{"slug": "uncovering-the-blind-spots-of-oks-map-a-unified-protocol-for-occlusion-joint-and", "title": "Uncovering the Blind Spots of OKS-mAP: A Unified Protocol for Occlusion, Joint-Angle, and Temporal Evaluation of 2D Pose Estimators", "summary": "A new arXiv paper (2611.12911v1) proposes a three-module supplementary evaluation protocol for 2D human pose estimation, arguing that the standard OKS-mAP metric has blind spots on occlusion, joint-angle error and temporal stability. Across COCO val2017, CrowdPose, OCHuman and PoseTrack18 and four models from two architecture families (YOLO11s-pose, an occlusion-domain fine-tuned variant, ViTPose-B/L), the authors report the occlusion gap Delta_occ was negative in every combination, ranging from -0.19 to -0.47, meaning aggregate mAP overestimates occluded-scene performance. On PoseTrack18 val, pixel-domain OneEuro smoothing cut jump rates 9-10% at no matched-scope AP cost, and the protocol and harness are open-sourced as a complement to, not a replacement for, OKS-mAP.", "body_md": "arXiv:2611.12911v1 Announce Type: new \nAbstract: The dominant metric for 2D human pose estimation, OKS-mAP, has three blind spots: it does not distinguish visible from occluded keypoints, does not measure joint-angle error, and is silent on the temporal stability of tracking-free per-frame inference. We propose a supplementary protocol with three modules: (M1) OKS-mAP stratified by ground-truth visibility, with Delta_occ = mAP(v=1) - mAP(full), quantifying how much the aggregate metric masks occlusion-specific differences; (M2) joint-angle error (RMSE/MAE/P95) plus knee-valgus detection consistency; (M3) frame-to-frame displacement, median-filter residual jitter, and jump rate, before and after OneEuro smoothing. We ran it on four datasets (COCO val2017, CrowdPose, OCHuman, PoseTrack18) and four models from two architecture families (YOLO11s-pose, an occlusion-domain fine-tuned variant, ViTPose-B/L), under a common detector-free oracle protocol and an open-source harness. Delta_occ is negative in every combination (-0.19 to -0.47): aggregate mAP overestimates occluded-scene performance in every tested combination. Joint-angle error is amplified in occluded layers; angle metrics reveal differences mAP cannot localize, e.g., the smaller occlusion-trained model significantly outperforming a larger transformer in occluded elbows. On PoseTrack18 val, raw jitter matched between the two YOLO models; pixel-domain OneEuro smoothing cut jump rates 9-10% at no matched-scope AP cost; residual jitter persists after detector removal; the transformer pair's jump rate is significantly lower; smoothing benefits replicate across architectures. Stratified mAP tracks full mAP closely (sign-consistency 1.0, 12/12), serving magnitude diagnosis rather than re-ranking; angle-metric difference vectors (especially knee) partially diverge, suggesting independent information. The protocol and harness are open-sourced, complementing rather than replacing OKS-mAP.", "url": "https://wpnews.pro/news/uncovering-the-blind-spots-of-oks-map-a-unified-protocol-for-occlusion-joint-and", "canonical_source": "https://arxiv.org/abs/2611.12911", "published_at": "2026-11-11 05:00:00+00:00", "updated_at": "2026-11-11 05:23:56.241524+00:00", "lang": "en", "topics": ["computer-vision", "ai-research", "machine-learning"], "entities": ["arXiv", "OKS-mAP", "COCO val2017", "CrowdPose", "OCHuman", "PoseTrack18", "YOLO11s-pose", "ViTPose-B/L"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/uncovering-the-blind-spots-of-oks-map-a-unified-protocol-for-occlusion-joint-and", "markdown": "https://wpnews.pro/news/uncovering-the-blind-spots-of-oks-map-a-unified-protocol-for-occlusion-joint-and.md", "text": "https://wpnews.pro/news/uncovering-the-blind-spots-of-oks-map-a-unified-protocol-for-occlusion-joint-and.txt", "jsonld": "https://wpnews.pro/news/uncovering-the-blind-spots-of-oks-map-a-unified-protocol-for-occlusion-joint-and.jsonld"}}