Skip to main content

and
  1. No Access

    Article

    Supervised biadjacency networks for stereo matching

    Convolutional neural network (CNN) based stereo matching methods using cost volume techniques have gained prominence in stereo matching. State-of-the-art cost volume based methods use two weight-sharing featur...

    Hanqing Sun, Jungong Han, Yanwei Pang, Xuelong Li in Multimedia Tools and Applications (2024)

  2. No Access

    Article

    Spatial attention-guided deformable fusion network for salient object detection

    Most of salient object detection methods employ U-shape architecture as the understructure. Although promising performance has been achieved, they struggle to detect salient objects with non-rigid shapes and a...

    Ai** Yang, Yan Liu, Simeng Cheng, Jiale Cao, Zhong Ji, Yanwei Pang in Multimedia Systems (2023)

  3. No Access

    Article

    Learning intensity and detail map** parameters for dehazing

    State-of-the-art methods for removing haze from a single image rely on a haze image formation model and the inversion problem is solved by estimating medium transmission and global atmospheric light. In this p...

    Xuhang Lian, Yanwei Pang, Ai** Yang in Multimedia Tools and Applications (2018)