[PDF] RMPE: Regional Multi-person Pose Estimation | Semantic Scholar (2024)

[PDF] Semantic Reader

On the COCO keypoints dataset, the pose estimation method outperforms all previous bottom-up methods both in accuracy and speed; it also performs on par with the best top-down methods while being at least 4x faster.

A simple network called Multi-Domain Pose Network (MDPN) is presented, which shows significant improvement over baselines and achieves the best performance on PoseTrack ECCV 2018 Challenge without additional datasets other than MPII and COCO.

A novel framework PoseDet (Estimating Pose by Detection) to localize and associate body joints simultaneously at higher inference speed is presented and the keypoint-aware pose embedding to represent an object in terms of the locations of its keypoints is proposed.

The results prove that the proposed method can more effectively distinguish ambiguous keypoints and estimate poses and introduce a channel-attention mechanism to enhance the predictive ability of heat map on keypoints.

A multi-task model for human pose estimation and person detection simultaneously, named PersonPD (person pose and person Detection), which predicts keypoint heatmaps and regresses a 4D relative displacement vector which actually encodes the person bounding box and also acts as keypoints' grouping clues.

This work proposes and attention module that could let the model get global receptive field at the shallow layer of the network and pay more attention to the key areas which is more important to pose estimation.

The proposed PETR method views pose estimation as a hierarchical set prediction problem and effectively removes the need for many hand-crafted modules like RoI cropping, NMS and grouping post-processing, and largely overcomes the feature misalignment difficulty in pose estimation and improves the performance considerably.

This work proposes the integration of top-down and bottom-up approaches to address the common gaps between training and testing data, and introduces a two-person pose discriminator that enforces natural two- person interactions.

This article presents AlphaPose, a system that can perform accurate whole-body pose estimation and tracking jointly while running in realtime, and proposes several new techniques: Symmetric Integral Keypoint Regression (SIKR) for fast and fine localization, Parametric Pose Non-Maximum-Suppression (P-NMS) for eliminating redundant human detections and Pose Aware Identity Embedding for jointly posing and tracking.

A generic bottom-up approach for multi-person pose estimation is presented, which introduces limb detection heatmaps as a representation of body joint pairs association, which are simultaneously learned with joint detections.

...

...

This work proposes a method that estimates the poses of multiple persons in an image in which a person can be occluded by another person or might be truncated, and considers multi-person pose estimation as a joint-to-person association problem.

An approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene, identifies occluded body parts, and disambiguates body parts between people in close proximity of each other is proposed.

This work proposes a method for multi-person detection and 2-D pose estimation that achieves state-of-art results on the challenging COCO keypoints task by using a novel form of keypoint-based Non-Maximum-Suppression (NMS), instead of the cruder box-level NMS, and by introducing a novel aggregation procedure to obtain highly localized keypoint predictions.

This work proposes a new technique to extend an existing training set that allows to explicitly control pose and shape variations and defines a new challenge of combined articulated human detection and pose estimation in real-world scenes.

A novel multi-person pose estimation framework, which extends pictorial structures (PS) to explicitly model interactions between people and to estimate their poses jointly, resulting in better pose estimates in group photos, where several persons stand nearby and occlude each other.

This paper uses a model that resembles existing architectures for single-frame pose estimation but is substantially faster to generate proposals for body joint locations and forms articulated tracking as spatio-temporal grouping of such proposals.

A novel benchmark "MPII Human Pose" is introduced that makes a significant advance in terms of diversity and difficulty, a contribution that is required for future developments in human body models.

A novel network structure called Cascaded Pyramid Network (CPN) is presented which targets to relieve the problem from these "hard" keypoints, with state-of-art results on the COCO keypoint benchmark, with average precision at 73.0.

...

...