Sequence-Aware Learnable Sparse Mask for Frame-Selectable End-to-End Dense Video Captioning for IoT Smart Cameras.
Syu-Huei HuangChing-Hu LuPublished in: IEEE Internet Things J. (2024)
Keyphrases
- end to end
- video frames
- smart camera
- scalable video
- key frames
- video sequences
- video data
- video processing
- video content
- video streams
- real time
- multimedia
- frame rate
- ad hoc networks
- traffic monitoring
- camera network
- video analysis
- surveillance system
- dynamic scenes
- multimedia data
- sparse representation
- video segmentation
- network topology
- computer vision algorithms
- video surveillance
- foreground detection
- transport protocol