Video saliency prediction for First-Person View UAV videos: Dataset and benchmark.
Hao CaiKao ZhangZhao ChenChenxi JiangZhenzhong ChenPublished in: Neurocomputing (2024)
Keyphrases
- human actions
- video dataset
- video frames
- video content
- web videos
- video sequences
- video data
- trecvid multimedia event detection
- event recognition
- video database
- action recognition
- video analysis
- multimedia event detection
- weakly labeled
- event detection
- youtube videos
- video clips
- saliency map
- online video
- video streams
- video editing
- video annotation
- video classification
- video search
- video indexing
- key frames
- human activities
- input video
- video images
- action classification
- video event detection
- video segments
- spatio temporal
- space time interest points
- spatiotemporal features
- video event
- concept detection
- video retrieval
- video representation
- temporal coherence
- content based copy detection
- user generated
- video shots
- video segmentation
- natural language descriptions
- multimedia
- video summarization
- dynamic scenes
- visual analysis
- sports video
- video quality assessment
- high definition
- successive frames
- motion features
- surveillance videos
- human motion
- lecture videos
- photo collections
- visual saliency
- space time
- semantic concept detection
- human visual system
- visual information
- spatial and temporal
- visual attention
- stereoscopic video
- low level features
- moving camera
- unmanned aerial vehicles