Summary of Foul Prediction with Estimated Poses From Soccer Broadcast Video, by Jiale Fang et al.
Foul prediction with estimated poses from soccer broadcast video
by Jiale Fang, Calvin Yeung, Keisuke Fujii
First submitted to arxiv on: 15 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 This paper introduces a novel deep learning approach to predict soccer fouls by integrating video data, bounding box positions, image details, and pose information. The proposed method combines convolutional and recurrent neural networks (CNNs and RNNs) to merge information from these four modalities. Experimental results show that the full model outperformed ablated models, with all RNN modules, bounding box position and image, and estimated pose contributing to foul prediction. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research helps us understand soccer fouls better. It’s hard to predict when a player will commit a foul because it depends on many things like where they are on the field and what they’re doing. The researchers created a new way to use computer vision and deep learning to make these predictions. They combined different types of data, like video, location, and body pose, to create a model that can predict fouls. The results show that this approach works well, which is important for understanding the game better. |
Keywords
* Artificial intelligence * Bounding box * Deep learning * Rnn
