DHHN: Dual Hierarchical Hybrid Network for Weakly-Supervised Audio-Visual Video Parsing.
Xun JiangXing XuZhiguo ChenJingran ZhangJingkuan SongFumin ShenHuimin LuHeng Tao ShenPublished in: ACM Multimedia (2022)
Keyphrases
- audio visual
- weakly supervised
- visual data
- multimedia
- multi modal
- visual information
- video data
- topic models
- object class
- video sequences
- superpixels
- semi supervised
- natural language processing
- named entities
- machine learning
- relation extraction
- natural language
- video frames
- three dimensional
- data analysis
- object recognition