Attention-Set based Metric Learning for Video Face Recognition

2017-04-12 · Yibo Hu, Xiang Wu, Ran He

Face recognition has made great progress with the development of deep learning. However, video face recognition (VFR) is still an ongoing task due to various illumination, low-resolution, pose variations and motion blur. Most existing CNN-based VFR methods only obtain a feature vector from a single image and simply aggregate the features in a video, which less consider the correlations of face images in one video. In this paper, we propose a novel Attention-Set based Metric Learning (ASML) method to measure the statistical characteristics of image sets. It is a promising and generalized extension of Maximum Mean Discrepancy with memory attention weighting. First, we define an effective distance metric on image sets, which explicitly minimizes the intra-set distance and maximizes the inter-set distance simultaneously. Second, inspired by Neural Turing Machine, a Memory Attention Weighting is proposed to adapt set-aware global contents. Then ASML is naturally integrated into CNNs, resulting in an end-to-end learning scheme. Our method achieves state-of-the-art performance for the task of video face recognition on the three widely used benchmarks including YouTubeFace, YouTube Celebrities and Celebrity-1000.

📄 PDF Abstract BibTeX arXiv:1704.03805

Code (0)

등록된 구현이 없습니다.

Tasks

Face Recognition Metric Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Sigmoid Activation 설명 없음

Tanh Activation 설명 없음

Location-based Attention 설명 없음

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Content-based Attention Content-based attention is an attention mechanism based on cosine similarity: $$f_{att}\left(\textbf{h}_{i}, \textbf{s}\_{j}\right) =…

Neural Turing Machine A Neural Turing Machine is a working memory neural network model. It couples a neural network architecture with external memory resources. The whole architecture is…

Attention-Aware Deep Reinforcement Learning for Video Face Recognition

2017-10-01 · ICCV 2017 10 · Yongming Rao, Jiwen Lu, Jie zhou

In this paper, we propose an attention-aware deep reinforcement learning (ADRL) method for video face recognition, which aims to discard the misleading and confounding frames and find the focuses of attention in face vid…

Deep Reinforcement Learning Face Recognition Person Recognition reinforcement-learning+2

Attention-Aware Transformer-Based Aggregation Network for Video Periocular Recognition

2026-05-15 · Luiz G F Carreira, Breno A Mariano, Victor H C de Melo, David Menotti 외 arxiv

Video periocular recognition is the task of recognizing an individual's identity based on the region around an individual's eyes. The periocular area is one of the most discriminative regions of the human face, making it…

Self-attention aggregation network for video face representation and recognition

2020-10-11 · Ihor Protsenko, Taras Lehinevych, Dmytro Voitekh, Ihor Kroosh 외

Models based on self-attention mechanisms have been successful in analyzing temporal data and have been widely used in the natural language domain. We propose a new model architecture for video face representation and re…

Face Recognition

Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video

2016-08-15 · Zhiwu Huang, Ruiping Wang, Shiguang Shan, Luc van Gool 외

Riemannian manifolds have been widely employed for video representations in visual classification tasks including video-based face recognition. The success mainly derives from learning a discriminant Riemannian metric wh…