FTAN: Exploring Frame-Text Attention for lightweight Video Captioning.
Zijian ZengYali LiYue ZhengSiqi LiShengjin WangPublished in: ICCPR (2023)
Keyphrases
- lightweight
- video frames
- key frames
- video data
- video sequences
- single frame
- video content
- natural language descriptions
- news video
- image frames
- successive frames
- video search
- video analysis
- input video
- text mining
- text detection
- multimedia documents
- temporal coherence
- multimedia
- information retrieval
- dynamic scenes
- frame rate
- video clips
- video streams
- video objects
- video segments
- video surveillance
- wireless sensor networks
- video processing
- authentication protocol
- dos attacks
- keywords
- neighboring frames