A Novel Approach for Video Captioning Based on Semantic Cross Embedding and Skip-Connection.
Rakesh RadarapuNishanth BandariSatwik MuthyamDinesh NaikPublished in: CVIP (3) (2020)
Keyphrases
- video event
- semantic concepts
- video sequences
- video data
- video frames
- video streams
- semantic web
- semantic video
- real time
- video content
- content based video retrieval
- video analysis
- semantic similarity
- high level
- multimedia data
- event detection
- vector space
- semantic network
- digital video
- multimedia
- natural language
- semantic representation
- visual concepts
- visual data
- semantic annotation
- temporal information
- domain specific
- video database
- digital images
- video clips
- video surveillance
- space time
- sports video
- event recognition
- online video
- spatial and temporal