Structured Encoding Based on Semantic Disambiguation for Video Captioning.
Bo SunJinyu TianYong WuLunjun YuYuanyan TangPublished in: Cogn. Comput. (2024)
Keyphrases
- information retrieval
- natural language
- semantic search
- video event
- video sequences
- semantic concepts
- video data
- video content
- video streams
- video encoding
- content based video retrieval
- co occurrence
- real time
- video frames
- semantic similarity
- key frames
- multimedia
- real time video
- structured data
- information extraction
- video analysis
- audio visual content
- sports video
- encoding process
- high level
- space time
- semantic video
- word sense disambiguation
- video retrieval
- video clips
- digital video
- semantic information
- low complexity
- video processing
- semantic representation
- video encoder
- natural language processing
- compressed video
- semantic content
- domain specific
- semantic network
- semantic web
- semantic annotation
- human activities