Video Semantic Segmentation via Sparse Temporal Transformer.
Jiangtong LiWentao WangJunjie ChenLi NiuJianlou SiChen QianLiqing ZhangPublished in: ACM Multimedia (2021)
Keyphrases
- semantic segmentation
- street scenes
- superpixels
- conditional random fields
- label transfer
- video sequences
- weakly supervised
- video data
- scene classification
- pascal voc
- video frames
- object recognition
- object categories
- sparse representation
- image classification
- bag of words
- image understanding
- object classes
- long range
- computer vision