Skip to main content

3 Result(s)

within Jun Ho Chung Remove this filter Data Structures and Information Theory Remove this filter

and

  1. No Access

    Article

    Binary dense sift flow based two stream CNN for human action recognition

    Two-stream CNN is a widely-used network for human action recognition. Two-stream CNN consists of a spatial stream and a temporal stream. The spatial stream, through which the RGB image passes, extracts the sha...

    Sang Kyoo Park, Jun Ho Chung, Tae Koo Kang… in Multimedia Tools and Applications (2021)

  2. No Access

    Article

    ADM-Net: attentional-deconvolution module-based net for noise-coupled traffic sign recognition

    Convolutional Neural Networks (CNNs) have become primary technologies in computer vision systems across multiple fields. Its central characteristic is to slide filters on input images and repeats the same proc...

    Jun Ho Chung, Dong Won Kim, Tae Koo Kang, Myo Taeg Lim in Multimedia Tools and Applications (2022)

  3. No Access

    Article

    Fusion-attention network using dense scale-invariant feature transform flow image and point cloud for 3D pedestrian detection

    In this paper, we introduce a fusion-attention network for three-dimensional (3D) pedestrian detection using the fusion of dense scale-invariant feature transform (SIFT) flow image and point cloud data. Becaus...

    Sang Kyoo Park, Jun Ho Chung, Dong Sung Pae… in Multimedia Tools and Applications (2024)