# Neural Aggregation Network for Video Face Recognition

arXiv: https://arxiv.org/abs/1603.05474 · HTML: https://mlsanity.com/paper/1603.05474/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2016.

## Built on by (most cited first, 30 of 44)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [DigiFace-1M: 1 Million Digital Face Images for Face Recognition](https://mlsanity.com/paper/2210.02579/) (2022)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Pre-training strategies and datasets for facial representation learning](https://mlsanity.com/paper/2103.16554/) (2021)
- [QMagFace: Simple and Accurate Quality-Aware Face Recognition](https://mlsanity.com/paper/2111.13475/) (2021)
- [Cluster and Aggregate: Face Recognition with Large Probe Set](https://mlsanity.com/paper/2210.10864/) (2022)
- [Towards Universal Backward-Compatible Representation Learning](https://mlsanity.com/paper/2203.01583/) (2022)
- [SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition](https://mlsanity.com/paper/2205.12010/) (2022)
- [50 Years of Automated Face Recognition](https://mlsanity.com/paper/2505.24247/) (2025)
- [LARNet: Lie Algebra Residual Network for Face Recognition](https://mlsanity.com/paper/2103.08147/) (2021)
- [EQFace: A Simple Explicit Quality Network for Face Recognition](https://mlsanity.com/paper/2105.00634/) (2021)
- [Harnessing Unrecognizable Faces for Improving Face Recognition](https://mlsanity.com/paper/2106.04112/) (2021)
- [CoNAN: Conditional Neural Aggregation Network For Unconstrained Face Feature Fusion](https://mlsanity.com/paper/2307.10237/) (2023)
- [Generalizable Face Landmarking Guided by Conditional Face Warping](https://mlsanity.com/paper/2404.12322/) (2024)
- [Recent Advances in Deep Learning Techniques for Face Recognition](https://mlsanity.com/paper/2103.10492/) (2021)
- [Switchable Self-attention Module](https://mlsanity.com/paper/2209.05680/) (2022)
- [HAMIL: Hierarchical Aggregation-Based Multi-Instance Learning for Microscopy Image Classification](https://mlsanity.com/paper/2103.09764/) (2021)
- [Template-based Multi-Domain Face Recognition](https://mlsanity.com/paper/2409.09832/) (2024)
- [Open-set Face Recognition for Small Galleries Using Siamese Networks](https://mlsanity.com/paper/2105.06967/) (2021)
- [Balanced Masked and Standard Face Recognition](https://mlsanity.com/paper/2110.01521/) (2021)
- [Quality-Aware Multimodal Biometric Recognition](https://mlsanity.com/paper/2112.05827/) (2021)
- [Fiducial Focus Augmentation for Facial Landmark Detection](https://mlsanity.com/paper/2402.15044/) (2024)
- [MCA: Moment Channel Attention Networks](https://mlsanity.com/paper/2403.01713/) (2024)
- [Are you In or Out (of gallery)? Wisdom from the Same-Identity Crowd](https://mlsanity.com/paper/2508.06357/) (2025)
- [DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction](https://mlsanity.com/paper/2508.21407/) (2025)
- [A Survey of Face Recognition](https://mlsanity.com/paper/2212.13038/) (2022)
- [Set-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabulary](https://mlsanity.com/paper/2304.06249/) (2023)
- [Automated interpretation of congenital heart disease from multi-view echocardiograms](https://mlsanity.com/paper/2311.18788/) (2023)
- [Effective Adapter for Face Recognition in the Wild](https://mlsanity.com/paper/2312.01734/) (2023)

## Abstract (arXiv)

This paper presents a Neural Aggregation Network (NAN) for video face recognition. The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition. The whole network is composed of two modules. The feature embedding module is a deep Convolutional Neural Network (CNN) which maps each face image to a feature vector. The aggregation module consists of two attention blocks which adaptively aggregate the feature vectors to form a single feature inside the convex hull spanned by them. Due to the attention mechanism, the aggregation is invariant to the image order. Our NAN is trained with a standard classification or verification loss without any extra supervision signal, and we found that it automatically learns to advocate high-quality face images while repelling low-quality ones such as blurred, occluded and improperly exposed faces. The experiments on IJB-A, YouTube Face, Celebrity-1000 video face recognition benchmarks show that it consistently outperforms naive aggregation methods and achieves the state-of-the-art accuracy.