Papers › DVANet: Disentangling View and Action Features for Multi-View Action Recognition

DVANet: Disentangling View and Action Features for Multi-View Action Recognition

10 Dec 2023arXiv:2312.05719archive 2025-07-28

Nyle Siddiqui, Praveen Tirupattur, Mubarak Shah

In this work, we present a novel approach to multi-view action recognition where we guide learned action representations to be separated from view-relevant information in a video. When trying to classify action instances captured from multiple viewpoints, there is a higher degree of difficulty due to the difference in background, occlusion, and visibility of the captured action from different camera angles. To tackle the various problems introduced in multi-view action recognition, we propose a novel configuration of learnable transformer decoder queries, in conjunction with two supervised contrastive losses, to enforce the learning of action features that are robust to shifts in viewpoints. Our disentangled feature learning occurs in two stages: the transformer decoder uses separate queries to separately learn action and view information, which are then further disentangled using our two contrastive losses. We show that our model and method of training significantly outperforms all other uni-modal models on four multi-view action recognition datasets: NTU RGB+D, NTU RGB+D 120, PKU-MMD, and N-UCLA. Compared to previous RGB works, we see maximal improvements of 1.5\%, 4.8\%, 2.2\%, and 4.8\% on each dataset, respectively.

PaperPDFCode

Code

NyleSiddiqui/MultiView_Actions officialmentioned 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 RecognitionAction Recognition In VideosDecoder

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition N-UCLA DVANet Accuracy (Cross-Subject) 94.4 #1 of 1 Archive leaderboard report
Action Recognition N-UCLA DVANet Accuracy (Cross-View) 96.5 #1 of 1 Archive leaderboard report
Action Recognition NTU RGB+D DVANet (RGB only) Accuracy (CS) 93.4 #15 of 28 Archive leaderboard report
Action Recognition NTU RGB+D DVANet (RGB only) Accuracy (CV) 98.1 #15 of 28 Archive leaderboard report
Action Recognition NTU RGB+D 120 DVANet (RGB only) Accuracy (Cross-Setup) 90.4 #14 of 21 Archive leaderboard report
Action Recognition NTU RGB+D 120 DVANet (RGB only) Accuracy (Cross-Subject) 91.6 #14 of 21 Archive leaderboard report
Action Recognition In Videos PKU-MMD DVANet (RGB only) X-Sub 95.8 #5 of 5 Archive leaderboard report
Action Recognition In Videos PKU-MMD DVANet (RGB only) X-View 95.2 #5 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.

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