Learning Distributional Representation and Set Distance for Multi-shot Person Re-identification

08/03/2018
by   Ting-yao Hu, et al.
0

Person re-identification aims to identify a specific person at distinct time and locations. It is challenging because of occlusion, illumination, and viewpoint change in camera views. Recently, multi-shot person re-id task receives more attention because it is closer to real world application. A key point of a good algorithm for multi-shot person re-id is how to aggregate appearance features of all images temporally. Most of the current approaches apply pooling strategies and obtain a fixed size representation. We argue that representing a set of images as a feature vector may lose the matching evidences between examples. introducing multi-stage attention mechanism. However, In this work, we propose the idea of distributional representation, which interprets a image set as samples generated from a distribution in appearance feature space, and learn a distributional set distance function to compare two image sets. Specifically, we choose Wasserstein distance in this study. In this way, the proper alignment between two image sets can be discovered naturally in an non-parametric manner. Furthermore, the distance between distributions can serve as a supervision signal to finetune the appearance feature extractor in our model. Experiment results show that our proposed method achieve state-of-the-art performance on MARS dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/20/2019

ID-aware Quality for Set-based Person Re-identification

Set-based person re-identification (SReID) is a matching problem that ai...
research
04/28/2021

Pose-driven Attention-guided Image Generation for Person Re-Identification

Person re-identification (re-ID) concerns the matching of subject images...
research
04/11/2018

MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification

In this paper, a novel mask based deep ranking neural network with skipp...
research
03/07/2016

Learning a Discriminative Null Space for Person Re-identification

Most existing person re-identification (re-id) methods focus on learning...
research
06/13/2014

PRISM: Person Re-Identification via Structured Matching

Person re-identification (re-id), an emerging problem in visual surveill...
research
10/24/2014

A Novel Visual Word Co-occurrence Model for Person Re-identification

Person re-identification aims to maintain the identity of an individual ...
research
04/10/2020

Real-world Person Re-Identification via Degradation Invariance Learning

Person re-identification (Re-ID) in real-world scenarios usually suffers...

Please sign up or login with your details

Forgot password? Click here to reset