Summary of Video-based Exercise Classification and Activated Muscle Group Prediction with Hybrid X3d-slowfast Network, by Manvik Pasula and Pramit Saha
Video-based Exercise Classification and Activated Muscle Group Prediction with Hybrid X3D-SlowFast Network
by Manvik Pasula, Pramit Saha
First submitted to arxiv on: 10 Jun 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 The paper presents a novel approach for exercise classification and muscle group activation prediction (MGAP), which has significant implications for personal fitness. The current methods rely on mounted sensors and are limited in scope, making them impractical for everyday use. To address these limitations, the researchers developed a video-based deep learning framework that can handle a broad range of exercises and muscle groups, including strength training. The approach integrates X3D and SlowFast models to enhance exercise classification and MGAP performance. The findings show that this hybrid method outperforms existing baseline models in accuracy, with optimal channel reduction values identified for the SlowFast model. The study also explores fine-tuning and sets a new benchmark for both tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps people do exercises better by using videos to recognize what exercise is being done and which muscles are working. Current methods use special sensors that can be tricky to wear, and they only work with certain exercises. The researchers created a new way to do this using video recordings and deep learning technology. They tested their approach on many different exercises and found it worked better than other methods. This could help people with disabilities or who are just starting out with exercise. |
Keywords
» Artificial intelligence » Classification » Deep learning » Fine tuning
