TubeFormer-DeepLab: Video Mask Transformer.
Dahun KimJun XieHuiyu WangSiyuan QiaoQihang YuHong-Seok KimHartwig AdamIn So KweonLiang-Chieh ChenPublished in: CVPR (2022)
Keyphrases
- video sequences
- video data
- multimedia
- video streams
- video content
- video frames
- video analysis
- fuzzy logic
- video surveillance
- spatial and temporal
- real time video
- video images
- video clips
- data sets
- video retrieval
- video database
- spatial temporal
- digital video
- video search
- motion vectors
- multimedia data
- event detection
- power system
- digital images
- spatio temporal
- expert systems
- computer vision
- neural network