action Recognition in Videos using Deep Neural Networks”, co-authored by Yemin Shi, Yaowei Wang, Wei Zeng and Tiejun Huang, has been accepted by ICME 2015 as ORAL presentation.
• “Detecting Abnormal Behaviors in Surveillance Videos Based on Fuzzy Clustering and Multiple Auto-Encoders”, co-authored by Zhengying Chen, Yonghong Tian, Wei Zeng and Tiejun Huang, has been accepted by ICME 2015 as POSTER presentation.
• “Robust Multiple Cameras Pedestrian Detection with Multi-view Bayesian Network”, authored by Peixi Peng, Yonghong Tian^*, Yaowei Wang, Jia Li, Tiejun Huang, has been accepted by Pattern Recognition, at Dec 8, 2014.
• “Swiss-System based Cascade Ranking for Gait-based Person Re-identification“, authored by Lan Wei, Yonghong Tian^*, Yaowei Wang, Tiejun Huang, has been accepted by AAAI 2015.
• “TASC: A Transformation-Aware Soft Cascading Approach for Multimodal Video Copy Detection“, authored by Yonghong Tian, Mengren Qian, Tiejun Huang, has been accepted by ACM Transactions on Information Systems, at Oct. 20, 2014.
• “Optimizing the Hierarchical Prediction and Coding in HEVC for Surveillance and Conference Videos with Background Modeling”, is published in IEEE Transactions on Image Processing,  23(10), Oct. 2014. 4511-4526. DOI: 10.1109/TIP.2014.2352036
• “Can We Beat DDoS Attacks in Clouds?”,authored by Shui Yu, Yonghong Tian, Song Guo and Dapeng Oliver Wu, has published in IEEE Transactions on Parallel and Distributed Systems, 25(9), Sep. 2013, 2245-2254. DOI: 10.1109/TPDS.2013.181.
• “Learning Complementary Saliency Priors for Foreground Object Segmentation in Complex Scenes”, authored by Yonghong Tian, Jia Li, Shui Yu, Tiejun Huang, is accepted by Int’l Journal of Computer Vision.
• “Quality Assessment for Comparing Image Enhancement Algorithms”, written by Zhengying Chen, Tingting Jiang, Yonghong Tian, has been accepted by IEEE Computer Vision and Pattern Recognition 2014.
• “Multi-View Gait Recognition with Incomplete Training Data”, co-authored by Lan Wei, Yonghong Tian, Yaowei Wang, Tiejun Huang, accepted by IEEE International Conference on Multimedia & Expo 2014.
• “Background-Foreground Division Based Search for Motion Estimation in Surveillance Video Coding”, co-authored by Long Zhao, Yonghong Tian, Tiejun Huang has been accepted by IEEE International Conference on Multimeida and Expo, 2014.
• “Representing Visual Objects in HEVC Coding Loop”, written by Tiejun Huang, Siwei Dong, Yonghong Tian, has been published by IEEE Journal on Emerging and Selected Topics in Circuits and Systems, Volume 4, Issue 1, March 2014, 5-16. DOI: 10.1109/JETCAS.2014.2298274.
• “Visual Saliency with Statistical Priors”, authored by Jia Li, Yonghong Tian, Tiejun Huang, has been published by Int’l Journal of Computer Vision, Volume 107, Issue 3, May 2014, pp. 239-253. DOI: 10.1007/s11263-013-0678-0.
• “Background-Modeling Based Adaptive Prediction for Surveillance Video Coding”, authored by Xianguo Zhang, Tiejun Huang, Yonghong Tian, Wen Gao, has been published by IEEE Transactions on Image Processing, 23(2), Feb 2014, 769-784. DOI: 10.1109/TIP.2013.2294549.
• “IEEE 1857 Standard Empowering Smart Video Surveillance Systems”, authored by Wen Gao, Yonghong Tian (corresponding author), Tiejun Huang, Siwei Ma and Xianguo Zhang has been published by IEEE Intelligent Systems, 29(5), Sep.-Oct. 2014, 30-39. DOI: 10.1109/MIS.2013.101.
• “IEEE Standards for Advanced Audio and Video Coding in Emerging Applications“, authored by Prof. Wen Gao, Prof. Tiejun Huang, Dr. Cliff Reader, Prof. Weibei Dou,Prof. Xilin Chen, is published in IEEE Computer, May 2014.
• Dr. Jia Li and Prof. Wen Gao published their book “Visual Saliency Computation: A Machine Learning Perspective” in Springer, 2014. This book is based on the Ph.D study of Dr. Jia Li. 
• Video Copy Detection and Localization with a Scalable Cascading Framework, written by Prof. Yonghong Tian, is published in IEEE Multimedia, Sep 2013.
• IEEE COMSOC MMTC E-letter publishes the article “Multimodal Video Copy Detection using Multi-Detectors Fusion”, in which Yonghong Tian, Tiejun Huang, and Wen Gao from Peking University presented their video copy detection system that achieved the best overall accuracy and excellent localization precision in the TRECVID 2010 and 2011 content-based copy detection (CBCD) evaluation task hosted by NIST.

Competition News:

• We are organizing the first BigMM Challenge. The topic of BigMM 2015 Challenge is to address the problem of large-scale object tracking over a network of multiple cameras. More details can be found in BigMM 2015 Challenge.
• We have organized the Video Analysis Contest 2014, which was held in conjunction with the first National Graduate Contest on Smart-City Technology and Creative Design that is organized by China Academic Degrees & Graduate Education Development Center (CDGDC) and the Young Center of China Association of Science and Technology (CAST) and was hosted by Beihang University. The Video Analysis Contest 2015 will be hosted by Wuhan University.
• Our results in TRECVID-ED2011. We joined in five events and we got the first place in PeopleMeet and ObjectPut. We are the second place in Embrace and Pointing.
• Our results in TRECVID-ED2010. We joined four events in all seven. We got two best results and one second place in all participators.
• Our results in TRECVID-ED2009.We’ve joined in five events and got apparent improvement in  four events compared to the results in TRECVID-ED2008.
• We also own the championship in the mission of WikipediaMM in ImageCLEF, in 2008.

Activities:

• We had a trip to Beidaihe, Hebei on June 29th and 30th, to enjoy our summer outing as well as to celebrate the graduation of our five senior fellows.
• On Oct. 27th & 28th, 2012, we had an autumn outing to Qinglong Gorge and Mutianyu Greatwall, Huairou.