Papers › UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition

UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition

19 Jul 2021arXiv:2107.08580archive 2025-07-28

Di Yang, Yaohui Wang, Antitza Dantcheva, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond

Action recognition based on skeleton data has recently witnessed increasing attention and progress. State-of-the-art approaches adopting Graph Convolutional networks (GCNs) can effectively extract features on human skeletons relying on the pre-defined human topology. Despite associated progress, GCN-based methods have difficulties to generalize across domains, especially with different human topological structures. In this context, we introduce UNIK, a novel skeleton-based action recognition method that is not only effective to learn spatio-temporal features on human skeleton sequences but also able to generalize across datasets. This is achieved by learning an optimal dependency matrix from the uniform distribution based on a multi-head attention mechanism. Subsequently, to study the cross-domain generalizability of skeleton-based action recognition in real-world videos, we re-evaluate state-of-the-art approaches as well as the proposed UNIK in light of a novel Posetics dataset. This dataset is created from Kinetics-400 videos by estimating, refining and filtering poses. We provide an analysis on how much performance improves on smaller benchmark datasets after pre-training on Posetics for the action classification task. Experimental results show that the proposed UNIK, with pre-training on Posetics, generalizes well and outperforms state-of-the-art when transferred onto four target action classification datasets: Toyota Smarthome, Penn Action, NTU-RGB+D 60 and NTU-RGB+D 120.

PaperPDFCode

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

Code

YangDi666/UNIK officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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 ClassificationAction RecognitionSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Toyota Smarthome dataset UNIK CS 64.3 #4 of 13 Archive leaderboard report
Action Classification Toyota Smarthome dataset UNIK CV1 36.1 #4 of 13 Archive leaderboard report
Action Classification Toyota Smarthome dataset UNIK CV2 65.0 #4 of 13 Archive leaderboard report
Skeleton Based Action Recognition UPenn Action UNIK Accuracy 97.9 #1 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.

Methods

Graph Convolutional NetworksLinear LayerSoftmax

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