# Video Face Recognition: Component-wise Feature Aggregation Network (C-FAN)

arXiv: https://arxiv.org/abs/1902.07327 · HTML: https://mlsanity.com/paper/1902.07327/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2019.

## Built on by (most cited first, 13 of 13)

- [Controllable and Guided Face Synthesis for Unconstrained Face Recognition](https://mlsanity.com/paper/2207.10180/) (2022)
- [Cluster and Aggregate: Face Recognition with Large Probe Set](https://mlsanity.com/paper/2210.10864/) (2022)
- [The State of Aerial Surveillance: A Survey](https://mlsanity.com/paper/2201.03080/) (2022)
- [50 Years of Automated Face Recognition](https://mlsanity.com/paper/2505.24247/) (2025)
- [Harnessing Unrecognizable Faces for Improving Face Recognition](https://mlsanity.com/paper/2106.04112/) (2021)
- [Recent Advances in Deep Learning Techniques for Face Recognition](https://mlsanity.com/paper/2103.10492/) (2021)
- [Person Recognition in Aerial Surveillance: A Decade Survey](https://mlsanity.com/paper/2511.17674/) (2025)
- [Set-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabulary](https://mlsanity.com/paper/2304.06249/) (2023)
- [FaceCoresetNet: Differentiable Coresets for Face Set Recognition](https://mlsanity.com/paper/2308.14075/) (2023)
- [VideoClusterNet: Self-Supervised and Adaptive Face Clustering For Videos](https://mlsanity.com/paper/2407.12214/) (2024)
- [Efficient aggregation of face embeddings for decentralized face recognition deployments (extended version)](https://mlsanity.com/paper/2212.10108/) (2022)
- [On the Burstiness of Faces in Set](https://mlsanity.com/paper/2506.20312/) (2025)
- [Video-Based Palm-Vein Authentication under Challenging Conditions](https://mlsanity.com/paper/2609.02776/) (2026)

## Abstract (arXiv)

We propose a new approach to video face recognition. Our component-wise feature aggregation network (C-FAN) accepts a set of face images of a subject as an input, and outputs a single feature vector as the face representation of the set for the recognition task. The whole network is trained in two steps: (i) train a base CNN for still image face recognition; (ii) add an aggregation module to the base network to learn the quality value for each feature component, which adaptively aggregates deep feature vectors into a single vector to represent the face in a video. C-FAN automatically learns to retain salient face features with high quality scores while suppressing features with low quality scores. The experimental results on three benchmark datasets, YouTube Faces, IJB-A, and IJB-S show that the proposed C-FAN network is capable of generating a compact feature vector with 512 dimensions for a video sequence by efficiently aggregating feature vectors of all the video frames to achieve state of the art performance.