Recent Submissions

  • Learning Relevance Restricted Boltzmann Machine for Unstructured Group Activity and Event Understanding 

    Zhao, F; Huang, Y; Wang, L; Xiang, T; Tan, T (Springer, 2016-03-15)
    Analyzing unstructured group activities and events in uncontrolled web videos is a challenging task due to (1) the semantic gap between class labels and lowlevel visual features, (2) the demanding computational cost given ...
  • Learning from Weak and Noisy Labels for Semantic Segmentation 

    Lu, Z; Fu, Z; Xiang, T; Han, P; Wang, L; Gao, X (IEEE, 2016-04-08)
    A weakly supervised semantic segmentation (WSSS) method aims to learn a segmentation model from weak (image-level) as opposed to strong (pixel-level) labels. By avoiding the tedious pixel-level annotation process, it can ...
  • A Traffic-aware Resource Allocation Scheme for Internet of Vehicles: A Supply and Demand Function Approach 

    Li, J; Li, X; Wang, W; Zhang, Y; Kang, L; POSLAD, S (Binary Information Press, 2015)
    As the Internet advances and spreads further, the concept of Internet of Vehicles (IoV) makes components in Intelligent Transportation System (ITS) access the Internet to provide safer, greener, and comfortable driving for ...
  • On the impurity of street-scene video footage 

    Henderson, C; Blasi, S; Sobhani, F; IZQUIERDO, E; International Conference on Imaging for Crime Detection and Prevention (IEEE, 2015-07)
    In this paper, we present the technical challenges facing researchers in developing computer vision techniques to process street-scene videos from the wild. Video footage captured by surveillance CCTV cameras and hand-held ...
  • Robust Feature Matching in the Wild 

    IZQUIERDO, E; Science and Information Conference (IEEE, 2015-07)
    Finding corresponding key points in images from security camera videos is challenging. Images are generally low quality and acquired in uncontrolled conditions with visual distortions caused by weather, crowded scenes, ...
Return to top