Dense Video Captioning for Incomplete Videos.
Xuan DangGuolong WangKun XiongZheng QinPublished in: ICANN (5) (2021)
Keyphrases
- video content
- video frames
- video sequences
- video data
- video database
- video analysis
- video clips
- key frames
- youtube videos
- video editing
- online video
- video dataset
- input video
- temporal coherence
- video surveillance
- video annotation
- event recognition
- human activities
- video indexing
- video segments
- video images
- video event
- video browsing
- successive frames
- video shots
- video streams
- dynamic scenes
- natural language descriptions
- multimedia
- video classification
- video representation
- high definition
- spatiotemporal features
- surveillance videos
- video search
- stereoscopic video
- video retrieval
- motion features
- video material
- video sharing
- moving camera
- user generated
- content based copy detection
- web videos
- news video
- human actions
- foreground background segmentation
- high frame rate
- action detection
- spatial and temporal
- visual analysis
- event detection
- visual features
- semantic concept detection
- video stabilization
- instructional videos
- video collections
- sports video
- video signals
- spatio temporal
- video summaries
- image sequences
- temporal information
- stationary camera
- dynamic textures
- lecture videos