Recent Submissions

  • Person Re-Identification by Deep Learning Multi-Scale Representations 

    Chen, Y; Zhu, X; Gong, S; IEEE (IEEE, 2018-01)
    Existing person re-identification (re-id) methods depend mostly on single-scale appearance information. This not only ignores the potentially useful explicit information of other different scales, but also loses the chance ...
  • WebLogo-2M: Scalable Logo Detection by Deep Learning from the Web 

    Su, H; Gong, S; Zhu, X; IEEE (IEEE, 2018-01)
    Existing logo detection methods usually consider a small number of logo classes and limited images per class with a strong assumption of requiring tedious object bounding box annotations, therefore not scalable to real-world ...
  • RGB-Infrared Cross-Modality Person Re-identification 

    Wu, A; Zheng, WS; Yu, HX; Gong, S; Lai, J (IEEE, 2017-12)
    Person re-identification (Re-ID) is an important problem in video surveillance, aiming to match pedestrian images across camera views. Currently, most works focus on RGB-based Re-ID. However, in some applications, RGB ...
  • Attribute Recognition by Joint Recurrent Learning of Context and Correlation 

    Wang, J; Zhu, X; Gong, S; Li, W (IEEE, 2017-12)
    Recognising semantic pedestrian attributes in surveillance images is a challenging task for computer vision, particularly when the imaging quality is poor with complex background clutter and uncontrolled viewing conditions, ...
  • Class Rectification Hard Mining for Imbalanced Deep Learning 

    Dong, Q; Gong, S; Zhu, X (IEEE, 2017-12)
    Recognising detailed facial or clothing attributes in images of people is a challenging task for computer vision, especially when the training data are both in very large scale and extremely imbalanced among different ...
Return to top