ST-CLIP: Spatio-Temporal Enhanced CLIP Towards Dense Video Captioning.
Huimin ChenPengfei DuanMingru HuangJingyi GuoShengwu XiongPublished in: ICIC (11) (2024)
Keyphrases
- video clips
- spatio temporal
- key frames
- video data
- video database
- video streams
- video content
- spatial and temporal
- spatial temporal
- video segments
- space time
- video representation
- video frames
- long video
- video retrieval
- video shots
- video sequences
- video analysis
- spatio temporally
- video segmentation
- human actions
- low level features
- video images
- multimedia
- video copy detection
- video indexing
- feature vectors
- video processing
- digital video
- human motion
- dynamic scenes