Papers › Skeleton Image Representation for 3D Action Recognition based on Tree Structure and...

Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints

11 Sep 2019arXiv:1909.05704archive 2025-07-28

Carlos Caetano, François Brémond, William Robson Schwartz

In the last years, the computer vision research community has studied on how to model temporal dynamics in videos to employ 3D human action recognition. To that end, two main baseline approaches have been researched: (i) Recurrent Neural Networks (RNNs) with Long-Short Term Memory (LSTM); and (ii) skeleton image representations used as input to a Convolutional Neural Network (CNN). Although RNN approaches present excellent results, such methods lack the ability to efficiently learn the spatial relations between the skeleton joints. On the other hand, the representations used to feed CNN approaches present the advantage of having the natural ability of learning structural information from 2D arrays (i.e., they learn spatial relations from the skeleton joints). To further improve such representations, we introduce the Tree Structure Reference Joints Image (TSRJI), a novel skeleton image representation to be used as input to CNNs. The proposed representation has the advantage of combining the use of reference joints and a tree structure skeleton. While the former incorporates different spatial relationships between the joints, the latter preserves important spatial relations by traversing a skeleton tree with a depth-first order algorithm. Experimental results demonstrate the effectiveness of the proposed representation for 3D action recognition on two datasets achieving state-of-the-art results on the recent NTU RGB+D~120 dataset.

PaperPDFCode

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

Code

carloscaetano/skeleton-images officialmentioned in papermentioned on GitHub 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

3D Action RecognitionAction RecognitionSkeleton Based Action RecognitionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition NTU RGB+D 120 TSRJI Accuracy (Cross-Setup) 67.9 #19 of 21 Archive leaderboard report
Action Recognition NTU RGB+D 120 TSRJI Accuracy (Cross-Subject) 62.8 #19 of 21 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D TSRJI (Late Fusion) + HCN Accuracy (CS) 73.3 #125 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D TSRJI (Late Fusion) + HCN Accuracy (CV) 80.3 #125 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 TSRJI (Late Fusion) + HCN Accuracy (Cross-Setup) 62.8% #68 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 TSRJI (Late Fusion) + HCN Accuracy (Cross-Subject) 67.9% #68 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 TSRJI (Late Fusion) Accuracy (Cross-Setup) 59.7% #70 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 TSRJI (Late Fusion) Accuracy (Cross-Subject) 65.5% #70 of 83 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