arXiv:2511.13208v2 Announce Type: replace 
Abstract: Existing multi-person video pose estimation methods typically adopt a two-stage pipeline: detecting individuals in each frame, followed by temporal modeling for single person pose estimation. This design relies on heuristic operations such as detection, RoI cropping, and non-maximum suppression (NMS), limiting both accuracy and efficiency. In this paper, we present a fully end-to-end framework for multi-person 2D pose estimation in videos, effectively eliminating heuristic operations. A key challenge is to associate individuals across frames under complex and overlapping temporal trajectories. To address this, we introduce a novel Pose-Aware Video transformEr Network (PAVE-Net), which features a spatial encoder to model intra-frame relations and a spatiotemporal pose decoder to capture global dependencies across frames. To achieve accurate temporal association, we propose a pose-aware attention mechanism that enables each pose query to selectively aggregate features corresponding to the same individual across consecutive frames. Additionally, we explicitly model spatiotemporal dependencies among pose keypoints to improve accuracy. Notably, our approach is the first end-to-end method for multi-frame 2D human pose estimation. Extensive experiments show that PAVE-Net substantially outperforms prior image-based end-to-end methods, achieving a 6.0 mAP improvement on PoseTrack2017, and delivers accuracy competitive with state-of-the-art two-stage video based approaches, while offering significant gains in efficiency. Project page: https://github.com/zgspose/PAVENet.

تم تقديم إطار جديد لتقدير وضع الأشخاص المتعددين في مقاطع الفيديو من النهاية إلى النهاية، مما يلغي الاعتماد على العمليات الاستدلالية التي تحد من الدقة والكفاءة. هذا الإطار، المعروف باسم شبكة المحول المعنية بالوضع (PAVE-Net)، يربط الأفراد بفعالية عبر الإطارات، مما يعالج التحديات المتعلقة بالمسارات المعقدة والمتداخلة في بيانات الفيديو.

Se ha introducido un nuevo marco de estimación de pose 2D multi-personas en videos de extremo a extremo, eliminando la dependencia de operaciones heurísticas que limitan la precisión y la eficiencia. Este marco, denominado Pose-Aware Video transformEr Network (PAVE-Net), asocia eficazmente a los individuos a través de los fotogramas, abordando los desafíos de trayectorias complejas y superpuestas en los datos de video.

Un nouveau cadre de bout en bout pour l'estimation de pose 2D multi-personnes dans les vidéos a été introduit, éliminant la dépendance aux opérations heuristiques qui limitent la précision et l'efficacité. Ce cadre, nommé Pose-Aware Video transformEr Network (PAVE-Net), associe efficacement les individus à travers les images, abordant les défis des trajectoires complexes et chevauchantes dans les données vidéo.

A new end-to-end framework for multi-person 2D pose estimation in videos has been introduced, eliminating the reliance on heuristic operations that limit accuracy and efficiency. This framework, named Pose-Aware Video transformEr Network (PAVE-Net), effectively associates individuals across frames, addressing the challenges of complex and overlapping trajectories in video data.