STSI: Efficiently Mine Spatio- Temporal Semantic Information between Different Multimodal for Video Captioning.
Huiyu XiongLanxiao WangPublished in: VCIP (2022)
Keyphrases
- semantic information
- spatio temporal
- spatial and temporal
- semantic concepts
- space time
- wordnet
- semantic knowledge
- semantic analysis
- human actions
- domain knowledge
- semantic features
- multimedia
- video data
- video sequences
- semantic meaning
- structural information
- video frames
- low level features
- metadata
- low level
- image sequences
- keywords
- spatio temporally
- high level
- multi modal
- video content
- video clips
- contextual information
- video analysis
- semantic relatedness
- xml documents
- moving objects
- semantic content
- textual descriptions
- visual information
- domain ontology
- expert systems
- semantic similarity
- semantic tags
- syntactic information