Skip to Content
× You are about to create a new metadata only record. This record does not auto assign a DOI. To allocate a new DOI use the 'Upload data and allocate DOI' option.

Traditional Chinese Medicine Action Quality Assessment (TCM-AQA61)

TCM-AQA61 is a synchronized multi-view video dataset developed to support action quality assessment of finegrained procedures in Traditional Chinese Medicine rehabilitation training. It comprises two subsets, TCM-AQA61- A for acupuncture practice and TCM-AQA61-T for Tuina practice, each containing synchronized first-person and third-person video recordings of 61 participants performing structured procedures on a simulated practice platform. The complementary viewpoints capture detailed hand movements, hand-object interactions and manipulation dynamics from both participant and observer perspectives. Each performance was independently assessed by two experienced Traditional Chinese Medicine practitioners using clinically informed criteria, with annotations covering both categorical skill indicators and continuous performance measures, including aspects such as posture, technique, movement depth, amplitude and manipulation frequency. The dataset is intended to support research in action quality assessment, multi-view video understanding, fine-grained human action analysis, skill evaluation and vision-based training. More information: https://hubertshum.com

Descriptions

Resource type
Collection
Total Items
11
Size
97.6 GB
Contributors
Editor: Shum, Hubert P. H. 1
Editor: Zhang, Francis Xiatian 2
1 Durham University, UK
2 University of Edinburgh, UK
Research methods
The TCM-AQA61 dataset was collected using a synchronized multi-view recording setup in which participants performed structured acupuncture and Tuina procedures on a simulated practice platform. Each session was captured simultaneously from first-person and third-person viewpoints to provide complementary observations of hand movements, hand-object interactions and overall procedural execution. The recorded performances were independently evaluated by two experienced Traditional Chinese Medicine practitioners using predefined, clinically informed assessment criteria. The annotations include both categorical indicators of procedural quality and continuous measurements of movement characteristics, covering factors such as posture, technique, manipulation depth, movement amplitude and operation frequency. Any disagreements between the assessors were reviewed and resolved through consensus to improve annotation consistency.
Other description
Francis Xiatian Zhang, Hao Yao, Shengxuan Chen, Hong Zhu, Hongxiao Jia, Sisi Zheng and Hubert P. H. Shum, "Cross-view Multimodal Vision-Based Assessment Framework for Traditional Chinese Medicine Rehabilitation Training," IEEE Transactions on Neural Systems and Rehabilitation Engineering, IEEE, 2026.
Subject
Medicine, Chinese--Research
Machine learning
Cited in
doi:10.1109/TNSRE.2026.3705649
Identifier
ark:/32150/r1jm214p229
Publisher
Durham University
Collection icon

Actions

Items in this Collection

Sort the listing of items    
View results as:
List Gallery Masonry Slideshow
List of items in this collection
  Title Date Uploaded Visibility Action
 

README documentation for Traditional Chinese Medicine Action Quality Assessment (TCM-AQA61)

Is part of: Traditional Chinese Medicine Action Quality Assessment (TCM-AQA61)
16 July 2026 Open Access
File Name:
README.md
File Format:
plain (Plain text)
Creator:
Depositor:
P. Shum
Edit Access:
Users: cbmw62
2