Learning Delicate Local Representations for Multi-Person Pose Estimation
In this paper, we propose a novel method called Residual Steps Network (RSN). RSN aggregates features with the same spatial size (Intra-level features) efficiently to obtain delicate local representations, which retain rich low-level spatial information and result in precise keypoint localization. Additionally, we observe the output features contribute differently to final performance. To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations. Our approach won the 1st place of COCO Keypoint Challenge 2019 and achieves state-of-the-art results on both COCO and MPII benchmarks, without using extra training data and pretrained model. Our single model achieves 78.6 on COCO test-dev, 93.0 on MPII test dataset. Ensembled models achieve 79.2 on COCO test-dev, 77.1 on COCO test-challenge dataset. The source code is publicly available for further research at https://github.com/caiyuanhao1998/RSN/
Code (4)
Tasks
Keypoint DetectionMulti-Person Pose EstimationPose EstimationSimilar Papers 제목 키워드 기반
TransFR: Transferable Federated Recommendation with Pre-trained Language Models
Federated recommendations (FRs), facilitating multiple local clients to collectively learn a global model without disclosing user private data, have emerged as a prevalent architecture for privacy-preserving recommendati…
Privacy PreservingAdaFedFR: Federated Face Recognition with Adaptive Inter-Class Representation Learning
With the growing attention on data privacy and communication security in face recognition applications, federated learning has been introduced to learn a face recognition model with decentralized datasets in a privacy-pr…
Face ModelFace RecognitionFederated LearningPrivacy Preserving+1Collaborative Filtering Approach to Link Prediction
Link prediction is a fundamental challenge in network science. Among various methods, local similarity indices are widely used for their high cost-performance. However, the performance is less robust: for some networks l…
Collaborative FilteringLink PredictionPredictionRecommendation SystemsGaussianEditor: Editing 3D Gaussians Delicately with Text Instructions
Recently, impressive results have been achieved in 3D scene editing with text instructions based on a 2D diffusion model. However, current diffusion models primarily generate images by predicting noise in the latent spac…
3D scene EditingGPUOIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search
We address the task of person search, that is, localizing and re-identifying query persons from a set of raw scene images. Recent approaches are typically built upon OIMNet, a pioneer work on person search, that learns j…
Person Re-IdentificationPerson Search