Few-Shot Deep Adversarial Learning for Video-based Person Re-identification

Abstract

Video-based person re-identification (re-ID) refers to matching people across camera views from arbitrary unaligned video footages. Existing methods rely on supervision signals to optimise a projected space under which the distances between inter/intra-videos are maximised/minimised. However, this demands exhaustively labelling people across camera views, rendering them unable to be scaled in large networked cameras. Also, it is noticed that learning effective video representations with view invariance is not explicitly addressed for which features exhibit different distributions otherwise. Thus, matching videos for person re-ID demands flexible models to capture the dynamics in time-series observations and learn view-invariant representations with access to limited labeled training samples. In this paper, we propose a novel few-shot deep learning approach to video-based person re-ID, to learn comparable representations that are discriminative and view-invariant. The proposed method is developed on the variational recurrent neural networks (VRNNs) and trained adversarially to produce latent variables with temporal dependencies that are highly discriminative yet view-invariant in matching persons. Through extensive experiments conducted on three benchmark datasets, we empirically show the capability of our method in creating view-invariant temporal features and state-of-the-art performance achieved by our method.

arXiv commentAppearing at IEEE Transactions on Image Processing

References in corpus (20)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Auto-Encoding Variational Bayes
• FaceNet: A Unified Embedding for Face Recognition and Clustering
• Two-Stream Convolutional Networks for Action Recognition in Videos
• Unsupervised Learning of Video Representations using LSTMs
• Matching Networks for One Shot Learning
• Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition
• A Recurrent Latent Variable Model for Sequential Data
• Video (language) modeling: a baseline for generative models of natural videos
• Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks
• Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
• Deep Ranking for Person Re-identification via Joint Representation Learning
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
• Unsupervised Person Re-identification: Clustering and Fine-tuning
• 3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification
• Human Re-identification by Matching Compositional Template with Cluster Sampling
• Top Rank Optimization in Linear Time
• Recurrent Gaussian Processes
• Learning Invariant Color Features for Person Re-Identification

Cited by in corpus (12)

• Efficient Few-Shot Object Detection via Knowledge Inheritance
• A BERT based Sentiment Analysis and Key Entity Detection Approach for Online Financial Texts
• Exploring Image Enhancement for Salient Object Detection in Low Light Images
• Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification
• Eliminating cross-camera bias for vehicle re-identification
• Discriminative Feature and Dictionary Learning with Part-aware Model for Vehicle Re-identification
• One-Shot Open-Set Skeleton-Based Action Recognition
• Person Re-Identification using Deep Learning Networks: A Systematic Review
• PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification
• Weak Texture Information Map Guided Image Super-resolution with Deep Residual Networks
• Deep Visual Waterline Detection within Inland Marine Environment
• Co-regularized Multi-view Sparse Reconstruction Embedding for Dimension Reduction