Video Face Recognition: Component-wise Feature Aggregation Network (C-FAN)
arXiv:1902.07327
Abstract
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.
References in corpus (10)
- Deep Learning Face Representation by Joint Identification-Verification
- Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition
- SphereFace: Deep Hypersphere Embedding for Face Recognition
- CosFace: Large Margin Cosine Loss for Deep Face Recognition
- Targeting Ultimate Accuracy: Face Recognition via Deep Embedding
- MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
- Do We Really Need to Collect Millions of Faces for Effective Face Recognition?
- Quality Aware Network for Set to Set Recognition
- Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition
- DeepVisage: Making face recognition simple yet with powerful generalization skills
Cited by in corpus (5)
- Survey on the Analysis and Modeling of Visual Kinship: A Decade in the Making
- Recurrent Embedding Aggregation Network for Video Face Recognition
- Discriminability Distillation in Group Representation Learning
- Efficient aggregation of face embeddings for decentralized face recognition deployments (extended version)
- Self-attention aggregation network for video face representation and recognition