# Feature Aggregation Network for Video Face Recognition

## TL;DR

This paper introduces a meta attention-based feature aggregation network for video face recognition that adaptively weighs frame features to produce a compact, discriminative representation, improving recognition performance across varying video qualities.

## Contribution

It proposes a novel meta attention-based aggregation scheme and a network architecture that handles arbitrary frame numbers and order, enhancing video face recognition accuracy.

## Key findings

- Achieves competitive results on YouTube face and IJB-A datasets.
- Effectively exploits valuable features from all frames, including low-quality ones.
- Demonstrates robustness to frame order and number in video face recognition.

## Abstract

This paper aims to learn a compact representation of a video for video face recognition task. We make the following contributions: first, we propose a meta attention-based aggregation scheme which adaptively and fine-grained weighs the feature along each feature dimension among all frames to form a compact and discriminative representation. It makes the best to exploit the valuable or discriminative part of each frame to promote the performance of face recognition, without discarding or despising low quality frames as usual methods do. Second, we build a feature aggregation network comprised of a feature embedding module and a feature aggregation module. The embedding module is a convolutional neural network used to extract a feature vector from a face image, while the aggregation module consists of cascaded two meta attention blocks which adaptively aggregate the feature vectors into a single fixed-length representation. The network can deal with arbitrary number of frames, and is insensitive to frame order. Third, we validate the performance of proposed aggregation scheme. Experiments on publicly available datasets, such as YouTube face dataset and IJB-A dataset, show the effectiveness of our method, and it achieves competitive performances on both the verification and identification protocols.