Morning, May 27th, lstanbul, Turkey
🔥🔥🔥 News 🔥🔥🔥
| May 27, 2024
Description of the 1st SkatingVerse Workshop & Challenge
Human action understanding (HAU) is an essential topic in computer vision. Typically, HAU aims to locate, classify, and assess the human actions from a given video. Many tasks, e.g., action recognition, action segmentation, action localization, and action assessment, belong to the research scope of HAU. However, in a real-world scenario, it is typically necessary not only to segment each fine-grained action but also to assess their quality. Existing tasks and corresponding methods alone cannot meet this requirement. To this end, we construct a dataset consisting of 1,687 continuous videos in figure skating competition. We encourage participants to develop intelligent computer vision algorithms that can segment and assess each single action in an original and continuous competition video. Particularly, algorithms that can distinguish exactly similar actions and give a score based on action competition are highly expected. We hope this challenge can further promote the machine's perceptual cognition, which is a big step in real artificial intelligence.
This workshop will bring together academic and industrial experts in the field of HAU to discuss the techniques and applications of HAU. Participants are invited to submit their original contributions, surveys, and case studies that address the human actions perception and understanding issues.
Figure 1 Examples of figure skating actions: A (Axel); Lo (Loop); F (Flip); CSp (Camel Spin); Lz (Lutz); NB (No Basic).
Topics of interest
The submissions are expected to deal with visual perception and processing tasks which include but are not limited to:
- Applications of computer vision and machine learning on HAU
- 2D/3D sensing techniques for professional sports
- Fine-grained human action recognition
- Segmentation or localization of human actions
- Open-set identification of human actions
- Assessment of fine-grained human actions
- Real-time lightweight deep learning inference for HAU tasks
- Large-scale benchmark datasets on HAU
- Biologically inspired computer vision techniques for HAU
- Technical survey on HAU