What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification

07/21/2017
by   Lin Wu, et al.
0

Matching pedestrians across disjoint camera views, known as person re-identification (re-id), is a challenging problem that is of importance to visual recognition and surveillance. Most existing methods exploit local regions within spatial manipulation to perform matching in local correspondence. However, they essentially extract fixed representations from pre-divided regions for each image and perform matching based on the extracted representation subsequently. For models in this pipeline, local finer patterns that are crucial to distinguish positive pairs from negative ones cannot be captured, and thus making them underperformed. In this paper, we propose a novel deep multiplicative integration gating function, which answers the question of what-and-where to match for effective person re-id. To address what to match, our deep network emphasizes common local patterns by learning joint representations in a multiplicative way. The network comprises two Convolutional Neural Networks (CNNs) to extract convolutional activations, and generates relevant descriptors for pedestrian matching. This thus, leads to flexible representations for pair-wise images. To address where to match, we combat the spatial misalignment by performing spatially recurrent pooling via a four-directional recurrent neural network to impose spatial dependency over all positions with respect to the entire image. The proposed network is designed to be end-to-end trainable to characterize local pairwise feature interactions in a spatially aligned manner. To demonstrate the superiority of our method, extensive experiments are conducted over three benchmark data sets: VIPeR, CUHK03 and Market-1501.

READ FULL TEXT

page 4

page 6

page 12

research
08/03/2018

Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification

Video-based person re-identification (re-id) is a central application in...
research
07/28/2016

Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification

Matching pedestrians across multiple camera views, known as human re-ide...
research
04/30/2018

Deep Co-attention based Comparators For Relative Representation Learning in Person Re-identification

Person re-identification (re-ID) requires rapid, flexible yet discrimina...
research
01/04/2018

Crossing Generative Adversarial Networks for Cross-View Person Re-identification

Person re-identification (re-id) refers to matching pedestrians across d...
research
10/25/2019

An End-to-End Foreground-Aware Network for Person Re-Identification

Person re-identification is a crucial task of identifying pedestrians of...
research
01/29/2019

Discovering Underlying Person Structure Pattern with Relative Local Distance for Person Re-identification

Modeling the underlying person structure for person re-identification (r...
research
09/11/2020

Devil's in the Detail: Graph-based Key-point Alignment and Embedding for Person Re-ID

Although Person Re-Identification has made impressive progress, difficul...

Please sign up or login with your details

Forgot password? Click here to reset