Fast Semantic Segmentation on Video Using Block Motion-Based Feature Interpolation

  title={Fast Semantic Segmentation on Video Using Block Motion-Based Feature Interpolation},
  author={S. Jain and Joseph E. Gonzalez},
  booktitle={ECCV Workshops},
  • S. Jain, Joseph E. Gonzalez
  • Published in ECCV Workshops 2018
  • Computer Science
  • Convolutional networks optimized for accuracy on challenging, dense prediction tasks are often prohibitively slow to run on each frame in a video. The spatial similarity of nearby video frames, however, suggests opportunity to reuse computation. Existing work has explored basic feature reuse and feature warping based on optical flow, but has encountered limits to the speedup attainable with these techniques. In this paper, we present a new, two part approach to accelerating inference on video… CONTINUE READING
    6 Citations
    Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video
    • S. Jain, Xin Wang, Joseph E. Gonzalez
    • Computer Science
    • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2019
    • 20
    • PDF
    TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge
    How to Train Your Dragon: Tamed Warping Network for Semantic Video Segmentation
    Temporal information integration for video semantic segmentation
    Learnable Hollow Kernels for Anatomical Segmentation
    • 1
    • PDF


    Semantic Video CNNs Through Representation Warping
    • 81
    • PDF
    Compressed Video Action Recognition
    • 118
    • PDF
    Budget-Aware Deep Semantic Video Segmentation
    • 22
    • PDF
    Clockwork Convnets for Video Semantic Segmentation
    • 99
    • PDF
    Real-Time Action Recognition with Enhanced Motion Vector CNNs
    • 250
    • PDF
    Video Segmentation with Just a Few Strokes
    • 109
    • PDF
    Combining Appearance and Structure from Motion Features for Road Scene Understanding
    • 217
    • PDF
    Video Segmentation via Object Flow
    • 217
    • PDF
    FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos
    • 205
    • PDF
    Deep Feature Flow for Video Recognition
    • 203
    • Highly Influential
    • PDF