Papers › Structure-Aware Human-Action Generation

Structure-Aware Human-Action Generation

4 Jul 2020ECCV 2020 8arXiv:2007.01971archive 2025-07-28

Ping Yu, Yang Zhao, Chunyuan Li, Junsong Yuan, Changyou Chen

Generating long-range skeleton-based human actions has been a challenging problem since small deviations of one frame can cause a malformed action sequence. Most existing methods borrow ideas from video generation, which naively treat skeleton nodes/joints as pixels of images without considering the rich inter-frame and intra-frame structure information, leading to potential distorted actions. Graph convolutional networks (GCNs) is a promising way to leverage structure information to learn structure representations. However, directly adopting GCNs to tackle such continuous action sequences both in spatial and temporal spaces is challenging as the action graph could be huge. To overcome this issue, we propose a variant of GCNs to leverage the powerful self-attention mechanism to adaptively sparsify a complete action graph in the temporal space. Our method could dynamically attend to important past frames and construct a sparse graph to apply in the GCN framework, well-capturing the structure information in action sequences. Extensive experimental results demonstrate the superiority of our method on two standard human action datasets compared with existing methods.

PaperPDFConference PDFCode

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

Code

PingYu-iris/SA-GCN 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 GenerationHuman action generationVideo Generationgraph construction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Human action generation Human3.6M SA-GCN MMDa 0.146 #2 of 5 Archive leaderboard report
Human action generation Human3.6M SA-GCN MMDs 0.134 #2 of 5 Archive leaderboard report
Human action generation NTU RGB+D 2D SA-GCN MMDa (CS) 0.285 #2 of 5 Archive leaderboard report
Human action generation NTU RGB+D 2D SA-GCN MMDa (CV) 0.316 #2 of 5 Archive leaderboard report
Human action generation NTU RGB+D 2D SA-GCN MMDs (CS) 0.299 #2 of 5 Archive leaderboard report
Human action generation NTU RGB+D 2D SA-GCN MMDs (CV) 0.335 #2 of 5 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

GCNGraph Convolutional Networks

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