Papers › View-Invariant Probabilistic Embedding for Human Pose

View-Invariant Probabilistic Embedding for Human Pose

2 Dec 2019ECCV 2020 8arXiv:1912.01001archive 2025-07-28

Jennifer J. Sun, Jiaping Zhao, Liang-Chieh Chen, Florian Schroff, Hartwig Adam, Ting Liu

Depictions of similar human body configurations can vary with changing viewpoints. Using only 2D information, we would like to enable vision algorithms to recognize similarity in human body poses across multiple views. This ability is useful for analyzing body movements and human behaviors in images and videos. In this paper, we propose an approach for learning a compact view-invariant embedding space from 2D joint keypoints alone, without explicitly predicting 3D poses. Since 2D poses are projected from 3D space, they have an inherent ambiguity, which is difficult to represent through a deterministic mapping. Hence, we use probabilistic embeddings to model this input uncertainty. Experimental results show that our embedding model achieves higher accuracy when retrieving similar poses across different camera views, in comparison with 2D-to-3D pose lifting models. We also demonstrate the effectiveness of applying our embeddings to view-invariant action recognition and video alignment. Our code is available at https://github.com/google-research/google-research/tree/master/poem.

PaperPDFConference PDFCode

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

Code

google-research/google-research officialmentioned in papertf 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 RecognitionPose RetrievalSkeleton Based Action RecognitionVideo Alignment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pose Retrieval Human3.6M Pr-VIPE Hit@1 76.2 #1 of 1 Archive leaderboard report
Pose Retrieval Human3.6M Pr-VIPE Hit@10 95.6 #1 of 1 Archive leaderboard report
Pose Retrieval MPI-INF-3DHP Pr-VIPE Hit@1 26.4 #1 of 1 Archive leaderboard report
Pose Retrieval MPI-INF-3DHP Pr-VIPE Hit@10 58.6 #1 of 1 Archive leaderboard report
Skeleton Based Action Recognition UPenn Action Pr-VIPE Accuracy 97.5 #2 of 3 Archive leaderboard report
Video Alignment UPenn Action Pr-VIPE Kendall's Tau 0.7476 #2 of 4 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