# View N-gram Network for 3D Object Retrieval

## TL;DR

This paper introduces View N-gram Network (VNN), a novel framework for aggregating multi-view representations of 3D objects that captures spatial information across views, improving retrieval accuracy.

## Contribution

The paper proposes VNN, which uses n-gram inspired view segmentation to better encode spatial relationships in multi-view 3D object retrieval.

## Key findings

- VNN outperforms existing methods on ModelNet10, ModelNet40, and ShapeNetCore55 datasets.
- Captures spatial information across views effectively.
- Achieves higher retrieval accuracy with efficient computation.

## Abstract

How to aggregate multi-view representations of a 3D object into an informative and discriminative one remains a key challenge for multi-view 3D object retrieval. Existing methods either use view-wise pooling strategies which neglect the spatial information across different views or employ recurrent neural networks which may face the efficiency problem. To address these issues, we propose an effective and efficient framework called View N-gram Network (VNN). Inspired by n-gram models in natural language processing, VNN divides the view sequence into a set of visual n-grams, which involve overlapping consecutive view sub-sequences. By doing so, spatial information across multiple views is captured, which helps to learn a discriminative global embedding for each 3D object. Experiments on 3D shape retrieval benchmarks, including ModelNet10, ModelNet40 and ShapeNetCore55 datasets, demonstrate the superiority of our proposed method.