Survey on Deep Learning Techniques for Person Re-Identification Task

Lavi, Bahram; Serj, Mehdi Fatan; Ullah, Ihsan

doi:10.48550/arxiv.1807.05284

Cited by 11 publications

(15 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several surveys on person Re-ID already exist, most of which are concentrated in hand-crafted systems [1], [2], [31], though some surveys have also summarized the deep learning techniques [37], [38]. Our survey makes three major differences: 1) We provide an in-depth and comprehensive analysis of existing deep learning methods by discussing their advantages and limitations, rather than a simple overview.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Person Re-identification: A Survey and Outlook

Ye¹,

Shen²,

Lin³

et al. 2020

Preprint

View full text Add to dashboard Cite

Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. With the advancement of deep neural networks and increasing demand of intelligent video surveillance, it has gained significantly increased interest in the computer vision community. By dissecting the involved components in developing a person Re-ID system, we categorize it into the closed-world and open-world settings. The widely studied closed-world setting is usually applied under various research-oriented assumptions, and has achieved inspiring success using deep learning techniques on a number of datasets. We first conduct a comprehensive overview with in-depth analysis for closed-world person Re-ID from three different perspectives, including deep feature representation learning, deep metric learning and ranking optimization. With the performance saturation under closed-world setting, the research focus for person Re-ID has recently shifted to the open-world setting, facing more challenging issues. This setting is closer to practical applications under specific scenarios. We summarize the open-world Re-ID in terms of five different aspects. By analyzing the advantages of existing methods, we design a powerful AGW baseline, achieving state-of-the-art or at least comparable performance on both single-and cross-modality Re-ID tasks. Meanwhile, we introduce a new evaluation metric (mINP) for person Re-ID, indicating the cost for finding all the correct matches, which provides an additional criteria to evaluate the Re-ID system for real applications. Finally, some important yet under-investigated open issues are discussed.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning for Person Re-identification: A Survey and Outlook

Ye¹,

Shen²,

Lin³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Another possibility is to compare the textual content with the image by extracting the most representative words from the text message [8]. For the image, we can use a system for searching objects and persons in an image [17] which is an active domain, or a bag of visual words technique. Then by comparing the two contents, we can know if, for example, an image represents a person or an object that is not described in the text.…”

Section: Discussionmentioning

confidence: 99%

Including Images into Message Veracity Assessment in Social Media

Azri,

Favre,

Harbi

et al. 2020

Preprint

View full text Add to dashboard Cite

The extensive use of social media in the diffusion of information has also laid a fertile ground for the spread of rumors, which could significantly affect the credibility of social media. An ever-increasing number of users post news including, in addition to text, multimedia data such as images and videos. Yet, such multimedia content is easily editable due to the broad availability of simple and effective image and video processing tools. The problem of assessing the veracity of social network posts has attracted a lot of attention from researchers in recent years. However, almost all previous works have focused on analyzing textual contents to determine veracity, while visual contents, and more particularly images, remains ignored or little exploited in the literature. In this position paper, we propose a framework that explores two novel ways to assess the veracity of messages published on social networks by analyzing the credibility of both their textual and visual contents.

show abstract

“…For feature extraction, a number of methods have been introduced for appearance feature extraction, including deep learning methods such as Siamese Networks [17,15,19], auto-encoders [8,10], correlation filters [41,14], feature pyramids [19], and spatial attention [44]. Motion extraction has also been an integral part of tracking and a number of methods have been developed utilizing Kalman Filters [37], optical flow [34], LSTM [26], among others.…”

Section: Related Work 21 Multi-object Trackingmentioning

confidence: 99%

GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization

Papakis¹,

Sarkar²,

Karpatne³

2020

Preprint

View full text Add to dashboard Cite

This paper proposes a novel method for online Multi-Object Tracking (MOT) using Graph Convolutional Neural Network (GCNN) based feature extraction and end-toend feature matching for object association. The Graph based approach incorporates both appearance and geometry of objects at past frames as well as the current frame into the task of feature learning. This new paradigm enables the network to leverage the "context" information of the geometry of objects and allows us to model the interactions among the features of multiple objects. Another central innovation of our proposed framework is the use of the Sinkhorn algorithm for end-to-end learning of the associations among objects during model training. The network is trained to predict object associations by taking into account constraints specific to the MOT task. Experimental results demonstrate the efficacy of the proposed approach in achieving top performance on the MOT16 & 17 Challenge problems among state-of-the-art online and supervised approaches. The code is available at this https URL.

show abstract

Survey on Deep Learning Techniques for Person Re-Identification Task

Cited by 11 publications

References 52 publications

Deep Learning for Person Re-identification: A Survey and Outlook

Deep Learning for Person Re-identification: A Survey and Outlook

Including Images into Message Veracity Assessment in Social Media

GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization

Contact Info

Product

Resources

About