Current Students and Postdocs   

Weitong Cai - Video search

Raymond Jiabo Huang - Unsupervised learning

Pan Li - Few-shot learning

Kevin Qilei Li - Weakly supervised learning

Shitong Sun - Distributed learning

Gavin Guile Wu - Multi-view multi-object visual tracking

 

Former Students and Postdocs

Aytac Kanaci (2020), Depp representation learning for vehicle re-identification

Zhiyi Cheng (2020), Person recognition in low-quality imagery

Wei Li (2020), Scalable deep learning architecture design

Yanbei Chen (2020), Visual learning in limited-label regime

Xu Lan (2020), Knowledge transfer in object recognition

Andrew Guan'an Wang (2020), Faster re-identification (CAS)

Jimmy Minxian Li (2020), People and vehicle search in-the-wild

Jane Qingze Yin (2020), Semi-supervised learning for re-identification (NJUST)

Grace Qi Dong (2019), Imbalanced deep learning for person attribute analysis

Hang Su (2019), Deep learning logo recognition

Eddy Xiatian Zhu (2019), People and vehicle re-identification in-the-wild

Kiya Jingya Wang (2018), Learning correlations for visual understanding

Zimo Liu (2018), Deep learning for person re-identification (DUT)

Yali Zhao (2018), Deep learning for hashing (Tsinghua)

Stephen Weihong Li (2018), Deep learning for video search (SYSU)

David Li Zhang (2017), Cross-view learning

Elyor Kodirov (2017), Cross-class transfer learning for visual data 

Hanxiao Wang (2017), Minimising human annotation for scalable person re-identification

Arne Schumann (2016), Deep learning person re-identification (Fraunhofer)

Alex Xun Xu (2016), Learning semantic spaces for video analysis of behaviour

Yi Li (2016), Sketch recognition and synthesis

Xiaolong Ma (2016), Person re-identification by unsupervised video matching (Tsinghua)

Zhenyong (Ian) Fu (2016), SUNNY object categorisation

Ioannis Alexiou (2016), SmartPrevent cross-domain action recognition

Lu Tian (2015), Multi-camera tracking (Tsinghua)

Ryan Layne (2015), Person re-identification by attribute

Yanwei Fu (2015), Attribute learning for image and video understanding

Brais Cancela Barizo (2014), Open-world person re-identification (A Coruna)

Taiqing Wang (2014), Person re-identification by video ranking (Tsinghua)

Chunxiao Liu (2013), Man-in-the-Loop learning and feature mining for person re-identification (Tsinghua)

Cory Ke Chen (2013), Latent dependency mining for regression in computer vision

Cavan Loy (2013), Abnormal behaviour recognition, SAMURAI multi-camera correlation, GETAWAY crowd analysis

Tim Hospedales (2012), SAMURAI behaviour mining, super-resolution, re-identification

Bryan Prosser (2011), Person re-identification over non-overlapping camera views

Matteo Bregonzio (2011), Representation and recognition of human actions in video

Luke Zalewski (2011), Statistical modelling for facial expression dynamics

Wei-Shi Zheng (2011), SAMURAI object detection, person re-identification

Diego Tosato (2011), Object and action recognition (Verona)

Somboon Hongeng (2010), VISTA real-time video analytics

Khalid Bashir (2010), Gait analysis

Jian Li (2010), BEWARE behaviour semantic correlation

Samuel Pachoud (2010), Audio-visual speech and emotion recognition 

Yogesh Raja (2010), Adaptive visual sampling

Emanuel Zelniker (2010), BEWARE

David Russell (2009), Spatial and temporal background modelling of non-stationary visual scenes

Yong Wang (2008), Automatic image annotation and categorisation

Alex Leung (2007), Appearance-based tracking of non-rigid objects

Caifeng Shan (2007), Inferring facial and body language

Hayley Hung (2007), Visual saliency for video behaviour understanding

Chris Jia (2007), Visual object super-resolution

Jianguo Zhang (2007), INSIGHT

John Qiu (2007), INSIGHT

Andrew Graves (2006), Iconic indexing for video search

Tony Xiang (2006), ICONS, INSIGHT

Michela Farenzena (2005), 3D face modelling (Verona)

Melanie Aurnhammer (2005), INSIGHT

Dennis Parkinson (2004), ICONS, AIMS

Jaeho Lee (2004), Eigen light field (Seoul)

Vejen Hlebarov (2003), ICONS

Justin Lim (2003), Lip reading

Jeffrey Ng (2003), Learning temporal models for the interpretation of dynamic scenes

Michael Walter (2002), Automatic model acquisition and recognition of human gestures (Westminster)

Jack Chang (2001), Tracking multiple people using two widely separated cameras

Eng-Jon Ong (2001), Learning the visual dynamics of human body motion

Yongmin Li (2001), Dynamic face models

Jamie Sherrah (2001), ISCANIT: Recognising intention for visually mediated interaction

Jonathan Howell (2000), ISCANIT (Sussex)

Paul Verity  (2000), AIMS: Advanced Incident Monitoring Systems

Sami Romdhani (1999), Nonlinear active face shape models (Westminster)

Stephen McKenna (1998), IMV on Real-time target identification for security applications

Fernando de la Torre (1997), Tracking view-based appearance models (Barcelona)

Peter Loft (1997), Pose invariance in face recognition

J.J. Collins (1996), Parallel modelling of neural operators for pattern recognition

Eui Young Cha (1995), Neural networks for character recognition (Seoul)

Jason Reading (1993), Graphical interface for video sequence acquisition

Andrew Smallbone (1993), Spatio-temporal filters for optic flow and motion segmentation