MHSCNET: A Multimodal Hierarchical Shot-Aware Convolutional Network for Video Summarization.
Wujiang XuRunzhong WangXiaobo GuoShaoshuai LiQiongxu MaYunan ZhaoSheng GuoZhenfeng ZhuJunchi YanPublished in: ICASSP (2023)
Keyphrases
- video summarization
- video content
- audio visual
- key frames
- convolutional network
- video data
- video sequences
- coarse to fine
- convolutional neural networks
- video retrieval
- multi modal
- video shots
- video streams
- low level features
- event detection
- surveillance videos
- visual features
- sports video
- video frames
- video analysis
- visual information
- feature vectors
- image sequences
- video surveillance
- visual content
- video database
- moving objects
- multiscale