Summary of 3d Pose-based Temporal Action Segmentation For Figure Skating: a Fine-grained and Jump Procedure-aware Annotation Approach, by Ryota Tanaka et al.
3D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approach
by Ryota Tanaka, Tomohiro Suzuki, Keisuke Fujii
First submitted to arxiv on: 29 Aug 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 proposed paper tackles the task of Temporal Action Segmentation (TAS) in figure skating, focusing on automatically assigning temporal semantics to video sequences. The authors create a new dataset called FS-Jump3D, which captures complex and dynamic figure skating jumps using optical markerless motion capture. A fine-grained annotation method is also introduced for TAS models to learn jump procedures. Experimental results demonstrate the effectiveness of 3D pose features as input and the fine-grained dataset for TAS modeling in figure skating. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Figure skaters’ movements are analyzed to automatically assign meaning to video sequences. The goal is to create a system that can recognize specific actions, like jumps, in figure skating videos. To do this, the authors make a special dataset and a way to label it so machines can learn how to identify these actions. |
Keywords
» Artificial intelligence » Semantics
