Waterfall Transformer for Multi-person Pose Estimation
Not on the map. Why?
Abstract (arXiv)
We propose the Waterfall Transformer architecture for Pose estimation (WTPose), a single-pass, end-to-end trainable framework designed for multi-person pose estimation. Our framework leverages a transformer-based waterfall module that generates multi-scale feature maps from various backbone stages. The module performs filtering in the cascade architecture to expand the receptive fields and to capture local and global context, therefore increasing the overall feature representation capability of the network. Our experiments on the COCO dataset demonstrate that the proposed WTPose architecture, with a modified Swin backbone and transformer-based waterfall module, outperforms other transformer architectures for multi-person pose estimation
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 36 of its 45 references that are in the map. First posted on arXiv 28 Nov 2024.
Builds on
36 of 45 references.
References · 36
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
- 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
- 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
- 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
- 2019On the Convergence of Adam and Beyondcited by 841
- 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
- 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
24 more
- 2016Convolutional Pose Machinescited by 325
- 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
- 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
- 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
- 2022Neighborhood Attention Transformercited by 239
- 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
- 2020TransPose: Keypoint Localization via Transformercited by 126
- 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
- 2021TokenPose: Learning Keypoint Tokens for Human Pose Estimationcited by 107
- 2017Multi-Context Attention for Human Pose Estimationcited by 66
- 2022Dilated Neighborhood Attention Transformercited by 64
- 2019Rethinking on Multi-Stage Networks for Human Pose Estimationcited by 58
- 2016Human pose estimation via Convolutional Part Heatmap Regressioncited by 51
- 2019DirectPose: Direct End-to-End Multi-Person Pose Estimationcited by 49
- 2020UniPose: Unified Human Pose Estimation in Single Images and Videoscited by 49
- 2023Human Pose as Compositional Tokenscited by 45
- 2022Poseur: Direct Human Pose Regression with Transformerscited by 43
- 2021Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Trackingcited by 37
- 2021FCPose: Fully Convolutional Multi-Person Pose Estimation with Dynamic Instance-Aware Convolutionscited by 34
- 201915 Keypoints Is All You Needcited by 23
- 2019Human Pose Estimation with Spatial Contextual Informationcited by 21
- 2022Lite Pose: Efficient Architecture Design for 2D Human Pose Estimationcited by 16
- 2021OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimationcited by 6
- 2021BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representationscited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.