mlsanityData to 7 Oct 2026

AttWalk: Attentive Cross-Walks for Deep Mesh Analysis

arXiv 2104.11571 ↗First posted 23 Apr 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Mesh representation by random walks has been shown to benefit deep learning. Randomness is indeed a powerful concept. However, it comes with a price: some walks might wander around non-characteristic regions of the mesh, which might be harmful to shape analysis, especially when only a few walks are utilized. We propose a novel walk-attention mechanism that leverages the fact that multiple walks are used. The key idea is that the walks may provide each other with information regarding the meaningful (attentive) features of the mesh. We utilize this mutual information to extract a single descriptor of the mesh. This differs from common attention mechanisms that use attention to improve the representation of each individual descriptor. Our approach achieves SOTA results for two basic 3D shape analysis tasks: classification and retrieval. Even a handful of walks along a mesh suffice for learning.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 42 of its 66 references that are in the map. First posted on arXiv 23 Apr 2021.

Builds on

42 of 66 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  8. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  9. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  11. 2018Self-Attention Generative Adversarial Networkscited by 809
  12. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
30 more
  1. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  2. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  3. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  4. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  5. 2020Exploring Self-attention for Image Recognitioncited by 313
  6. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  7. 2015Stacked Attention Networks for Image Question Answeringcited by 273
  8. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  9. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  10. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  11. 2019Local Relation Networks for Image Recognitioncited by 210
  12. 2016Long Short-Term Memory-Networks for Machine Readingcited by 161
  13. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  14. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  15. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  16. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  17. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95
  18. 2019SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operatorcited by 89
  19. 2020MLCVNet: Multi-Level Context VoteNet for 3D Object Detectioncited by 80
  20. 2018Triplet-Center Loss for Multi-View 3D Object Retrievalcited by 69
  21. 2019PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrievalcited by 68
  22. 2020Primal-Dual Mesh Convolutional Neural Networkscited by 44
  23. 2020DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshescited by 42
  24. 2020CNNs on Surfaces using Rotation-Equivariant Featurescited by 42
  25. 2018Multi-directional Geodesic Neural Networks via Equivariant Convolutioncited by 32
  26. 2016GIFT: A Real-time and Scalable 3D Shape Search Enginecited by 31
  27. 2018A Deeper Look at 3D Shape Classifierscited by 25
  28. 2019View N-gram Network for 3D Object Retrievalcited by 18
  29. 2018VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classificationcited by 12
  30. 2020Multiscale Mesh Deformation Component Analysis with Attention-based Autoencoderscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 0; 2024: 1; 2025: 1; 2026: 1.

5 papers.

  1. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  2. 2024RayProNet: A Neural Point Field Framework for Radio Propagation Modeling in 3D Environmentscited by 4
  3. 2022Random Walks for Adversarial Meshescited by 3
  4. 2025Random Walks in Self-supervised Learning for Triangular Meshescited by 0
  5. 2026MME: Mixture of Mesh Experts with Random Walk Transformer Gatingcited by 0