End-to-End Video Object Detection with Spatial-Temporal Transformers.
Lu HeQianyu ZhouXiangtai LiLi NiuGuangliang ChengXiao LiWenxuan LiuYunhai TongLizhuang MaLiqing ZhangPublished in: ACM Multimedia (2021)
Keyphrases
- spatial temporal
- end to end
- object detection
- spatio temporal
- video shots
- temporal information
- action recognition
- spatial and temporal
- human actions
- scalable video
- temporal correlation
- computer vision
- spatial and temporal information
- visual information
- transport layer
- congestion control
- coding scheme
- spatial information
- space time
- video data
- multi modal
- wireless sensor networks
- mobile devices
- high level