Skip to main content

and
  1. No Access

    Article

    Trapezoid-structured LSTM with segregated gates and bridge joints for video frame inpainting

    This work considers the video frame inpainting problem, where several former and latter frames are given, and the goal is to predict the middle frames. The state-of-the-art solution has applied bidirectional l...

    Ting-Hui Chiang, Yun-Tang Lin, Jaden Chao-Ho Lin, Yu-Chee Tseng in The Visual Computer (2024)

  2. No Access

    Article

    HAPiCLR: heuristic attention pixel-level contrastive loss representation learning for self-supervised pretraining

    Recent self-supervised contrastive learning methods are powerful and efficient for robust representation learning, pulling semantic features from different crop** views of the same image while pushing other ...

    Van Nhiem Tran, Shen-Hsuan Liu, Chi-En Huang, Muhammad Saqlain Aslam in The Visual Computer (2024)