Summary of Enhancing Human Action Recognition and Violence Detection Through Deep Learning Audiovisual Fusion, by Pooya Janani (1) et al.
Enhancing Human Action Recognition and Violence Detection Through Deep Learning Audiovisual Fusion
by Pooya Janani, Amirabolfazl Suratgar, Afshin Taghvaeipour
First submitted to arxiv on: 4 Aug 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG); Multimedia (cs.MM); Image and Video Processing (eess.IV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed hybrid fusion-based deep learning approach combines audio and video modalities to improve human activity recognition and violence detection in public spaces. The study compares different fusion techniques, including late, intermediate, and hybrid fusion-based deep learning (HFBDL), with the goal of detecting and recognizing violence. Results show 96.67% accuracy on validation data, outperforming state-of-the-art methods. Additionally, the model demonstrates a promising performance in real-world scenarios, correctly detecting 52 out of 54 videos. This approach has potential applications for security purposes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper develops a new way to use deep learning to recognize human activities and detect violence in public places. By combining audio and video data, the method can better identify violent behavior. The researchers tested different ways of combining this information and found that their new approach worked best. They also showed that it works well on real-life videos. This could be useful for security purposes. |
Keywords
* Artificial intelligence * Activity recognition * Deep learning
