Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation.
Tianrui HuiShaofei HuangSi LiuZihan DingGuanbin LiWenguan WangJizhong HanFei WangPublished in: CVPR (2021)
Keyphrases
- spatial temporal
- video shots
- spatial and temporal
- spatio temporal
- temporal information
- action recognition
- image segmentation
- video sequences
- human actions
- multiscale
- natural language
- image classification
- video data
- spatial and temporal information
- machine learning
- video content
- three dimensional
- multimedia
- computer vision