# Pairwise Decomposition of Image Sequences for Active Multi-View Recognition

arXiv: https://arxiv.org/abs/1605.08359 · HTML: https://mlsanity.com/paper/1605.08359/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2016.

## Built on by (most cited first, 15 of 15)

- [MVT: Multi-view Vision Transformer for 3D Object Recognition](https://mlsanity.com/paper/2110.13083/) (2021)
- [Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection](https://mlsanity.com/paper/2105.10160/) (2021)
- [Interactron: Embodied Adaptive Object Detection](https://mlsanity.com/paper/2202.00660/) (2022)
- [Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views](https://mlsanity.com/paper/2108.03743/) (2021)
- [Active Open-Vocabulary Recognition: Let Intelligent Moving Mitigate CLIP Limitations](https://mlsanity.com/paper/2311.17938/) (2023)
- [Next-best-view Regression using a 3D Convolutional Neural Network](https://mlsanity.com/paper/2101.09397/) (2021)
- [Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation](https://mlsanity.com/paper/2111.07248/) (2021)
- [Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action Recognition](https://mlsanity.com/paper/2209.02986/) (2022)
- [R2-MLP: Round-Roll MLP for Multi-View 3D Object Recognition](https://mlsanity.com/paper/2211.11085/) (2022)
- [VSFormer: Mining Correlations in Flexible View Set for Multi-view 3D Shape Understanding](https://mlsanity.com/paper/2409.09254/) (2024)
- [Robust Pooling through the Data Mode](https://mlsanity.com/paper/2106.10850/) (2021)
- [PREMA: Part-based REcurrent Multi-view Aggregation Network for 3D Shape Retrieval](https://mlsanity.com/paper/2111.04945/) (2021)
- [Multi-View Active Fine-Grained Recognition](https://mlsanity.com/paper/2206.01153/) (2022)
- [ViewFormer: View Set Attention for Multi-view 3D Shape Understanding](https://mlsanity.com/paper/2305.00161/) (2023)
- [A Dynamic Data Driven Approach for Explainable Scene Understanding](https://mlsanity.com/paper/2206.09089/) (2022)

## Abstract (arXiv)

A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, which do not readily embrace recent trends in deep learning. We propose to bring Convolutional Neural Networks to generic multi-view recognition, by decomposing an image sequence into a set of image pairs, classifying each pair independently, and then learning an object classifier by weighting the contribution of each pair. This allows for recognition over arbitrary camera trajectories, without requiring explicit training over the potentially infinite number of camera paths and lengths. Building these pairwise relationships then naturally extends to the next-best-view problem in an active recognition framework. To achieve this, we train a second Convolutional Neural Network to map directly from an observed image to next viewpoint. Finally, we incorporate this into a trajectory optimisation task, whereby the best recognition confidence is sought for a given trajectory length. We present state-of-the-art results in both guided and unguided multi-view recognition on the ModelNet dataset, and show how our method can be used with depth images, greyscale images, or both.