School of Electronic Engineering and Computer Science

Professor Shaogang Gong, DPhil FIEE FBCS

Shaogang

Professor of Visual Computation

Email: s.gong@qmul.ac.uk
Telephone: +44 20 7882 5249
Room Number: Peter Landin, CS 325
Website: http://www.eecs.qmul.ac.uk/~sgg

Teaching

Deep Learning and Computer Vision (Postgraduate)

Fuelled by the advances in sensing, computing and Machine Learning, Computer Vision applications start finding their way in our everyday lives. Face detection/recognition in Facebook, augmented reality with Google glasses, gaming with Microsoft kinect, to name just a few. This module, covers emerging topics/applications in the field of Computer Vision, and the underlying Machine Learning methodologies.

Research

Research Interests:

Shaogang Gong is the Head of the Queen Mary Computer Vision Group, with research interests on computer vision, machine learning, and video analysis (http://www.eecs.qmul.ac.uk/~sgg/). He has written two research monographs: Visual Analysis of Behaviour: From Pixels to Semantics (2011) and Dynamic Vision: From Images to Face Recognition (2000); edited five books on topics ranging from Person Re-identification (2014), Video Analytics for Business Intelligence (2012), to Modelling and Analysis of Faces and Gestures (2007, 2005, 2003); and published over 400 papers (http://scholar.google.com/citations?user=Nhi0I8cAAAAJ). Gong's research has led to three start-up companies. He won the 2019 Bruce Dickinson Entrepreneur of the Year Award, the 2019 Queen Mary Innovation Award, and the 2017 Queen Mary Academic Commercial Enterprise Award. A commercial system built on the patents and software from his research won the 2017 Global Frost & Sullivan Award for Technical Innovation for Law Enforcement Video Forensics Technology, and the 2017 annual (12th) ADS (Aerospace Defence Security) Innovation Award for "revolutionary solution to reviewing CCTV footage". 

Since 1996, Gong has served as chairs, area chairs and on programme committees of over 130 computer vision and pattern recognition conferences including IEEE International Conferences on Computer Vision (ICCV'17, ICCV'15, ICCV'13, ICCV'11, ICCV'09, ICCV'05, ICCV'03, ICCV'01), IEEE Conferences on Computer Vision and Pattern Recognition (CVPR'18, CVPR'17, CVPR'16, CVPR'15, CVPR'14, CVPR'13, CVPR'12, CVPR'11, CVPR'10, CVPR'07, CVPR'05), European Conferences on Computer Vision (ECCV'18, ECCV'16, ECCV'14, ECCV'12, ECCV'10, ECCV'08, ECCV'06, ECCV'04, ECCV'02), International Conferences on Pattern Recognition (ICPR'14, ICPR'12, ICPR'10, ICPR'08, ICPR'04), and British Machine Vision Conferences (BMVC'19, BMVC'18, BMVC'17, BMVC'16, BMVC'15, BMVC'14, BMVC'13, BMVC'12, BMVC'11, BMVC'09, BMVC'08, BMVC'07, BMVC'06, BMVC'05, BMVC'04, BMVC'02, BMVC'01). He serves currently as an Associate Editor and on the Editorial Board of IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT). He received the 2015 IEEE TCSVT Best Associate Editor Award. He served as the Guest Editor of the Journal of Computer Vision and Image Understanding 2016 special issue on "Image and Video Understanding in Big Data", the Journal of Image and Vision Computing 2002 special issue on "Understanding Visual Behaviour".

Gong was a recipient of a Queen's Research Scientist Award (1987), a Royal Society Research Fellow (1987 & 1988), a GEC-Oxford Fellow (1989), elected a Fellow of the Institution of Electrical Engineers, a Fellow of the British Computer Society, and a member of the UK Computing Research Committee. He served on the UK Government Chief Scientific Adviser Science Review Steering Panel. 

Publications

  • Lin H, Fu Y, Lu P et al. (2019). TC-NEt for ISBIR: Triplet classification network for instance-level sketch based image retrieval. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Su H, Gong S, Zhu X (2019). Scalable logo detection by self co-learning. nameOfConference



    Citations: 0
  • Lan X, Zhu X, Gong S (2019). Self-Referenced Deep Learning. Asian Conference on Computer Vision



    Citations: 0
  • Li M, Zhu X, Gong S (2019). Unsupervised Tracklet Person Re-Identification. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Chen Y, Zhu X, Gong S (2019). Deep Association Learning for Unsupervised Video Person Re-identification. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 2
  • Cheng Z, Zhu X, Gong S (2019). Low-Resolution Face Recognition. Asian Conference on Computer Vision



    Citations: 0
  • Su H, Zhu X, Gong S (2019). Open logo detection challenge. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 1
  • Dong Q, Zhu X, Gong S et al. (2019). Single-Label Multi-Class Image Classification by Deep Logistic Regression. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Kanac¿ A, Zhu X, Gong S (2019). Vehicle Re-identification in Context. German Conference on Pattern Recognition



    Citations: 0
  • Wang J, Zhu X, Gong S et al. (2018). Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification. IEEE Conference on Computer Vision and Pattern Recognition



    Citations: 0
  • Lan X, Zhu X, Gong S (2018). Person Search by Multi-Scale Matching. European Conference on Computer Vision



    Citations: 0
  • Chen Y, Zhu X, Gong S (2018). Semi-supervised Deep Learning with Memory. European Conference on Computer Vision



    Citations: 0
  • Li M, Zhu X, Gong S (2018). Unsupervised Person Re-identification by Deep Learning Tracklet Association. European Conference on Computer Vision



    Citations: 0
  • Wang H, Zhu X, Gong S et al. (2018). Person Re-identification in Identity Regression Space. nameOfConference



    Citations: 0
  • GONG SS (2018). Harmonious Attention Network for Person Re-Identification. IEEE Conference on Computer Vision and Pattern Recognition



    Citations: 0
  • Dong Q, Gong S, Zhu X (2018). Imbalanced Deep Learning by Minority Class Incremental Rectification. nameOfConference



    Citations: 0
  • Jiao J, Zheng WS, Wu A et al. (2018). Deep low-resolution person re-identification. nameOfConference

    DOI: doi


    Citations: 7
  • Lan X, Zhu X, Gong S (2018). Knowledge distillation by on-the-fly native ensemble. Advances in Neural Information Processing Systems

    DOI: doi


    Citations: 0
  • Fu Y, Xiang T, Jiang YG et al. (2018). Recent Advances in Zero-Shot Recognition: Toward Data-Efficient Understanding of Visual Content. nameOfConference



    Citations: 0
  • Wang J, Zhu X, Gong S et al. (2017). Attribute Recognition by Joint Recurrent Learning of Context and Correlation. IEEE International Conference on Computer Vision



    Citations: 0
  • Dong Q, Gong S, Zhu X (2017). Class Rectification Hard Mining for Imbalanced Deep Learning. IEEE International Conference on Computer Vision



    Citations: 0
  • Chen Y, Zhu X, Gong S (2017). Person re-identification by deep learning multi-scale representations. IEEE International Conference on Computer Vision Workshops



    Citations: 0
  • Wu A, Zheng WS, Yu HX et al. (2017). RGB-Infrared Cross-Modality Person Re-identification. IEEE International Conference on Computer Vision



    Citations: 0
  • Su H, Gong S, Zhu X (2017). WebLogo-2M: Scalable Logo Detection by Deep Learning from the Web. IEEE International Conference on Computer Vision Workshops



    Citations: 0
  • Li W, Zhu X, Gong S (2017). Person re-identification by deep joint learning of multi-loss classification. International Joint Conference on Artificial Intelligence

    DOI: doi


    Citations: 0
  • Fu Z, XIANG T, Kodirov E et al. (2017). Zero-Shot Learning on Semantic Class Prototype Graph. nameOfConference



    Citations: 0
  • Zhang L, Xiang T, Gong S et al. (2017). Learning a Deep Embedding Model for Zero-Shot Learning. IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION



    Citations: 0
  • Kodirov E, Xiang T, Gong S et al. (2017). Semantic Autoencoder for Zero-Shot Learning. IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION



    Citations: 0
  • Zhang L, Sung F, Liu F et al. (2017). Actor-Critic Sequence Training for Image Captioning.. nameOfConference

    DOI: doi


    Citations: 0
  • Xu X, Hospedales TM, Gong S (2017). Discovery of Shared Semantic Spaces for Multiscene Video Query and Summarization. nameOfConference



    Citations: 0
  • Wang J, Zhu X, Gong S (2017). Discovering visual concept structure with sparse and incomplete tags. nameOfConference



    Citations: 0
  • Su H, Zhu X, Gong S (2017). Deep learning logo detection with data expansion by synthesising context. IEEE Winter Conference on Applications of Computer Vision



    Citations: 0
  • Dong Q, Gong S, Zhu X (2017). Multi-Task curriculum transfer deep learning of clothing attributes. IEEE Winter Conference on Applications of Computer Vision



    Citations: 0
  • Ma X, Zhu X, Gong S et al. (2017). Person re-identification by unsupervised video matching. nameOfConference



    Citations: 0
  • Murino V, Gong S, Loy CC et al. (2017). Image and Video Understanding in Big Data. nameOfConference



    Citations: 0
  • Schumann A, Gong S, Schuchert T (2017). Deep learning prototype domains for person re-identification. IEEE International Conference on Image Processing



    Citations: 0
  • Xu X, Hospedales T, Gong S (2017). Transductive Zero-Shot Action Recognition by Word-Vector Embedding. nameOfConference



    Citations: 0
  • Lan X, Wang H, Gong S et al. (2017). Deep reinforcement learning attention selection for person re-identification. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 5
  • Xu X, Gong S, Hospedales TM (2017). Zero-Shot Crowd Behavior Recognition. nameOfConference


    QMRO: qmroHref

    Citations: 1
  • Zhang L, Xiang T, Gong S (2016). Learning a discriminative null space for person re-identification. IEEE Conference on Computer Vision and Pattern Recognition



    Citations: 0
  • Peng P, Xiang T, Wang Y et al. (2016). Unsupervised cross-dataset transfer learning for person re-identification. IEEE Conference on Computer Vision and Pattern Recognition



    Citations: 0
  • Wang T, Gong S, Zhu X et al. (2016). Person Re-Identification by Discriminative Selection in Video Ranking.. nameOfConference



    Citations: 0
  • Li Y, Song YZ, Hospedales TM et al. (2016). Free-Hand Sketch Synthesis with Deformable Stroke Models. nameOfConference



    Citations: 0
  • Li Y, SONG Y, Hospedales T et al. (publicationYear). Free-hand sketch synthesis with deformable stroke models. nameOfConference

    DOI: doi


    Citations: 0
  • Alexiou I, Xiang T, Gong S (2016). Exploring synonyms as context in zero-shot action recognition. IEEE International Conference on Image Processing



    Citations: 0
  • Wang H, Zhu X, Xiang T et al. (2016). Towards unsupervised open-set person re-identification. IEEE International Conference on Image Processing



    Citations: 0
  • Zhu X, Loy CC, Gong S (2016). Constrained Clustering With Imperfect Oracles. nameOfConference



    Citations: 0
  • Zhu X, Loy CC, Gong S (2016). Learning from Multiple Sources for Video Summarisation. nameOfConference



    Citations: 11
  • Hu JF, Zheng WS, Lai J et al. (2016). Exemplar-Based Recognition of Human-Object Interactions. nameOfConference



    Citations: 0
  • Fu Y, Hospedales TM, Xiang T et al. (2016). Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels. nameOfConference



    Citations: 12
  • Zheng WS, Gong S, Xiang T (2016). Towards Open-World Person Re-Identification by One-Shot Group-Based Verification. nameOfConference



    Citations: 72
  • Xu X, Hospedales TM, Gong S (2016). Discovery of Shared Semantic Spaces for Multiscene Video Query and Summarization.. nameOfConference



    Citations: 0
  • Wang H, Gong S, Xiang T (2016). Highly efficient regression for scalable person re-identification. nameOfConference


    QMRO: qmroHref

    Citations: 9
  • Wang H, Gong S, Zhu X et al. (2016). Human-in-the-loop person re-identification. nameOfConference


    QMRO: qmroHref

    Citations: 20
  • Kodirov E, Xiang T, Fu Z et al. (2016). Learning robust graph regularisation for subspace clustering. nameOfConference


    QMRO: qmroHref

    Citations: 5
  • Xu X, Hospedales TM, Gong S (2016). Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation.. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Xu X, Hospedales TM, Gong S (2016). Multi-task zero-shot action recognition with prioritised data augmentation. nameOfConference


    QMRO: qmroHref

    Citations: 13
  • Kodirov E, Xiang T, Fu Z et al. (2016). Person re-identification by unsupervised ℓ1 graph learning. nameOfConference


    QMRO: qmroHref

    Citations: 32
  • Tan T, Gong S, Aggarval J (2016). Preface. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Fu Y, Hospedales TM, Xiang T et al. (2016). Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels.. nameOfConference



    Citations: 0
  • Wang J, Zhu X, Gong S (2016). Video semantic clustering with sparse and incomplete tags. nameOfConference

    DOI: doi


    Citations: 10
  • Li X, Zheng W, Li X et al. (2015). Multi-scale Person Re-identification. International Conference on Computer Vision

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Zheng W, Li X, XIANG T et al. (2015). Partial Person Re-identification. International Conference on Computer Vision


    QMRO: qmroHref

    Citations: 0
  • Xu X, Hospedales T, Gong S (2015). Semantic embedding space for zero-shot action recognition. nameOfConference



    Citations: 29
  • Fu Y, Hospedales TM, Xiang T et al. (2015). Transductive Multi-View Zero-Shot Learning. nameOfConference



    Citations: 131
  • Alexiou I, XIANG T, Gong S (2015). Learning A Joint Discriminative-Generative Model for Action Recognition. International Conference on Systems, Signals and Image Processing


    QMRO: qmroHref

    Citations: 0
  • Kodirov E, XIANG T, Gong S (2015). Dictionary Learning with Iterative Laplacian Regularisation for Unsupervised Person Re-Identification. British Machine Vision Conference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Fu Z, XIANG T, Kodirov E et al. (2015). Zero-Shot Object Recognition by Semantic Manifold Distance. IEEE Conference on Computer Vision and Pattern Recognition



    Citations: 0
  • Li Y, Hospedales TM, Song YZ et al. (2015). Free-hand sketch recognition by multi-kernel feature learning. nameOfConference



    Citations: 42
  • Fu Y, Hospedales T, XIANG T et al. (2015). Transductive Multi-view Zero-Shot Learning. nameOfConference



    Citations: 0
  • Li X, Zheng WS, Wang X et al. (2015). Multi-scale learning for low-resolution person re-identification. nameOfConference



    Citations: 42
  • Layne R, Hospedales TM, Gong S (2015). Investigating open-world person re-identification using a drone. nameOfConference



    Citations: 6
  • Xu X, Hospedales TM, Gong S (2015). Semantic embedding space for zero-shot action recognition.. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Fu Y, Hospedales TM, Xiang T et al. (2015). Transductive Multi-View Zero-Shot Learning.. nameOfConference



    Citations: 0
  • Fu Y, Yang Y, Hospedales TM et al. (2015). Transductive Multi-class and Multi-label Zero-shot Learning.. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Kodirov E, XIANG T, Gong S (2015). Unsupervised Domain Adaptation for Zero-Shot Learning. International Conference on Computer Vision


    QMRO: qmroHref

    Citations: 0
  • Xu X, Hospedales TM, Gong S (2015). Zero-Shot Action Recognition by Word-Vector Embedding.. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • FU Y, Hospedales T, XIANG T et al. (2014). Interestingness Prediction by Robust Learning to Rank. European Conference on Computer Vision

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Liu C, Gong S, Loy CC (2014). On-the-fly feature importance mining for person re-identification. nameOfConference



    Citations: 65
  • Fu Y, Hospedales TM, Xiang T et al. (2014). Learning multimodal latent attributes. nameOfConference



    Citations: 72
  • Layne R, Hospedales TM, Gong S (2014). Attributes-based re-identification. nameOfConference


    QMRO: qmroHref

    Citations: 62
  • Zhu X, Loy CC, Gong S (2014). Constructing robust affinity graphs for spectral clustering. nameOfConference



    Citations: 63
  • Liu C, Gong S, Loy CC et al. (2014). Evaluating feature importance for re-identification. nameOfConference


    QMRO: qmroHref

    Citations: 9
  • Li Y, Hospedales TM, Song YZ et al. (2014). Fine-grained sketch-based image retrieval by matching deformable part models. nameOfConference

    DOI: doi


    Citations: 26
  • Zheng WS, Gong S, Xiang T (2014). Group association: Assisting re-identification by visual context. nameOfConference


    QMRO: qmroHref

    Citations: 5
  • Fu Y, Hospedales TM, Xiang T et al. (2014). Interestingness prediction by robust learning to rank. nameOfConference



    Citations: 20
  • Li Y, Hospedales TM, Song Y-Z et al. (2014). Intra-category sketch-based image retrieval by matching deformable part models.. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Cancela B, Hospedales TM, Gong S (2014). Open-world person re-identification by multi-label assignment inference. nameOfConference

    DOI: doi


    Citations: 17
  • Wang T, Gong S, Zhu X et al. (2014). Person re-identification by video ranking. nameOfConference



    Citations: 208
  • Gong S, Cristani M, Yan S et al. (2014). Preface. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Layne R, Hospedales TM, Gong S (2014). Re-id: Hunting attributes in the wild. nameOfConference

    DOI: doi


    Citations: 29
  • Raja Y, Gong S (2014). Scalable multi-camera tracking in a metropolis. nameOfConference


    QMRO: qmroHref

    Citations: 4
  • Gong S, Cristani M, Loy CC et al. (2014). The re-identification challenge. nameOfConference


    QMRO: qmroHref

    Citations: 46
  • Fu Y, Yang Y, Hospedales TM et al. (2014). Transductive Multi-label Zero-shot Learning.. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Fu Y, Hospedales TM, Xiang T et al. (2014). Transductive multi-view embedding for zero-shot recognition and annotation. nameOfConference



    Citations: 64
  • Wang H, Gong S, Xiang T (2014). Unsupervised learning of generative topic saliency for person re-identification. nameOfConference

    DOI: doi


    Citations: 44
  • Zhu X, Loy CC, Gong S (2013). Constrained clustering: Effective constraint propagation with imperfect oracles. nameOfConference



    Citations: 5
  • Loy CC, Liu C, Gong S (2013). Person re-identification by manifold ranking. nameOfConference



    Citations: 97
  • Chen K, Gong S, Xiang T et al. (2013). Cumulative attribute space for age and crowd density estimation. nameOfConference



    Citations: 226
  • Zheng W, Gong S, Xiang T (2013). Re-identification by Relative Distance Comparison. nameOfConference



    Citations: 0
  • Xu X, Gong S, Hospedales T (2013). Cross-domain traffic scene understanding by motion model transfer. nameOfConference


    QMRO: qmroHref

    Citations: 3
  • Layne R, Hospedales TM, Gong S (2013). Domain transfer for person re-identification. nameOfConference


    QMRO: qmroHref

    Citations: 20
  • Hospedales TM, Gong S, Xiang T (2013). Finding Rare Classes: Active Learning with Generative and Discriminative Models. nameOfConference



    Citations: 0
  • Loy CC, Gong S, Xiang T (2013). From semi-supervised to transfer counting of crowds. nameOfConference


    QMRO: qmroHref

    Citations: 55
  • Liu C, Gong S, Loy CC (2013). On-the-fly feature importance mining for person re-identification. nameOfConference



    Citations: 0
  • Liu C, Loy CC, Gong S et al. (2013). POP: Person re-identification post-rank optimisation. nameOfConference


    QMRO: qmroHref

    Citations: 88
  • Hu JF, Zheng WS, Lai J et al. (2013). Recognising human-object interaction via exemplar based modelling. nameOfConference


    QMRO: qmroHref

    Citations: 19
  • Li Y, Song YZ, Gong S (2013). Sketch recognition by ensemble matching of structured features. nameOfConference


    QMRO: qmroHref

    Citations: 36
  • Zhu X, Loy CC, Gong S (2013). Video synopsis by heterogeneous multi-source correlation. nameOfConference


    QMRO: qmroHref

    Citations: 29
  • Hospedales TM, Gong S (2012). Real-time dictionary based super-resolution of surveillance video streams and targets. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Fu Y, Hospedales TM, Xiang T et al. (2012). Attribute learning for understanding unstructured social activity. nameOfConference


    QMRO: qmroHref

    Citations: 53
  • Loy CC, Hospedales TM, Xiang T et al. (2012). Stream-based joint exploration-exploitation active learning. nameOfConference


    QMRO: qmroHref

    Citations: 43
  • Zheng WS, Gong S, Xiang T (2012). Transfer re-identification: From person to set-based verification. nameOfConference


    QMRO: qmroHref

    Citations: 54
  • Loy CC, Xiang T, Gong S (2012). Incremental activity modeling in multiple disjoint cameras.. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Loy CC, Xiang T, Gong S (2012). Salient motion detection in crowded scenes. nameOfConference


    QMRO: qmroHref

    Citations: 29
  • Hospedales TM, Gong S, Xiang T (2012). Video Behaviour Mining Using a Dynamic Topic Model. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Zheng WS, Gong S, Xiang T (2012). Re-identification by Relative Distance Comparison.. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Li J, Gong S, Xiang T (2012). Learning Behavioural Context. nameOfConference


    QMRO: qmroHref

    Citations: 30
  • Zheng W-S, Gong S, Xiang T (2012). Quantifying and transferring contextual information in object detection.. nameOfConference



    Citations: 0
  • HOSPEDALES T, Gong S, Xiang T (2012). A Unifying Theory of Active Discovery and Learning. European Conference on Computer Vision


    QMRO: qmroHref

    Citations: 0
  • Zhu X, Gong S, Loy CC (2012). Comparing visual feature coding for learning disjoint camera dependencies. nameOfConference


    QMRO: qmroHref

    Citations: 3
  • Chen K, Loy CC, Gong S et al. (2012). Feature mining for localised crowd counting. nameOfConference


    QMRO: qmroHref

    Citations: 183
  • Layne R, Hospedales T, Gong S (2012). Person re-identification by attributes. nameOfConference


    QMRO: qmroHref

    Citations: 206
  • Liu C, Gong S, Loy CC et al. (2012). Person re-identification: What features are important?. nameOfConference


    QMRO: qmroHref

    Citations: 169
  • Raja Y, Gong S (2012). Scaling up multi-camera tracking for real-world deployment. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Layne R, Hospedales TM, Gong S (2012). Towards person identification and re-identification with attributes. nameOfConference


    QMRO: qmroHref

    Citations: 48
  • Chen K, Gong S, Xiang T (2011). Human pose estimation using structural support vector machines. nameOfConference


    QMRO: qmroHref

    Citations: 4
  • Hospedales TM, Gong S, Xiang T (2011). Learning tags from unsegmented videos of multiple human actions. nameOfConference


    QMRO: qmroHref

    Citations: 7
  • Bregonzio M, XIANG T, Gong S (2011). Fusing appearance and distribution information of interest points for action recognition. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Li J, Gong S, Xiang T (2011). Learning Behavioural Context. nameOfConference



    Citations: 0
  • Hospedales TM, Gong S, Xiang T (2011). Finding rare classes: Adapting generative and discriminative models in active learning. nameOfConference


    QMRO: qmroHref

    Citations: 7
  • Zheng W, Gong S, XIANG T (2011). Person Re-identification by Probabilistic Relative Distance Comparison. IEEE Conference on Computer Vision and Pattern Recognition


    QMRO: qmroHref

    Citations: 0
  • Gong S, Xiang T (2011). Visual Analysis of Behaviour: From Pixels to Semantics. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Hospedales TM, Li J, Gong S et al. (2011). Identifying Rare and Subtle Behaviours: A Weakly Supervised Joint Topic Model.. nameOfConference



    Citations: 0
  • Hospedales T, Gong S, XIANG T (2011). Finding Rare Classes: Adapting Generative and Discriminative Models in Active Learning. Pacific-Asia Conference on Knowledge Discovery and Data Mining

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Zhang J, Gong S (2011). Fusion of motion and appearance for robust people detection in cluttered scenes. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Loy C, Xiang T, Gong S (2011). Detecting and Discriminating Behavioural Anomalies. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Chen K, Gong S, Xiang T et al. (2011). Human Pose Estimation Using Structural Support Vector Machines. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 1
  • Li J, Hospedales TM, Gong SG et al. (2011). Learning Rare Behaviours. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Zheng W-S, Gong S, Xiang T et al. (2011). Person Re-identification by Probabilistic Relative Distance Comparison. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 281
  • Loy CC, Xiang T, Gong S (2011). Stream-Based Active Unusual Event Detection. nameOfConference


    QMRO: qmroHref

    Citations: 5
  • Zheng WS, Gong SG, Xiang T (2011). Unsupervised Selective Transfer Learning for Object Recognition. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Raja Y, Gong S, Xiang T (2011). User-assisted visual search and tracking across distributed multi-camera networks. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Hospedales T, Gong S, Xiang T (2011). Video Behaviour Mining Using a Dynamic Topic Model. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 1
  • Li J, Hospedales T, Gong S et al. (2010). Learning Rare Behaviours. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Loy C, Xiang T, Gong S (2010). Stream-based Active Anomaly Detection. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Zheng W, Gong S, Xiang T (2010). Unsupervised Selective Transfer Learning for Object Recognition. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Bashir K, Xiang T, Gong S (2010). Gait Recognition without Subject Cooperation. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Gong S, Xiang T, Hongeng S (2010). Learning Human Pose in Crowd. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Loy CC, Xiang T, Gong SG (2010). Time-Delayed Correlation Analysis for Multi-Camera Activity Understanding. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Bashir K, Xiang T, Gong S (2010). Cross-View Gait Recognition Using Correlation Strength. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Bregonzio M, Li J, Gong S et al. (2010). Discriminative Topics Modelling for Action Feature Selection and Recognition. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Prosser B, Zheng W, Gong S et al. (2010). Person Re-Identification by Support Vector Ranking. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Zhang JG, Gong SG (2010). Action categorization by structural probabilistic latent semantic analysis. nameOfConference


    QMRO: qmroHref

    Citations: 1
  • Zhang JG, Gong SG (2010). Action categorization with modified hidden conditional random field. nameOfConference


    QMRO: qmroHref

    Citations: 6
  • Bregonzio M, Gong S, Xiang T (2009). Action Recognition with Cascaded Feature Selection and Classification. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Bashir K, Xiang T, Gong S (2009). Gait Recognition Using Gait Entropy Image. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Loy CC, Xiang T, Gong S (2009). Surveillance video behaviour profiling and anomaly detection. nameOfConference


    QMRO: qmroHref

    Citations: 6
  • Hospedales T, Gong S, Xiang T (2009). A Markov Clustering Topic Model for Mining Behaviour in Video. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Li J, Gong S, Xiang T (2009). Discovering Multi-Camera Behaviour Correlations for On-the-Fly Global Activity Prediction and Anomaly Detection. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Loy C, Xiang T, Gong S (2009). Modelling Activity Global Temporal Dependencies using Time Delayed Probabilistic Graphical Model. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Zheng W, Gong S, Xiang T (2009). Quantifying Contextual Information for Object Detection. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Zelniker E, Hospedales T, Gong S et al. (2009). A Unified Approach for Adaptive Multiple Feature Tracking for Surveillance Applications. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Zheng W, Gong S, Xiang T (2009). Associating Groups of People. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Bashir K, Xiang T, Gong S (2009). Gait Representation Using Flow Fields. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Orozco J, Gong S, Xiang T (2009). Head Pose Classification in Crowded Scenes. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Loy C, Xiang T, Gong S (2009). Multi-Object Activity Modelling Using Gaussian Processes. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Pachoud S, Gong S, Cavallaro A (2009). Space-Time Audio-Visual Speech Recognition with Multiple Multi-Class Probabilistic Support Vector Machines. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Loy C, Xiang T, Gong S (2009). Multi-Camera Activity Correlation Analysis. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Bregonzio M, Gong S, Xiang T (2009). Recognising Action as Clouds of Space-Time Interest Points. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Shan CF, Gong SG, McOwan PW (2009). Facial expression recognition based on Local Binary Patterns: A comprehensive study. nameOfConference


    QMRO: qmroHref

    Citations: 24
  • Zhang JG, Gong SG (2009). People detection in low-resolution video with non-stationary background. nameOfConference


    QMRO: qmroHref

    Citations: 1
  • Wang Y, Mei T, Gong SG et al. (2009). Combining global, regional and contextual features for automatic image annotation. nameOfConference


    QMRO: qmroHref

    Citations: 5
  • Hospedales T, Gong S, Xiang T (2009). A Markov Clustering Topic Model for Mining Behaviour in Video. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Zelniker EE, Hospedales TM, Gong S et al. (2009). A unified Bayesian framework for adaptive visual tracking. nameOfConference


    QMRO: qmroHref

    Citations: 4
  • Bregonzio M, Gong S, Xiang T (2009). Action Recognition with Cascaded Feature Selection and Classification. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Zheng W, Gong S, Xiang T (2009). Associating Groups of People. British Machine Vision Conference (BMVC)


    QMRO: qmroHref

    Citations: 0
  • Li J, Gong S, Xiang T (2009). Discovering Multi-Camera Behaviour Correlations for On-the-Fly Global Activity Prediction and Anomaly Detection. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Jia K, Gong S (2009). Face Sample Quality. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Bashir K, Xiang T, Gong S (2009). Gait Recognition Using Gait Entropy Image. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Bashir K, Xiang T, Gong S (2009). Gait Representation Using Flow Fields. British Machine Vision Conference (BMVC)


    QMRO: qmroHref

    Citations: 0
  • Orozco J, Xiang T, Gong S (2009). Head Pose Classification in Crowded Scenes. British Machine Vision Conference (BMVC)


    QMRO: qmroHref

    Citations: 0
  • Loy C, Xiang T, Gong S (2009). Modelling Activity Global Temporal Dependencies using Time Delayed Probabilistic Graphical Model. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Loy C, Xiang T, Gong S (2009). Modelling Multi-object Activity by Gaussian Processes. British Machine Vision Conference (BMVC)


    QMRO: qmroHref

    Citations: 0
  • Zheng W, Gong S, Xiang T (2009). Quantifying Contextual Information for Object Detection. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong SG (2008). Optimising dynamic graphical models for video content analysis. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Loy C, Xiang T, Gong S (2008). From Local Temporal Correlation to Global Anomaly Detection. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Zelniker E, Gong S, Xiang T (2008). Global Abnormal Behaviour Detection Using a Network of CCTV Cameras. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Russell D, Gong S (2008). Multi-Layered Decomposition of Recurrent Scenes. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Prosser B, Gong S, Xiang T (2008). Multi-camera Matching under Illumination Change Over Time. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Li J, Gong S, Xiang T (2008). Scene Segmentation for Behaviour Correlation. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Mei T, Wang Y, Hua XS et al. (2008). Coherent image annotation by learning semantic distance. nameOfConference


    QMRO: qmroHref

    Citations: 39
  • Russell D, Gong S (2008). Exploiting Periodicity in Recurrent Scenes. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Bashir K, Xiang T, Gong S (2008). Feature Selection for Gait Recognition without Subject Cooperation. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Li J, Gong S, Xiang T (2008). Global Behaviour Inference using Probabilistic Latent Semantic Analysis. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Prosser B, Gong S, Xiang T (2008). Multi-camera Matching Using Bi-Directional Cumulative Brightness Transfer Functions. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Pachoud S, Gong S, Cavallaro A (2008). Video Augmentation for Improving Audio Speech Recognition under Noise. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Mang T, Gong SG (2008). Activity based surveillance video content modelling. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong SG (2008). Incremental and adaptive abnormal behaviour detection. nameOfConference


    QMRO: qmroHref

    Citations: 6
  • Mei T, Wang Y, Hua X et al. (2008). Coherent Image Annotation by Semantic Distance Learning. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Shan CF, Gong SG, McOwan PW (2008). Fusing gait and face cues for human gender recognition. nameOfConference


    QMRO: qmroHref

    Citations: 6
  • Jia K, Gong SG (2008). Generalized face super-resolution. nameOfConference



    Citations: 0
  • Xiang T, Gong S (2008). Video behavior profiling for anomaly detection.. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Bashir K, Xiang T, Gong S (2008). Feature Selection on Gait Energy Image for Human Identification. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong S (2008). Spectral clustering with eigenvector selection. nameOfConference


    QMRO: qmroHref

    Citations: 12
  • Bashir K, Xiang T, Gong S (2008). Feature Selection for Gait Recognition without Subject Cooperation. British Machine Vision Conference (BMVC)


    QMRO: qmroHref

    Citations: 0
  • Bashir K, Xiang T, Gong SG (2008). Feature selection on gait energy image for human identification. nameOfConference


    QMRO: qmroHref

    Citations: 3
  • Li J, Gong S, Xiang T (2008). Global Behaviour Inference Using Probabilistic Latent Semantic Analysis. British Machine Vision Conference (BMVC)


    QMRO: qmroHref

    Citations: 0
  • Pachoud S, Gong S, Cavallaro A (2008). Macro-cuboid based probabilistic matching for lip-reading digits. nameOfConference



    Citations: 0
  • Prosser B, Gong S (2008). Multi-camera Matching Using Bi-Directional Cumulative Brightness Transfer Functions. British Machine Vision Conference (BMVC)


    QMRO: qmroHref

    Citations: 0
  • Russell D, Gong SG (2008). Multi-layered Decomposition of Recurrent Scenes. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Li J, Gong SG, Xiang T (2008). Scene Segmentation for Behaviour Correlation. nameOfConference


    QMRO: qmroHref

    Citations: 2
  • Pachoud S, Gong S, Cavallaro A (2008). Video augmentation for improving audio speech recognition under noise. nameOfConference



    Citations: 0
  • Wang Y, Gong S (2007). Translating Topics to Words for Image Annotation. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Gong S, Shan C, Xiang T (2007). Visual Inference of Human Emotion and Behaviour. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Shan C, Gong S, McOwan P (2007). Beyond Facial Expressions: Learning Human Emotion from Body Gestures. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Shan C, Gong S, McOwan P (2007). Capturing Correlations among Facial Parts for Facial Expression Analysis. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Wang Y, Gong S (2007). Conditional Random Field for Natural Scene Image Classification. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S (2007). Holistic video detection. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Russell D, Gong S (2007). Segmenting Highly Textured Nonstationary Background. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Wang Y, Gong S (2007). Refining Image Annotation Using Contextual Relations Between Words. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Leung A, Gong S (2007). Optimizing Distribution-based Matching by Random Subsampling. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • (2007). Analysis and Modeling of Faces and Gestures. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Wang Y, Gong S (2007). Conditional random field for natural scene categorization. nameOfConference


    QMRO: qmroHref

    Citations: 16
  • Gong SG (2007). Holistic video detection - art. no. 674103. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Shan CF, Gong SG, McOwan PW (2007). Learning gender from human gaits and faces. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Leung AP, Gong SG (2007). Optimizing distribution-based matching by random subsampling. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Gong SG, Shan CF, Xiang T (2007). Visual Inference of Human Emotion and Behaviour. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Jia K, Gong S (2006). Hallucinating multiple occluded face images of different resolutions. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Hung H, Gong S (2006). Classification of human interaction from a distance using salient body behaviour modelling. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Jia K, Gong S, Leung A (2006). Coupling face registration and super-resolution. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Shan C, Gong S, McOwan P (2006). Dynamic facial expression recognition using a Bayesian temporal manifold model. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Leung A, Gong S (2006). Mean-shift tracking with random sampling. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Russell D, Gong S (2006). Minimum cuts of a time-varying background. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong S (2006). Optimal dynamic graphs for video content analysis. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Raja Y, Gong S (2006). Sparse multiscale local binary patterns. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S, XIANG T (2006). Model Selection for Unsupervised Learning of Visual Context. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong SG (2006). Model selection for unsupervised learning of visual context. nameOfConference


    QMRO: qmroHref

    Citations: 3
  • Wang Y, Gong S (2006). Tensor discriminant analysis for view-based object recognition. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Shan C, Gong S, McOwan P (2006). A Comprehensive empirical study on linear subspace methods for facial expression analysis. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Jia K, Gong S (2006). Multi-resolution patch tensor for facial expression hallucination. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Zhang J, Gong S (2006). Beyond static detectors: A Bayesian approach to fusing long-term motion with appearance for robust people detection in highly cluttered scenes. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong S (2006). Incremental visual behaviour modelling. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong SG (2006). Beyond tracking: Modelling activity and understanding behaviour. nameOfConference


    QMRO: qmroHref

    Citations: 60
  • Jia K, Gong S, Leung AP (2006). Coupling face registration and super-resolution. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 4
  • Hung H, Gong SG (2006). Detection of human interaction from a distance using salient body behaviour modelling - art. no. 640203. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Shan C, Gong S, McOwan PW (2006). Dynamic facial expression recognition using a Bayesian temporal manifold model. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 45
  • Leung AP, Gong S (2006). Mean-shift tracking with random sampling. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 14
  • Russell D, Gong S (2006). Minimum cuts of a time-varying background. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 10
  • Xiang T, Gong S (2006). Optimal dynamic graphs for video content analysis. British Machine Vision Conference (BMVC)

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Raja Y, Gong S (2006). Sparse multiscale local binary patterns. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 11
  • Wang Y, Gong SG (2006). Tensor discriminant analysis for view-based object recognition. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Russell D, Gong SG (2005). A highly efficient block-based dynamic background model. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • GONG SS, Zalewski L (2005). A statistical virtual head animator. IEE International Conference on Visual Information Engineering

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • GONG SS, Leung A (2005). An optimization framework for real-time appearance-based tracking under weak perspective. British Machine Vision Conference


    QMRO: qmroHref

    Citations: 0
  • GONG S, Zhao W, Tang X (2005). Analysis and Modelling of Faces and Gestures. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Shan CF, Gong SG, McOwan PW (2005). Appearance manifold of facial expression. nameOfConference


    QMRO: qmroHref

    Citations: 7
  • GONG SS, Jia K (2005). CCTV face hallucination under occlusion with motion blur. IEE International Symposium on Imaging for Crime Detection and Prevention

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S, MCOWAN PW, Shan C (2005). Conditional Mutual Information Based Boosting for Facial Expression Recognition. British Machine Vision Conference (BMVC'05), Oxford, UK


    QMRO: qmroHref

    Citations: 0
  • Hung H, Gong S (2005). Detecting and quantifying unusual interactions by correlating salient motion. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Jia K, Gong S (2005). Face super-resolution using multiple occluded images of different resolutions. nameOfConference


    QMRO: qmroHref

    Citations: 1
  • Jia K, Gong S (2005). Multi-modal face image super-resolutions in tensor space. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Jia K, Gong SG (2005). Multi-modal tensor face for simultaneous super-resolution and recognition. nameOfConference


    QMRO: qmroHref

    Citations: 4
  • GONG SS, Leung AP (2005). Multi-view temporal tracking under weak perspective in real-time. IEE International Conference on Visual Information Engineering

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Del Bue A, Llado X, Agapito L (2005). Non-rigid face modelling using shape priors. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Leung AP, Gong SG (2005). Online feature selection using mutual information for real-time multi-view object tracking. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • GONG SS, Xiang T (2005). Online video behaviour abnormality detection using reliability measure. British Machine Vision Conference


    QMRO: qmroHref

    Citations: 0
  • Shan CF, Gong SG, McOwan PW (2005). Recognizing facial expressions at low resolution. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong SG (2005). Relevance learning for spectral clustering with applications on image segmentation and video behaviour profiling. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Shan CF, Gong SG, McOwan PW (2005). Robust facial expression recognition using local binary patterns. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Zalewski L, Gong S (2005). Statistical models of facial expressions for realistic 3D avatar animation. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • GONG SS, Graves A (2005). Surveillance video indexing with iconic patterns of activity. IEE International Conference on Visual Information Engineering

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong S (2005). Unsupervised Learning of Visual Context Using Completed Likelihood AIC. IEE International Conference on Visual Information Engineering (VIE)

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • GONG SS, Xiang T (2005). Unsupervised learning of visual context using mixture models. IEE International Conference on Visual Information Engineering

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong SG (2005). Video behaviour profiling and abnormality detection without manual labelling. nameOfConference


    QMRO: qmroHref

    Citations: 7
  • Xiang T, Gong S (2005). Visual learning given sparse data of unknown complexity. nameOfConference


    QMRO: qmroHref

    Citations: 1
  • Gong S (2004). Finding a needle in haystacks: Towards behaviour recognition based video surveillance. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong S (2004). Activity-based scene representation and segmentation of CCTV surveillance videos. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Hung H, Gong S (2004). Quantifying temporal saliency. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Graves A, Gong S (2004). Wavelet-based holistic sequence descriptor for generating video summaries. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Li YM, Gong SG, Sherrah J et al. (2004). Support vector machine based multi-view face detection and recognition. nameOfConference


    QMRO: qmroHref

    Citations: 25
  • GONG SS, Zalewski L (2004). A probabilistic hierarchical framework for expression classification. Artificial Intelligence and the Simulation of Behaviour Symposium on Language, Speech and Gesture for Expressive Characters

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Zalewski L, Gong SG (2004). Synthesis and recognition of facial expressions in virtual 3D views. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Gong SG (2004). Towards behaviour recognition based video surveillance. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Ng J, Gong S (2003). Learning pixel-wise signal energy for understanding semantics. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Li Y, Gong S, Liddell H (2003). Recognising trajectories of facial identities using Kernel Discriminant Analysis. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Li YM, Gong SG, Liddell H (2003). Recognising trajectories of facial identities using kernel discriminant analysis. nameOfConference


    QMRO: qmroHref

    Citations: 4
  • Xiang T, Gong S (2003). On the structure of dynamic Bayesian networks for complex scene modelling. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong S, Parkinson D (2003). Outdoor activity recognition using multi-linked temporal processes. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Graves A, Gong S (2003). Spotting scene change for indexing surveillance video. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Li YM, Gong SG, Liddell H (2003). Constructing facial identity surfaces for recognition. nameOfConference


    QMRO: qmroHref

    Citations: 11
  • Gong S, Xiang T (2003). Scene event recognition without tracking. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Xiang T, Gong SG (2003). Discovering Bayesian causality among visual events in a complex outdoor scene. nameOfConference


    QMRO: qmroHref

    Citations: 5
  • (2003). IEEE International Workshop on Analysis and Modelling of Faces and Gestures. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • GONG SS, Ng J (2003). Learning pixel-wise signal energy for understanding semantics. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Gong SG, Xiang T (2003). Recognition of group activities using dynamic Probabilistic networks. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Gong SG, Ng J, Sherrah J (2002). On the semantics of visual behaviour, structured events and trajectories of human action. nameOfConference


    QMRO: qmroHref

    Citations: 12
  • Gong SG, Buxton H (2002). Understanding visual behaviour. nameOfConference


    QMRO: qmroHref

    Citations: 6
  • Xiang T, Gong S, Parkinson D (2002). Autonomous visual events detection and classification without explicit object-centred segmentation and tracking. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Ng J, Gong S (2002). Learning intrinsic video content using Levenshtein distance in graph partitioning. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Ng J, Gong SG (2002). Composite support vector machines for detection of faces across views and pose estimation. nameOfConference


    QMRO: qmroHref

    Citations: 19
  • Psarrou A, Gong SG, Walter M (2002). Recognition of human gestures and behaviour based on motion trajectories. nameOfConference


    QMRO: qmroHref

    Citations: 14
  • Ong EJ, Gong SG (2002). The dynamics of linear combinations: tracking 3D skeletons of human subjects. nameOfConference


    QMRO: qmroHref

    Citations: 6
  • Sherrah J, Gong S (2002). Automated detection of localised visual events over varying temporal scales. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Chang T-H, Gong S (2002). Bayesian Modality Fusion for tracking multiple people with a multi-camera system. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Ng J, Gong S (2002). Composite support vector machines for the detection of faces across views and pose estimation. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • GONG SS, Romdhani S, Psarrou A (2002). Corresponding dynamic appearances. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Ng J, Gong SG (2002). Learning intrinsic video content using Levenshtein distance in graph partitioning. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 2
  • Ng J, Gong SG (2002). On the binding mechanism of synchronised visual events. nameOfConference


    QMRO: qmroHref

    Citations: 1
  • Psarrou A, Gong S, Walter M (2002). Recognition of human gestures and behaviour. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Ong E, Gong S (2002). The dynamics of linear combinations. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Sherrah J, Gong S, Ong EJ (2001). Face distributions in similarity space under varying head pose. nameOfConference


    QMRO: qmroHref

    Citations: 12
  • Walter M, Psarrou A, Gong S (2001). Data driven model acquisition using Minimum Description Length. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Li Y, Gong S, Liddell H (2001). Recognising trajectories of facial identities using Kernel Discriminate Analysis. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Sherrah J, Gong SG (2001). Fusion of perceptual cues for robust tracking of head pose and position. nameOfConference


    QMRO: qmroHref

    Citations: 9
  • Walter M, Psarrou A, Gong S (2001). Auto-clustering for unsupervised learning of atomic gesture components using Minimum Description Length. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Li Y, Gong S, Liddell H (2001). Constructing structures of facial identities on the view sphere using Kernel Discriminant Analysis. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Li Y, Gong S, Liddell H (2001). Video-based online face recognition using identity surfaces. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Li YM, Gong SG, Liddell H (2001). Constructing facial identity surfaces in a nonlinear discriminating space. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 1
  • Sherrah J, Gong SG (2001). Continuous global evidence-based Bayesian modality fusion for simultaneous tracking of multiple objects. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Li YM, Gong SG, Liddell H (2001). Modelling faces dynamically across views and over time. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Chang TH, Gong SG (2001). Tracking multiple people with a multi-camera system. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Li YM, Gong SG, Liddell H (2001). Video-based online face recognition using identity surfaces. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Romdhani S, Gong S, Psarrou A (2000). A generic face appearance model of shape and texture under very large pose variations from profile to profile views. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 4
  • Romdhani S, Gong S, Psarrou A (2000). A generic face appearance model of shape and texture under very large pose variations from profile to profile views. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Sherrah J, Gong S, Howell J et al. (2000). Interpretation of group behaviour in visually mediated interaction. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Ong E-J, Gong S (2000). Quantifying ambiguities in inferring vector-based 3D models. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Sherrah J, Gong S (2000). Resolving visual uncertainty and occlusion through probabilistic reasoning. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Chang T-H, Gong S, Ong E-J (2000). Tracking multiple people under occlusion using multiple cameras. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Romdhani S, Psarrou A, Gong S (2000). On utilising template and feature-based correspondence in multi-view appearance models. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Sherrah J, Gong S (2000). Tracking discontinuous motion using Bayesian inference. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Li Y, Gong S, Liddell H (2000). Support vector regression and classification based multi-view face detection and recognition. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Walter M, Psarrou A, Gong S (2000). An incremental approach towards automatic model acquisition for human gesture recognition. nameOfConference


    QMRO: qmroHref

    Citations: 4
  • Gong S, McKenna S, Psarrou A (2000). Dynamic Vision: From Images to Face Recognition. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Sherrah J, Gong SG, Howell AJ et al. (2000). Interpretation of group behaviour in visually mediated interaction. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Li YM, Gong SG, Sherrah J et al. (2000). Multi-view face detection using support vector machines and eigenspace modelling. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 2
  • Romdhani S, Psarrou A, Gong SG (2000). On utilising template and feature-based correspondence in muli-view appearance models. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 1
  • Sherrah J, Gong SG (2000). VIGOUR: A system for tracking and recognition of multiple people and their activities. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 4
  • Ong E-J, Gong S (1999). A dynamic virtual human model using hybrid 2D and 3D representations. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Sherrah J, Gong S (1999). Exploiting context in gesture recognition. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Ng J, Gong S (1999). Multi-view based support vector machines for real-time face detection and pose estimation. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Romdhani S, Gong S, Psarrou A (1999). Multi-view nonlinear active shape model using Kernel PCA. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Romdhani S, Gong S, Psarrou A (1999). Multi-view nonlinear active shape model using kernel PCA. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S, Walter M, Psarrou A (1999). Recognition of temporal structures: Learning prior and propagating observation augmented densities via hidden Markov states. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Sherrah J, Gong S (1999). Fusion of 2D face alignment and 3D head pose estimation for robust and real-Time performance. nameOfConference


    QMRO: qmroHref

    Citations: 5
  • Romdhani S, Psarrou A, Gong S (1999). Learning a single active face shape model across views. nameOfConference


    QMRO: qmroHref

    Citations: 3
  • Ng J, Gong S (1999). Multi-View face detection and pose estimation using a composite support vector machine across the view sphere. nameOfConference


    QMRO: qmroHref

    Citations: 52
  • Walter M, Gong S, Psarrou A (1999). Stochastic temporal models of human activities. nameOfConference


    QMRO: qmroHref

    Citations: 3
  • McKenna S, Raja Y, Gong S (1999). Tracking colour objects using adaptive mixture models. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Ong EJ, Gong S (1999). Tracking hybrid 2D-3D human models from multiple views. nameOfConference


    QMRO: qmroHref

    Citations: 17
  • McKenna S, Gong S (1998). Gesture recognition for visually mediated interaction using probabilistic event trajectories. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S, Ong E-J, McKenna S (1998). Learning to associate faces across views in vector space of similarities to prototypes. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Torre FDL, Gong S, McKenna S (1998). View-based Adaptive Affine Alignment. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Raja Y, McKenna S, Gong S (1998). Tracking and segmenting people in varying lighting conditions using colour. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Raja Y, McKenna SJ, Gong S (1998). Colour model selection and adaptation in dynamic scenes. nameOfConference


    QMRO: qmroHref

    Citations: 58
  • McKenna S, Gong S, Raja Y (1998). Modelling facial colour and identity with Gaussian mixtures. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • McKenna S, Gong S (1998). Real-time face pose estimation. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • McKenna S, Gong S (1998). Recognising moving faces. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Raja Y, McKenna SJ, Gong S (1998). Tracking and segmenting people in varying lighting conditions using colour. nameOfConference


    QMRO: qmroHref

    Citations: 139
  • De La Torre F, Gong S, McKenna S (1998). View alignment with dynamically updated affine tracking. nameOfConference


    QMRO: qmroHref

    Citations: 6
  • de La Torre F, Gong S, McKenna S (1998). View-based adaptive affine tracking. nameOfConference


    QMRO: qmroHref

    Citations: 14
  • McKenna S, Gong S (1997). Non-intrusive person authentication for access control by visual tracking and face recognition. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S, Ong EJ, Loft PJ (1997). Appearance-based face recognition under large head rotations in depth. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 2
  • McKenna SJ, Gong S (1997). Face recognition from sequences using models of identity. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • McKenna SJ, Raja Y, Gong S (1997). Object tracking using adaptive colour mixture models. nameOfConference


    QMRO: qmroHref

    Citations: 24
  • Raja Y, McKenna SJ, Gong S (1997). Segmentation and tracking using colour mixture models. nameOfConference


    QMRO: qmroHref

    Citations: 35
  • McKenna SJ, Gong S, Würtz RP et al. (1997). Tracking facial feature points with Gabor wavelets and shape models. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 44
  • McKenna S, Gong S, Wurtz R et al. (1997). Tracking facial motion using Gabor wavelets and flexible shape models. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S, McKenna S, Collins JJ (1996). An investigation into face pose distributions. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • McKenna S, Gong S (1996). Tracking faces. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • McKenna S, Gong S, Raja Y (1996). Face recognition in dynamic scenes. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Psarrou A, Gong S, Buxton H (1995). Modelling spatio-temporal trajectories and face signatures using partially recurrent neural networks. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Buxton H, Gong S (1995). Visual surveillance in a dynamic and uncertain world. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Gong S, Psarrou A, Katsoulis I et al. (1994). Tracking and recognition of face image sequences. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S, Buxton H (1993). Bayesian nets for motion segmentation and object tracking. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S (1992). Visual behavior: modeling 'hidden' purposes in motion. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S, Buxton H (1992). On the visual expectation of moving objects: A probabilistic approach with augmented hidden Markov models. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S (1992). Visual observation as reactive learning. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S, Brady JM (1990). Parallel computation of optic flow. nameOfConference


    QMRO: qmroHref

    Citations: 0
  • Gong S (1989). Parallel Computation of Visual Motion. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S (1989). On curve motion constraint equation and its applications. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0
  • Gong S (1988). Improving local flow. nameOfConference

    DOI: doi

    QMRO: qmroHref

    Citations: 0