# MANet: Multimodal Attention Network based Point- View fusion for 3D Shape Recognition

arXiv: https://arxiv.org/abs/2002.12573 · HTML: https://mlsanity.com/paper/2002.12573/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2020.

## Built on by (most cited first, 2 of 2)

- [Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning](https://mlsanity.com/paper/2107.08369/) (2021)
- [Attention Models for Point Clouds in Deep Learning: A Survey](https://mlsanity.com/paper/2102.10788/) (2021)

## Abstract (arXiv)

3D shape recognition has attracted more and more attention as a task of 3D vision research. The proliferation of 3D data encourages various deep learning methods based on 3D data. Now there have been many deep learning models based on point-cloud data or multi-view data alone. However, in the era of big data, integrating data of two different modals to obtain a unified 3D shape descriptor is bound to improve the recognition accuracy. Therefore, this paper proposes a fusion network based on multimodal attention mechanism for 3D shape recognition. Considering the limitations of multi-view data, we introduce a soft attention scheme, which can use the global point-cloud features to filter the multi-view features, and then realize the effective fusion of the two features. More specifically, we obtain the enhanced multi-view features by mining the contribution of each multi-view image to the overall shape recognition, and then fuse the point-cloud features and the enhanced multi-view features to obtain a more discriminative 3D shape descriptor. We have performed relevant experiments on the ModelNet40 dataset, and experimental results verify the effectiveness of our method.