mlsanityData to 7 Oct 2026

Full-Resolution Encoder-Decoder Networks with Multi-Scale Feature Fusion for Human Pose Estimation

arXiv 2106.00566 ↗First posted 1 Jun 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

To achieve more accurate 2D human pose estimation, we extend the successful encoder-decoder network, simple baseline network (SBN), in three ways. To reduce the quantization errors caused by the large output stride size, two more decoder modules are appended to the end of the simple baseline network to get full output resolution. Then, the global context blocks (GCBs) are added to the encoder and decoder modules to enhance them with global context features. Furthermore, we propose a novel spatial-attention-based multi-scale feature collection and distribution module (SA-MFCD) to fuse and distribute multi-scale features to boost the pose estimation. Experimental results on the MS COCO dataset indicate that our network can remarkably improve the accuracy of human pose estimation over SBN, our network using ResNet34 as the backbone network can even achieve the same accuracy as SBN with ResNet152, and our networks can achieve superior results with big backbone networks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 38 references that are in the map. First posted on arXiv 1 Jun 2021.

Builds on

32 of 38 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2017Mask R-CNNcited by 7,259
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2017Squeeze-and-Excitation Networkscited by 4,763
  10. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  11. 2017Non-local Neural Networkscited by 2,290
  12. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
20 more
  1. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  2. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  3. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  4. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  5. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  6. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  7. 2016Convolutional Pose Machinescited by 325
  8. 2017Integral Human Pose Regressioncited by 255
  9. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  10. 2018BAM: Bottleneck Attention Modulecited by 171
  11. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  12. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  13. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  14. 2016DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Modelcited by 96
  15. 2019The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimationcited by 79
  16. 2017Multi-Context Attention for Human Pose Estimationcited by 66
  17. 2018PoseFix: Model-agnostic General Human Pose Refinement Networkcited by 47
  18. 2016ArtTrack: Articulated Multi-person Tracking in the Wildcited by 27
  19. 2017Stacked Deconvolutional Network for Semantic Segmentationcited by 18
  20. 2019A Context-and-Spatial Aware Network for Multi-Person Pose Estimationcited by 3

Built on by

Not cited yet.