Summary of Generalized Jersey Number Recognition Using Multi-task Learning with Orientation-guided Weight Refinement, by Yung-hui Lin et al.
Generalized Jersey Number Recognition Using Multi-task Learning With Orientation-guided Weight Refinement
by Yung-Hui Lin, Yu-Wen Chang, Huang-Chia Shih, Takahiro Ogawa
First submitted to arxiv on: 3 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG); Multimedia (cs.MM)
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 paper proposes a multi-task learning method called the angle-digit refine scheme (ADRS) to improve jersey number recognition (JNR) in sports analytics. The ADRS approach combines human body orientation angles and digit number clues to recognize athletic jersey numbers, addressing challenges such as blurring, occlusion, deformity, and low resolution. By recognizing each individual digit, the method enables more robust results than previous approaches that ignored the impact of human body rotation angles on jersey digit identification. The proposed method outperforms state-of-the-art methods in terms of inference information and prediction accuracy, achieving 64.07% Top-1 accuracy and 89.97% Top-2 accuracy with corresponding F1 scores of 67.46% and 90.64%, respectively. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making it easier to recognize numbers on athletic jerseys in sports analytics. Right now, images can be blurry or hard to read because of things like body rotation angles, so this method tries to solve that problem. It’s called the angle-digit refine scheme (ADRS) and it combines two ideas: how the human body is positioned and what the numbers look like on the jersey. This makes it more accurate than other methods. The paper shows that this approach works well for different sports like soccer, football, basketball, volleyball, and baseball. |
Keywords
» Artificial intelligence » Inference » Multi task
