End-to-End Video Object Detection with Spatial-Temporal Transformers.
Lu HeQianyu ZhouXiangtai LiLi NiuGuangliang ChengXiao LiWenxuan LiuYunhai TongLizhuang MaLiqing ZhangPublished in: CoRR (2021)
Keyphrases
- spatial temporal
- end to end
- object detection
- video shots
- spatial and temporal
- action recognition
- temporal information
- congestion control
- spatio temporal
- computer vision
- temporal correlation
- human actions
- spatial and temporal information
- video retrieval
- video database
- video data
- scalable video
- video content
- spatial information
- low level
- object recognition