Video captioning with stacked attention and semantic hard pull.
Md. Mushfiqur RahmanThasin AbedinKhondokar S. S. ProttoyAyana MoshrubaFazlul Hasan SiddiquiPublished in: PeerJ Comput. Sci. (2021)
Keyphrases
- video event
- video data
- multimedia
- semantic concepts
- video streams
- semantic web
- video frames
- sports video
- video content
- semantic video
- real time video
- video analysis
- domain specific
- semantic analysis
- video sequences
- low level features
- event detection
- digital video
- semantic relationships
- visual concepts
- semantic search
- event recognition
- video clips
- semantic annotation
- online video
- spatial and temporal
- space time
- multi modal
- low level
- real time
- high level
- semantic description
- semantic video retrieval
- soccer video
- video images
- semantic representation
- semantic knowledge
- video processing
- video segmentation
- video surveillance
- visual attention
- temporal information
- multimedia data
- semantic information
- natural language