Papers › Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields

Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields

29 Nov 2018CVPR 2019 6arXiv:1811.11975archive 2025-07-28

Yaadhav Raaj, Haroon Idrees, Gines Hidalgo, Yaser Sheikh

We present an online approach to efficiently and simultaneously detect and track the 2D pose of multiple people in a video sequence. We build upon Part Affinity Field (PAF) representation designed for static images, and propose an architecture that can encode and predict Spatio-Temporal Affinity Fields (STAF) across a video sequence. In particular, we propose a novel temporal topology cross-linked across limbs which can consistently handle body motions of a wide range of magnitudes. Additionally, we make the overall approach recurrent in nature, where the network ingests STAF heatmaps from previous frames and estimates those for the current frame. Our approach uses only online inference and tracking, and is currently the fastest and the most accurate bottom-up approach that is runtime invariant to the number of people in the scene and accuracy invariant to input frame rate of camera. Running at ∼30 fps on a single GPU at single scale, it achieves highly competitive results on the PoseTrack benchmarks.

PaperPDFConference PDF

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

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

Pose Tracking

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pose Tracking PoseTrack2017 STAF MOTA 53.81 #7 of 10 Archive leaderboard report
Pose Tracking PoseTrack2017 STAF mAP 70.28 #7 of 10 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