PROFESSOR SHAOGANG GONG
E1 4NS, United Kingdom
Tel: +44 (0)20-7882 5249
Fax: +44 (0)20-7882 7064
s.gong AT qmul.ac.uk
Shaogang (Sean) Gong is Professor of Visual Computation at Queen Mary
of University London and a Turing Fellow of the Alan Turing Institute of Data Science and Artificial Intelligence. He established the Queen Mary Computer Vision Laboratory in 1993 and has enjoyed immensely working with PhD students and postdoctoral researchers. His research is in Computer Vision and Machine Learning (Google Scholar and DBLP), with a focus on Object Recognition, Action Recognition, and Video Analysis. His brief bio, publications with pdf download, and guide to PhD study.
Shaogang Gong, Marco Cristani, Shuicheng Yan, Chen Change Loy (Eds.). Person Re-Identification, Springer, January 2014.
Caifeng Shan, Fatih Porikli, Tao Xiang, Shaogang Gong (Eds.). Video Analytics for Business Intelligence, Springer, March 2012.
Shaogang Gong, Tao Xiang. Visual Analysis of Behaviour: From Pixels to Semantics, Springer, May 2011.
Shaogang Gong, Stephen J. McKenna, Alexandra Psarrou. Dynamic Vision: From Images to Face Recognition, Imperial College Press, June 2000.
S. Kevin Zhou, Wenyi Zhao, Xiaoou Tang, Shaogang Gong (Eds.). Analysis and Modelling of Faces and Gestures, Springer, October 2007.
Wenyi Zhao, Shaogang Gong, Xiaoou Tang (Eds.). Analysis and Modelling of Faces and Gestures, Springer, October 2005.
Shaogang Gong, Hong-Jiang Zhang, Stan Li, Andrew Senior, Thomas Vetter, Wenyi Zhao (Eds.). Analysis and Modelling of Faces and Gestures, IEEE Computer Society, October 2003.
2021 IEEE Transactions on Circuits and Systems for Video Technology Special Issue on "Large-Scale Visual Sensor Networks: Architectures and Applications", Vol. 31, No. 4; Paolo Spagnolo, Hamid Aghajan, George Bebis, Shaogang Gong, Amy Loutfi, Leonid Sigal, Wei-Shi Zheng. Editorial: Introduction to Large-Scale Visual Sensor Networks: Architectures and Applications, Vol. 31, No. 4, pp. 1249-1252, April 2021.
2017 Computer Vision and Image Understanding Special Issue on "Image and Video Understanding in Big Data", Vol. 156; Vittorio Murino, Shaogang Gong, Chen Change Loy, Loris Bazzani. Editorial: Image and Video Understanding in Big Data, Vol. 156, pp. 1-3, March 2017.
2002 Image and Vision Computing Special Issue on "Understanding Visual Behaviour", Vol. 20, No. 12; Shaogang Gong, Hilary Buxton. Editorial: Understanding Visual Behaviour, Vol.20, No.12, pp. 825-826, October 2002.
2019 IEEE International Conference on Computer Vision (ICCV), Second International Workshop and Challenge on Real-World Face and Object Recognition from Low-Quality Images and Videos (FOR-LQ), Seoul, Korea, October 2019.
2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Second International Workshop on Target Re-identification and Multi-Target Multi-Camera Tracking, Long Beach, CA, USA, June 2019.
2014 European Conference on Computer Vision (ECCV), International Workshop on Surveillance and Re-Identification, Zurich, Switzerland, September 2014.
2012 European Conference on Computer Vision (ECCV), First International Workshop on Person Re-Identification, Florence, Italy, October 2012.RECENT PUBLICATIONS (full listing with pdf download)
Guile Wu, Shaogang Gong. "Collaborative Optimisation and Aggregation for Decentralised Domain Generalisation and Adaptation". In Proc. IEEE International Conference on Computer Vision, Montreal, Canada, October 2021.
Jiabo Huang, Yang Liu, Shaogang Gong, Hailin Jin. "Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation". In Proc. IEEE International Conference on Computer Vision, Montreal, Canada, October 2021.
Guile Wu, Shaogang Gong, Pan Li. "Striking a Balance between Stability and Plasticity for Class-Incremental Learning". In Proc. IEEE International Conference on Computer Vision, Montreal, Canada, October 2021.
Pan Li, Da Li, Wei Li, Shaogang Gong, Yanwei Fu, Timothy Hospedales. "A Simple Feature Augmentation for Domain Generalisation". In Proc. IEEE International Conference on Computer Vision, Montreal, Canada, October 2021.
Wei-Shi Zheng, Jincheng Hong, Jiening Jiao, Ancong Wu, Xiatian Zhu, Shaogang Gong, Jianhuang Lai. "Joint Bilateral-Resolution Identity Modelling for Low-Resolution Person Re-Identification". International Journal of Computer Vision, accepted, July 2021.
Qingze Yin, Guan'an Wang, Guodong Ding, Shaogang Gong, Zhenmin Tang. "Multi-View Label Prediction for Unsupervised Learning Person Re-Identification". IEEE Signal Processing Letters, Vol. 28, pp. 1390-1394, June 2021.
Pan Li, Yanwei Fu, Shaogang Gong. "Regularising Knowledge Transfer by Meta Functional Learning". In Proc. International Joint Conference on Artificial Intelligence, Montreal, Canada, August 2021.
Pan Li, Guile Wu, Shaogang Gong, Xu Lan. "Semi-Supervised Few-Shot Learning with Pseudo Label Refinement". In Proc. IEEE International Conference on Multimedia and Expo, Shenzhen, China, July 2021.
Wei Li, Shaogang Gong, Xiatian Zhu. "Hierarchical Distillation Learning for Scalable Person Search". Pattern Recognition, Vol. 114, 107862, February 2021.
Xiangping Zhu, Xiatian Zhu, Minxian Li, Pietro Morerio, Vittorio Murino, Shaogang Gong. "Intra-Camera Supervised Person Re-Identification". International Journal of Computer Vision, Vol. 129, pp. 1580-1595, February 2021.
Hang Su, Shaogang Gong, Xiatian Zhu. "Multi-Perspective Cross-Class Domain Adaptation for Open Logo Detection". Computer Vision and Image Understanding, Vol. 204, 103156, March 2021.
Guile Wu and Shaogang Gong. "Decentralised Learning from Independent Multi-Domain Labels for Person Re-Identification". In Proc. AAAI Conference on Artificial Intelligence, February 2021.
Guile Wu and Shaogang Gong. "Generalising without Forgetting for Lifelong Person Re-Identification". In Proc. AAAI Conference on Artificial Intelligence, February 2021.
Guile Wu and Shaogang Gong. "Peer Collaborative Learning for Online Knowledge Distillation". In Proc. AAAI Conference on Artificial Intelligence, February 2021.
Zhiyi Cheng, Xiatian Zhu, Shaogang Gong. "Face Re-Identification Challenge: Are Face Recognition Models Good Enough?". Pattern Recognition, Vol. 107, 107422, November 2020.
Guan'an Wang, Shaogang Gong, Jian Cheng, Zengguang Hou. "Faster Person Re-Identification". In Proc. European Conference on Computer Vision, Glasgow, Scotland, August 2020.
Minxian Li, Xiatian Zhu, Shaogang Gong. "Unsupervised Tracklet Person Re-Identification". IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 42, No. 7, pp. 1770-1782, July 2020.
Wei Li, Xiatian Zhu, Shaogang Gong. "Scalable Person Re-Identification by Harmonious Attention". International Journal of Computer Vision, Vol. 128, No. 6, pp. 1635-1653, June 2020.
Ancong Wu, Wei-Shi Zheng, Shaogang Gong, Jianhuang Lai. "RGB-IR Person Re-identification by Cross-Modality Similarity Preservation". International Journal of Computer Vision, Vol. 128, No. 6, pp. 1765-1785, June 2020.
Jiabo Huang, Shaogang Gong, Xiatian Zhu. "Deep Semantic Clustering by Partition Confidence Maximisation". In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Seattle, Washington, USA, June 2020.
Yanbei Chen, Shaogang Gong, Loris Bazzani. "Image Search with Text Feedback by Visionlinguistic Attention Learning". In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Seattle, Washington, USA, June 2020. (featured in Amazon Science Blog and deeplearning.ai)
Zhiyi Cheng, Qi Dong, Shaogang Gong, Xiatian Zhu. "Inter-Task Association Critic for Cross-Resolution Person Re-Identification". In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Seattle, Washington, USA, June 2020.
Person Re-ID, Vehicle Re-ID, and Face Recognition Datasets:
- Native Unconstrained Low-Resolution Face Dataset (TinyFace), 169,403 face images of 5,139 identities in native low-resolution (not down-sampled) with average size of 20×16 pixels for 1:N face recognition algorithm evaluation, collected from public web data across a large variety of uncontrolled viewing conditions in pose, illumination, occlusion and background (ACCV 2018)
- Vehicle Re-Identification In Context datatset (VRIC), vehicle re-id images from videos of unconstrained resolution, motion blur, illumination, occlusion, and viewpoint, with 60,430 images of 5,622 vehicle identities captured by 60 different cameras at road traffic scenes from both day-time and night-time (GCPR 2018)
- Surveillance Face Recognition Dataset (QMUL-SurveFace), a large scale surveillance face recognition challenge of native low-resolution face images from surveillance videos, with 463,507 facial images of 15,573 identities (2018 arXiv)
- iLIDS Video re-IDentification (iLIDS-VID) Dataset (ECCV 2014, PAMI 2016)
- Mobile Re-identification Platform (MRP) Drone Dataset (ECCV 2014 Workshop on Visual Surveillance and Re-ID)
- Underground Re-Identification (GRID) Dataset (CVPR 2009, IJCV 2010, PR 2014, IJCAI 2017)
- QMUL i-LIDS Re-Identification Dataset ("Associating Groups of People"
(BMVC 2009), "Relative Distance Comparison" (CVPR 2011, PAMI 2013), "Group Association: Assisting Re-Identification by Visual Context", Person Re-Identification Springer 2014)
- QMUL i-LIDS Pedestrian Detection Dataset ("Quantifying Contextual Information for Object Detection" (ICCV 2009) and "Quantifying and Transferring Contextual Information in Object Detection" (PAMI 2012))
- QMUL Re-Identification Attribute Labelling (for VIPeR, GRID and PRID datasets) (BMVC 2012, Person Re-Identification Springer 2014)
- QMUL Multiview Face Dataset (FG 1996, BMVC 1998, Dynamic Vision: From Images to Face Recognition Imperial College Press 2000)
Logo Recognition Datasets:
- QMUL OpenLogo Challenge (BMVC 2018)
- QMUL WebLogo-2M Dataset (IEEE ICCV 2017 Workshop on Web-Scale Vision and Social Media)
- QMUL TopLogo10 Dataset (IEEE WACV 2017)
Activity Analysis Datasets:
- QMUL Junction Dataset, also available here prepared by David Russell and Jian Li (ECCV 2008, BMVC 2008, ICCV 2009, BMVC 2009, PR 2011, CVPR 2012, IJCV 2012)
- Shopping Mail Dataset (BMVC 2012, CVPR 2013, ICCV 2013)
- QMUL Roundabout Dataset and QMUL Junction 2 Dataset (BMVC 2008, ECCV 2008, IJCV 2012)
- Sports News Dataset Raw Data (1GB), Extracted Features and Annotations (3MB) ("Learning Tags from Unsegmented Videos of Multiple Human Actions" (ICDM 2011))
Video Summerisation Datasets:
- Queen Mary Multi-Camera Distributed Traffic Scenes (QMDTS) Dataset (IEEE TCSVT 2015)
- TIme Square Intersection (TISI) Dataset (ICCV 2013, IJCV 2016)
- Educational Resource Centre (ERCe) Dataset (ICCV 2013, IJCV 2016)
Deep Learning for Large-Scale Video Semantic Search
Developing and Commercialising Intelligent Video Analytics Solutions for Public Safety (Deep Learning for Smart City)
Deep Learning for Cross-Domain Object Recognition
Person Re-Identification In-The-Wild
SmartPrevent (Smart Video-Surveillance System to Detect and Prevent Local Crimes in Urban Areas)
VISTA(Video Analytics for Real-Time Human Profiling)
ViTAB (Video-based Threat Assessment and Biometrics) Network
SERVE (Surveillance, Evaluation, Research, Validation, and Exploitation) Network
s.gong AT qmul.ac.uk