Papers › Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition

Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition

4 Jul 2017arXiv:1707.00823archive 2025-07-28

Jian Liu, Naveed Akhtar, Ajmal Mian

We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints. Learning such universal models requires training images where all factors are varied for every human pose. Capturing such data is prohibitively expensive. Therefore, we develop a framework for synthesizing the training data. First, we learn representative human poses from a large corpus of real motion captured human skeleton data. Next, we fit synthetic 3D humans with different body shapes to each pose and render each from 180 camera viewpoints while randomly varying the clothing textures, background and lighting. Generative Adversarial Networks are employed to minimize the gap between synthetic and real image distributions. CNN models are then learned that transfer human poses to a shared high-level invariant space. The learned CNN models are then used as invariant feature extractors from real RGB and depth frames of human action videos and the temporal variations are modelled by Fourier Temporal Pyramid. Finally, linear SVM is used for classification. Experiments on three benchmark cross-view human action datasets show that our algorithm outperforms existing methods by significant margins for RGB only and RGB-D action recognition.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionSkeleton Based Action RecognitionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition NTU RGB+D HPM_RGB+HPM_3D+Traj Accuracy (CS) 80.9 #110 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D HPM_RGB+HPM_3D+Traj Accuracy (CV) 86.1 #110 of 135 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

SVM

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