Papers › Detect-and-Track: Efficient Pose Estimation in Videos

Detect-and-Track: Efficient Pose Estimation in Videos

26 Dec 2017CVPR 2018 6arXiv:1712.09184archive 2025-07-28

Rohit Girdhar, Georgia Gkioxari, Lorenzo Torresani, Manohar Paluri, Du Tran

This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon the latest advancements in human detection and video understanding. Our method operates in two-stages: keypoint estimation in frames or short clips, followed by lightweight tracking to generate keypoint predictions linked over the entire video. For frame-level pose estimation we experiment with Mask R-CNN, as well as our own proposed 3D extension of this model, which leverages temporal information over small clips to generate more robust frame predictions. We conduct extensive ablative experiments on the newly released multi-person video pose estimation benchmark, PoseTrack, to validate various design choices of our model. Our approach achieves an accuracy of 55.2% on the validation and 51.8% on the test set using the Multi-Object Tracking Accuracy (MOTA) metric, and achieves state of the art performance on the ICCV 2017 PoseTrack keypoint tracking challenge.

PaperPDFConference PDFCode

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

Code

facebookresearch/DetectAndTrack mentioned on GitHubcaffe2 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

Human DetectionKeypoint EstimationMulti-Object TrackingObject TrackingPose EstimationPose TrackingVideo Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Keypoint Detection COCO test-challenge Girdhar et al. AR 70.2 #7 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Girdhar et al. ARM 60.7 #7 of 8 Archive leaderboard report
Pose Tracking PoseTrack2017 ProTracker MOTA 51.82 #8 of 10 Archive leaderboard report
Pose Tracking PoseTrack2017 ProTracker mAP 59.56 #8 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.

Methods

ConvolutionMask R-CNNRPNRoIAlignSoftmax

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