# VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification

arXiv: https://arxiv.org/abs/1808.06698 · HTML: https://mlsanity.com/paper/1808.06698/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2018.

## Built on by (most cited first, 12 of 12)

- [A Closer Look at Few-Shot 3D Point Cloud Classification](https://mlsanity.com/paper/2303.18210/) (2023)
- [MVTN: Learning Multi-View Transformations for 3D Understanding](https://mlsanity.com/paper/2212.13462/) (2022)
- [AttWalk: Attentive Cross-Walks for Deep Mesh Analysis](https://mlsanity.com/paper/2104.11571/) (2021)
- [APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification](https://mlsanity.com/paper/2205.00847/) (2022)
- [Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action Recognition](https://mlsanity.com/paper/2209.02986/) (2022)
- [GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation](https://mlsanity.com/paper/2305.15213/) (2023)
- [VSFormer: Mining Correlations in Flexible View Set for Multi-view 3D Shape Understanding](https://mlsanity.com/paper/2409.09254/) (2024)
- [Self-supervised Learning by View Synthesis](https://mlsanity.com/paper/2304.11330/) (2023)
- [ViewFormer: View Set Attention for Multi-view 3D Shape Understanding](https://mlsanity.com/paper/2305.00161/) (2023)
- [Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification](https://mlsanity.com/paper/2505.17666/) (2025)
- [Tactile-ViewGCN: Learning Shape Descriptor from Tactile Data using Graph Convolutional Network](https://mlsanity.com/paper/2203.06183/) (2022)
- [Face recognition on point cloud with cgan-top for denoising](https://mlsanity.com/paper/2506.06864/) (2025)

## Abstract (arXiv)

Multi-view deep neural network is perhaps the most successful approach in 3D shape classification. However, the fusion of multi-view features based on max or average pooling lacks a view selection mechanism, limiting its application in, e.g., multi-view active object recognition by a robot. This paper presents VERAM, a recurrent attention model capable of actively selecting a sequence of views for highly accurate 3D shape classification. VERAM addresses an important issue commonly found in existing attention-based models, i.e., the unbalanced training of the subnetworks corresponding to next view estimation and shape classification. The classification subnetwork is easily overfitted while the view estimation one is usually poorly trained, leading to a suboptimal classification performance. This is surmounted by three essential view-enhancement strategies: 1) enhancing the information flow of gradient backpropagation for the view estimation subnetwork, 2) devising a highly informative reward function for the reinforcement training of view estimation and 3) formulating a novel loss function that explicitly circumvents view duplication. Taking grayscale image as input and AlexNet as CNN architecture, VERAM with 9 views achieves instance-level and class-level accuracy of 95:5% and 95:3% on ModelNet10, 93:7% and 92:1% on ModelNet40, both are the state-of-the-art performance under the same number of views.