AI Paper Atlas

Research map / 3D vision / Human pose estimation

From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection

Yepeng Liu, Hao Li, Liwen Yang, Fangzhen Li, Xudi Ge, Yuliang Gu, Kuang Gao, Bing Wang, Guang Chen, Hangjun Ye, Yongchao Xu

CVPR 2026 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use sequence-level rewards instead of pairwise (ablation)TraqPoint · MegaDepth-1500 / KITTI Seq 01-03AUC@5 / AKTL: AUC@5 53.3 -> 55.8; AKTL 4.3 -> 6.6Improved
use track reward instead of basic match reward (ablation)TraqPoint · MegaDepth-1500 / KITTI Seq 01-03AUC@5 / AKTL: 49.7 -> 53.3 AUC@5; 2.8 -> 4.3 AKTLImproved
add rank reward (ablation)TraqPoint · MegaDepth-1500 / KITTI Seq 01-03AUC@5 / AKTL: 52.6 -> 55.8 AUC@5; 4.0 -> 6.6 AKTLImproved
add distinctiveness reward (ablation)TraqPoint · MegaDepth-1500 / KITTI Seq 01-03AUC@5 / AKTL: 54.6 -> 55.8 AUC@5; 5.9 -> 6.6 AKTLImproved
add RL training over supervised training (ablation)TraqPoint · MegaDepth-1500 / KITTI Seq 01-03AUC@5 / AKTL: 52.0 -> 55.8 AUC@5; 3.8 -> 6.6 AKTLImproved
use DINOv3-ConvNeXt instead of DINOv2-ViT (ablation)TraqPoint · MegaDepth-1500 / KITTI Seq 01-03AUC@5 / AKTL: 54.8 -> 55.8 AUC@5; 6.4 -> 6.6 AKTLImproved
use DINOv3-ConvNeXt instead of ResNet-50 (ablation)TraqPoint · MegaDepth-1500 / KITTI Seq 01-03AUC@5 / AKTL: 54.5 -> 55.8 AUC@5; 6.1 -> 6.6 AKTLImproved
lengthen training sequence beyond 5 frames (ablation)TraqPoint · MegaDepth-1500 / KITTI Seq 01-03AUC@5 / AKTLHurt
use TraqPoint instead of RDDTraqPoint · MegaDepth-1500AUC@5: 51.9 -> 55.8Improved
use TraqPoint instead of RDDTraqPoint · ETH Madrid MetropolisReproj Err: 1.03px vs RootSIFT 0.60pxHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy