Query-Guided End-To-End Person Search (2019-05-03T00:00:00.000000Z)

TL;DR

A novel query-guided end-to-end person search network (QEEPS) to address both person detection and re-identification and outperform the previous state-of-the-art datasets by a large margin.

Abstract

Person search has recently gained attention as the novel task of finding a person, provided as a cropped sample, from a gallery of non-cropped images, whereby several other people are also visible. We believe that i. person detection and re-identification should be pursued in a joint optimization framework and that ii. the person search should leverage the query image extensively (e.g. emphasizing unique query patterns). However, so far, no prior art realizes this. We introduce a novel query-guided end-to-end person search network (QEEPS) to address both aspects. We leverage a most recent joint detector and re-identification work, OIM [37]. We extend this with i. a query-guided Siamese squeeze-and-excitation network (QSSE-Net) that uses global context from both the query and gallery images, ii. a query-guided region proposal network (QRPN) to produce query-relevant proposals, and iii. a query-guided similarity subnetwork (QSimNet), to learn a query-guided re-identification score. QEEPS is the first end-to-end query-guided detection and re-id network. On both the most recent CUHK-SYSU [37] and PRW [46] datasets, we outperform the previous state-of-the-art by a large margin.

Authors

Federico Tombari

15 papers

S. Amin

3 papers

Fabio Galasso

3 papers

TL;DR

Abstract

Authors

References46 items

Maximum Margin Metric Learning Over Discriminative Nullspace for Person Re-identification

Person Re-identification with Deep Similarity-Guided Graph Neural Network

Person Search via A Mask-Guided Two-Stream CNN Model

Attention-Aware Compositional Network for Person Re-identification

Squeeze-and-Excitation Networks

Tiny head pose classification by bodily cues

Focal Loss for Dense Object Detection

Geometric proposals for faster R-CNN

Neural Person Search Machines

IAN: The Individual Aggregation Network for Person Search

Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification

Mask R-CNN

YOLO9000: Better, Faster, Stronger

MARS: A Video Benchmark for Large-Scale Person Re-Identification

A Discriminative Feature Learning Approach for Deep Face Recognition

A Siamese Long Short-Term Memory Architecture for Human Re-identification

Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function

End-to-End Comparative Attention Networks for Person Re-Identification

Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification

Person Re-identification in the Wild

Joint Detection and Identification Feature Learning for Person Search

Scalable Semi-Automatic Annotation for Multi-Camera Person Tracking

Large Scale Similarity Learning Using Similar Pairs for Person Verification

Deep Residual Learning for Image Recognition

SSD: Single Shot MultiBox Detector

Efficient PSD Constrained Asymmetric Metric Learning for Person Re-Identification

Multi-Scale Learning for Low-Resolution Person Re-Identification

Deep feature learning with relative distance comparison for person re-identification

An improved deep learning architecture for person re-identification

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Learning to rank in person re-identification with metric ensembles

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Beyond frontal faces: Improving Person Recognition using multiple cues

Person Re-Identification by Saliency Learning

Person Search in a Scene by Jointly Modeling People Commonness and Person Uniqueness

Deep Metric Learning for Person Re-identification

Fast Feature Pyramids for Object Detection

DeepReID: Deep Filter Pairing Neural Network for Person Re-identification

Person re-identification by Local Maximal Occurrence representation and metric learning

Unsupervised Salience Learning for Person Re-identification

Large scale metric learning from equivalence constraints

Object Detection with Discriminatively Trained Part Based Models

Person re-identification by symmetry-driven accumulation of local features

Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features

Shape and Appearance Context Modeling

Learning to rank in person re-identiﬁcation with metric ensembles

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names