Multi-view learning for visual violence recognition with maximum entropy discrimination and deep features.
Information Fusion(2019)
Abstract
•We apply multi-view learning to violent behavior recognition of still images.•A violence image recognition database is constructed and made public.•We propose an MVMED+ model for learning with different numbers of views.•A sequential minimal optimization algorithm is provided for efficient training.•The proposed model outperforms multiple baselines.
MoreTranslated text
Key words
Maximum entropy discrimination,Multi-view learning,Sequential minimal optimization,Violence image recognition
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined