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

By Mang Ye, Jianbing Shen, Gaojie Lin, Tao A. Xiang, Ling Shao, Steven C. H. Hoi. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020

2,199 citations recorded by the source corpus.

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 twelve datasets for four different 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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a6bba5ce9867c978210e3d056691b5c1e769b760

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Channel Augmented Joint Learning for Visible-Infrared Recognition (2021, methodology): “The training/testing split procedure is repeated ten times [33, 36, 51], Table 1.”
FastReID: A Pytorch Toolbox for General Instance Re-identification (2020, neutral): “%) and 73.1% (79.8) at rank-1/mAP metrics.”
Disentangled Representation Learning for Text-Video Retrieval (2022, methodology): “The dot-product method is widely used in biometrics [7,46], text-image retrieval [47], and text document retrieval [15].”
DATFuse: Infrared and Visible Image Fusion via Dual Attention Transformer (2023, positive): “Due to its powerful feature representation capability, deep learning (DL) has been successfully applied to computer vision tasks such as image super-resolution [48], image restoration [49], and person re-identification [50], [51].”
Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification (2020, methodology): “Following existing VI-ReID works, ResNet50 [12] is adopted as our backbone network for fair comparison, following [59].”
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (2020, background): “Deep learning has achieved great success in a variety of computer vision tasks [20,12,43,35,45,44,25,24,53,52].”
Empowering Things With Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things (2020, methodology): “To address these challenges, different methods have been proposed [110] including deep metric learning based on various losses, integration of local features and context, multi-task learning based on extra attribute annotations, and using human pose and parsing mask as guidance.”