Simple Baselines for Human Pose Estimation and Tracking

@inproceedings{Xiao2018SimpleBF,
  title={Simple Baselines for Human Pose Estimation and Tracking},
  author={Bin Xiao and Haiping Wu and Yichen Wei},
  booktitle={ECCV},
  year={2018}
}
There has been significant progress on pose estimation and increasing interests on pose tracking in recent years. [...] Key Result State-of-the-art results are achieved on challenging benchmarks. The code will be released.Expand
The Network Improvement and Connection Refinement for Multi-Person Pose Estimation
TLDR
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. Expand
Multi-person pose tracking with occlusion solving using motion models
TLDR
To track and associate frame-by-frame human detections obtained using a deep learning approach, it is proposed to combine motion features extracted by optical flow and Kalman filtering, which allow us to predict the future poses of targets. Expand
A Simple Baseline for Pose Tracking in Videos of Crowed Scenes
TLDR
This paper presents the solution to ACM MM challenge: Large-scale Human-centric Video Analysis in Complex Events by using a multi-object tracking method to assign human ID to each bounding box generated by the detection model and generates the final pose tracking result. Expand
A Top-Down Approach to Articulated Human Pose Estimation and Tracking
TLDR
This paper aims to build a strong baseline system with three modules: human candidate detector, single-person pose estimator and human pose tracker, and chooses a generic object detector among state-of-the-art methods to detect human candidates. Expand
Multi-Domain Pose Network for Multi-Person Pose Estimation and Tracking
TLDR
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. Expand
Human Pose Regression by Combining Indirect Part Detection and Contextual Information
TLDR
This paper uses the proposed Soft-argmax function to convert feature maps directly to joint coordinates, resulting in a fully differentiable framework that is able to learn heat maps representations indirectly, without additional steps of artificial ground truth generation. Expand
FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
TLDR
This paper addresses the task of articulated multi-person pose estimation and tracking towards real-time speed by adopting an occlusion-aware Re-ID feature strategy in the pose tracking module of an end-to-end multi-task network (MTN). Expand
Manual Annotations on Depth Maps for Human Pose Estimation
TLDR
This paper proposes an annotation refinement tool of human poses, by means of body joints, and a novel set of fine joint annotations for the Watch-n-Patch dataset, which has been collected with the proposed tool. Expand
Explicit Pose Deformation Learning for Tracking Human Poses
TLDR
A method for human pose tracking that learns explicitly about the dynamic effects of human motion on joint appearance by incorporating concepts from human pose estimation into an optical flow-like framework and achieves state-of-the-art performance on standard benchmarks for various pose tracking tasks. Expand
Simple and Lightweight Human Pose Estimation
TLDR
This paper redesigns a lightweight bottleneck block with two non-novel concepts: depthwise convolution and attention mechanism and presents a Lightweight Pose Network (LPN) following the architecture design principles of SimpleBaseline. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 36 REFERENCES
Pose Flow: Efficient Online Pose Tracking
TLDR
An online optimization framework to build the association of cross-frame poses and form pose flows (PF-Builder) and a novel pose flow non-maximum suppression ( PF-NMS) is designed to robustly reduce redundant pose flows and re-link temporal disjoint ones. Expand
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
TLDR
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. Expand
Multi-Person Pose Estimation for PoseTrack with Enhanced Part Affinity Fields
This paper is a description for method we adopted in the competition of “PoseTrack, ICCV 2017 workshop” [1]. We presents an improved approach based on Part Affinity Fields (PAFs) [2]. To achieve aExpand
PoseTrack: A Benchmark for Human Pose Estimation and Tracking
TLDR
PoseTrack is a new large-scale benchmark for video-based human pose estimation and articulated tracking that conducts an extensive experimental study on recent approaches to articulated pose tracking and provides analysis of the strengths and weaknesses of the state of the art. Expand
Detect-and-Track: Efficient Pose Estimation in Videos
This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon theExpand
Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
This paper proposes a new hybrid architecture that consists of a deep Convolu-tional Network and a Markov Random Field. We show how this architecture is successfully applied to the challengingExpand
Towards Accurate Multi-person Pose Estimation in the Wild
TLDR
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. Expand
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learnExpand
DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
TLDR
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. Expand
Learning Feature Pyramids for Human Pose Estimation
TLDR
This work designs a Pyramid Residual Module (PRMs) to enhance the invariance in scales of DCNNs and provides theoretic derivation to extend the current weight initialization scheme to multi-branch network structures. Expand
...
1
2
3
4
...