Attention-Set Based Metric Learning for Video Face Recognition

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. In this paper, we propose a novel Attention-Set based Metric Learning (ASML) method for VFR. It is a promising and generalized extension of Maximum Mean Discrepancy with Memory Attention Weighting inspired by Neural Turing Machine. ASML can be naturally integrated into Convolutional Neural Networks, resulting in an end-to-end learning scheme. Our method achieves state-of-the-art performance for the task of video face recognition on three widely used benchmarks including YouTubeFace, YouTube Celebrities and Celebrity-1000.

• Publication year

  2017

• Venue

  Asian Conference on Pattern Recognition

• Publication date

  2017-04-12

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1109/ACPR.2017.43arXiv 1704.03805
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Collaborative Random Faces-Guided Encoders for Pose-Invariant Face Representation Learning

  2018cited by this paper
• Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition

  2016cited by this paper
• Neural Aggregation Network for Video Face Recognition

  2016influential reference
• A Discriminative Feature Learning Approach for Deep Face Recognition

  2016cited by this paper
• Recurrent Regression for Face Recognition

  2016cited by this paper
• Simultaneous Feature and Sample Reduction for Image-Set Classification

  2016cited by this paper
• Distance Metric Learning for Aspect Phrase Grouping

  2016cited by this paper
• FaceNet: A unified embedding for face recognition and clustering

  2015influential reference
• Projection Metric Learning on Grassmann Manifold with Application to Video based Face Recognition

  2015cited by this paper
• Sparsifying Neural Network Connections for Face Recognition

  2015influential reference
• Deep Face Recognition

  2015influential reference
• Discriminant analysis on Riemannian manifold of Gaussian distributions for face recognition with image sets

  2015cited by this paper
• A Light CNN for Deep Face Representation With Noisy Labels

  2015cited by this paper
• Image set representation and classification with covariate-relation graph

  2015cited by this paper
• Face recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning

  2015cited by this paper
• Representation learning with deep extreme learning machines for efficient image set classification

  2015cited by this paper
• End-To-End Memory Networks

  2015cited by this paper
• Multi-manifold deep metric learning for image set classification

  2015cited by this paper
• Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set Classification

  2015cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• Towards End-To-End Speech Recognition with Recurrent Neural Networks

  2014cited by this paper
• Simultaneous Feature and Dictionary Learning for Image Set Based Face Recognition

  2014cited by this paper
• Caffe: Convolutional Architecture for Fast Feature Embedding

  2014cited by this paper
• DeepFace: Closing the Gap to Human-Level Performance in Face Verification

  2014influential reference
• Learning Non-linear Reconstruction Models for Image Set Classification

  2014cited by this paper
• Deeply learned face representations are sparse, selective, and robust

  2014influential reference
• Neural Turing Machines

  2014influential reference
• Eigen-PEP for Video Face Recognition

  2014cited by this paper
• Toward Large-Population Face Identification in Unconstrained Videos

  2014cited by this paper
• Going deeper with convolutions

  2014influential reference
• Face Recognition in Movie Trailers via Mean Sequence Sparse Representation-Based Classification

  2013cited by this paper
• Deep Convolutional Network Cascade for Facial Point Detection

  2013cited by this paper
• Image Set Classification Using Holistic Multiple Order Statistics Features and Localized Multi-kernel Metric Learning

  2013cited by this paper
• Dictionary-Based Face Recognition from Video

  2012cited by this paper
• Visual Classification With Multitask Joint Sparse Representation

  2012cited by this paper
• Graph embedding discriminant analysis on Grassmannian manifolds for improved image set matching

  2011cited by this paper
• Face recognition in unconstrained videos with matched background similarity

  2011cited by this paper
• Face tracking and recognition with visual constraints in real-world videos

  2008influential reference
• Sample Selection Bias Correction Theory

  2008cited by this paper
• Grassmann discriminant analysis: a unifying view on subspace-based learning

  2008cited by this paper
• A Kernel Method for the Two-Sample-Problem

  2006influential reference

• A Quadruplet Loss for Enforcing Semantically Coherent Embeddings in Multi-Output Classification Problems

  2020cites this paper
• An Automated Framework for Patient Identification and Verification Using Deep Learning

  2020cites this paper
• Duplex Metric Learning for Image Set Classification

  2018cites this paper