Papers › Forward Propagation, Backward Regression, and Pose Association for Hand Tracking in the Wild

Forward Propagation, Backward Regression, and Pose Association for Hand Tracking in the Wild

1 Jan 2022CVPR 2022 1archive 2025-07-28

Mingzhen Huang, Supreeth Narasimhaswamy, Saif Vazir, Haibin Ling, Minh Hoai

We propose HandLer, a novel convolutional architecture that can jointly detect and track hands online in unconstrained videos. HandLer is based on Cascade-RCNNwith additional three novel stages. The first stage is Forward Propagation, where the features from frame t-1 are propagated to frame t based on previously detected hands and their estimated motion. The second stage is the Detection and Backward Regression, which uses outputs from the forward propagation to detect hands for frame t and their relative offset in frame t-1. The third stage uses an off-the-shelf human pose method to link any fragmented hand tracklets. We train the forward propagation and backward regression and detection stages end-to-end together with the other Cascade-RCNN components.To train and evaluate HandLer, we also contribute YouTube-Hand, the first challenging large-scale dataset of unconstrained videos annotated with hand locations and their trajectories. Experiments on this dataset and other benchmarks show that HandLer outperforms the existing state-of-the-art tracking algorithms by a large margin.

PaperPDFCode

Code

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

Multiple Object Trackingregression

Datasets

Introduced by this paper, per the archive.

YouTube-Hands

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multiple Object Tracking YouTube-Hands HandLer HOTA 59.4 #1 of 1 Archive leaderboard report
Multiple Object Tracking YouTube-Hands HandLer MOTA 70.0 #1 of 1 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