MHSCNet: A Multimodal Hierarchical Shot-aware Convolutional Network for Video Summarization.
Wujiang XuShaoshuai LiQiongxu MaYunan ZhaoSheng GuoXiaobo GuoBing HanJunchi YanYifei XuPublished in: CoRR (2022)
Keyphrases
- video summarization
- video content
- audio visual
- key frames
- video data
- convolutional network
- video sequences
- coarse to fine
- convolutional neural networks
- multi modal
- video retrieval
- sports video
- event detection
- multimedia
- video shots
- low level features
- video streams
- surveillance videos
- multiresolution
- video database
- visual content
- video analysis
- dynamic programming
- object recognition
- feature vectors
- visual features
- multiscale
- multi class
- low level