</> Code with Papers by Syntology

Papers › Just Add π! Pose Induced Video Transformers for Understanding Activities of Daily Living

Just Add π! Pose Induced Video Transformers for Understanding Activities of Daily Living

30 Nov 2023arXiv:2311.18840archive 2025-07-28

Dominick Reilly, Srijan Das

Video transformers have become the de facto standard for human action recognition, yet their exclusive reliance on the RGB modality still limits their adoption in certain domains. One such domain is Activities of Daily Living (ADL), where RGB alone is not sufficient to distinguish between visually similar actions, or actions observed from multiple viewpoints. To facilitate the adoption of video transformers for ADL, we hypothesize that the augmentation of RGB with human pose information, known for its sensitivity to fine-grained motion and multiple viewpoints, is essential. Consequently, we introduce the first Pose Induced Video Transformer: PI-ViT (or π-ViT), a novel approach that augments the RGB representations learned by video transformers with 2D and 3D pose information. The key elements of π-ViT are two plug-in modules, 2D Skeleton Induction Module and 3D Skeleton Induction Module, that are responsible for inducing 2D and 3D pose information into the RGB representations. These modules operate by performing pose-aware auxiliary tasks, a design choice that allows π-ViT to discard the modules during inference. Notably, π-ViT achieves the state-of-the-art performance on three prominent ADL datasets, encompassing both real-world and large-scale RGB-D datasets, without requiring poses or additional computational overhead at inference.

PaperPDFCode

Code

dominickrei/pi-vit 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 ClassificationAction Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Toyota Smarthome dataset π-ViT CS 72.9 #1 of 13 Archive leaderboard report
Action Classification Toyota Smarthome dataset π-ViT CV1 55.2 #1 of 13 Archive leaderboard report
Action Classification Toyota Smarthome dataset π-ViT CV2 64.8 #1 of 13 Archive leaderboard report
Action Recognition NTU RGB+D π-ViT (RGB + Pose) Accuracy (CS) 96.3 #3 of 28 Archive leaderboard report
Action Recognition NTU RGB+D π-ViT (RGB + Pose) Accuracy (CV) 99.0 #3 of 28 Archive leaderboard report
Action Recognition NTU RGB+D π-ViT (RGB only) Accuracy (CS) 94.0 #12 of 28 Archive leaderboard report
Action Recognition NTU RGB+D π-ViT (RGB only) Accuracy (CV) 97.9 #12 of 28 Archive leaderboard report
Action Recognition NTU RGB+D 120 π-ViT (RGB + Pose) Accuracy (Cross-Setup) 96.1 #3 of 21 Archive leaderboard report
Action Recognition NTU RGB+D 120 π-ViT (RGB + Pose) Accuracy (Cross-Subject) 95.1 #3 of 21 Archive leaderboard report
Action Recognition NTU RGB+D 120 π-ViT (RGB only) Accuracy (Cross-Setup) 91.9 #8 of 21 Archive leaderboard report
Action Recognition NTU RGB+D 120 π-ViT (RGB only) Accuracy (Cross-Subject) 92.9 #8 of 21 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