Skip to main content

and
  1. No Access

    Chapter and Conference Paper

    Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection

    Human-Object Interaction (HOI) detection plays a crucial role in activity understanding. Though significant progress has been made, interactiveness learning remains a challenging problem in HOI detection: exis...

    **aoqian Wu, Yong-Lu Li, **npeng Liu, Junyi Zhang, Yuzhe Wu in Computer Vision – ECCV 2022 (2022)

  2. No Access

    Chapter and Conference Paper

    Constructing Balance from Imbalance for Long-Tailed Image Recognition

    Long-tailed image recognition presents massive challenges to deep learning systems since the imbalance between majority (head) classes and minority (tail) classes severely skews the data-driven deep neural net...

    Yue Xu, Yong-Lu Li, Jiefeng Li, Cewu Lu in Computer Vision – ECCV 2022 (2022)

  3. No Access

    Chapter and Conference Paper

    Asynchronous Interaction Aggregation for Action Detection

    Understanding interaction is an essential part of video action detection. We propose the Asynchronous Interaction Aggregation network (AIA) that leverages different interactions to boost action detection. Ther...

    Jiajun Tang, ** **a, **nzhi Mu, Bo Pang, Cewu Lu in Computer Vision – ECCV 2020 (2020)

  4. No Access

    Chapter and Conference Paper

    Attention-Based Audio-Visual Fusion for Video Summarization

    Video summarization compresses videos while preserving the most meaningful content for users. Many image-based works focus on how to effectively utilize video visual cues to choose keyframes. However, apart fr...

    Yinghong Fang, Junpeng Zhang, Cewu Lu in Neural Information Processing (2019)