Papers › NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle...

NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle Human Actions

27 Jan 2021arXiv:2101.11529archive 2025-07-28

Neel Trivedi, Anirudh Thatipelli, Ravi Kiran Sarvadevabhatla

The lack of fine-grained joints (facial joints, hand fingers) is a fundamental performance bottleneck for state of the art skeleton action recognition models. Despite this bottleneck, community's efforts seem to be invested only in coming up with novel architectures. To specifically address this bottleneck, we introduce two new pose based human action datasets - NTU60-X and NTU120-X. Our datasets extend the largest existing action recognition dataset, NTU-RGBD. In addition to the 25 body joints for each skeleton as in NTU-RGBD, NTU60-X and NTU120-X dataset includes finger and facial joints, enabling a richer skeleton representation. We appropriately modify the state of the art approaches to enable training using the introduced datasets. Our results demonstrate the effectiveness of these NTU-X datasets in overcoming the aforementioned bottleneck and improve state of the art performance, overall and on previously worst performing action categories. Code and pretrained models can be found at https://github.com/skelemoa/ntu-x .

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

skelemoa/ntu-x officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionSkeleton Based Action Recognition

Datasets

Introduced by this paper, per the archive.

NTU-X

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition NTU60-X 4s-ShiftGCN Accuracy (Body + Fingers + Face joints) 89.64 #1 of 3 Archive leaderboard report
Skeleton Based Action Recognition NTU60-X 4s-ShiftGCN Accuracy (Body + Fingers joints) 91.78 #1 of 3 Archive leaderboard report
Skeleton Based Action Recognition NTU60-X 4s-ShiftGCN Accuracy (Body joints) 89.56 #1 of 3 Archive leaderboard report
Skeleton Based Action Recognition NTU60-X MS-G3D Accuracy (Body + Fingers + Face joints) 91.12 #2 of 3 Archive leaderboard report
Skeleton Based Action Recognition NTU60-X MS-G3D Accuracy (Body + Fingers joints) 91.76 #2 of 3 Archive leaderboard report
Skeleton Based Action Recognition NTU60-X MS-G3D Accuracy (Body joints) 91.26 #2 of 3 Archive leaderboard report
Skeleton Based Action Recognition NTU60-X PA-ResGCN Accuracy (Body + Fingers + Face joints) 89.79 #3 of 3 Archive leaderboard report
Skeleton Based Action Recognition NTU60-X PA-ResGCN Accuracy (Body + Fingers joints) 91.64 #3 of 3 Archive leaderboard report
Skeleton Based Action Recognition NTU60-X PA-ResGCN Accuracy (Body joints) 89.98 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections