Related papers: Generalizable Re-Identification from Videos with C…
Unsupervised person re-identification (Re-ID) aims to match pedestrian images from different camera views in unsupervised setting. Existing methods for unsupervised person Re-ID are usually built upon the pseudo labels from clustering.…
Unsupervised domain adaptive person re-identification (ReID) has been extensively investigated to mitigate the adverse effects of domain gaps. Those works assume the target domain data can be accessible all at once. However, for the…
Unsupervised video-based person re-identification (re-ID) methods extract richer features from video tracklets than image-based ones. The state-of-the-art methods utilize clustering to obtain pseudo-labels and train the models iteratively.…
A large part of the current success of deep learning lies in the effectiveness of data -- more precisely: labelled data. Yet, labelling a dataset with human annotation continues to carry high costs, especially for videos. While in the image…
Unsupervised domain adaptation person re-identification (Re-ID) aims to identify pedestrian images within an unlabeled target domain with an auxiliary labeled source-domain dataset. Many existing works attempt to recover reliable identity…
We address the challenging task of video-based person re-identification. Recent works have shown that splitting the video sequences into clips and then aggregating clip based similarity is appropriate for the task. We show that using a…
Single-camera-training person re-identification (SCT re-ID) aims to train a re-ID model using SCT datasets where each person appears in only one camera. The main challenge of SCT re-ID is to learn camera-invariant feature representations…
Person re-identification is best known as the problem of associating a single person that is observed from one or more disjoint cameras. The existing literature has mainly addressed such an issue, neglecting the fact that people usually…
With rich temporal-spatial information, video-based person re-identification methods have shown broad prospects. Although tracklets can be easily obtained with ready-made tracking models, annotating identities is still expensive and…
Large-scale language-image pre-trained models (e.g., CLIP) have shown superior performances on many cross-modal retrieval tasks. However, the problem of transferring the knowledge learned from such models to video-based person…
Human intelligence can retrieve any person according to both visual and language descriptions. However, the current computer vision community studies specific person re-identification (ReID) tasks in different scenarios separately, which…
Person Re-Identification (ReID) remains a challenging problem in computer vision. This work reviews various training paradigm and evaluates the robustness of state-of-the-art ReID models in cross-domain applications and examines the role of…
Person re-identification (Re-ID) is one of the primary components of an automated visual surveillance system. It aims to automatically identify/search persons in a multi-camera network having non-overlapping field-of-views. Owing to its…
Person search is a challenging task that involves detecting and retrieving individuals from a large set of un-cropped scene images. Existing person search applications are mostly trained and deployed in the same-origin scenarios. However,…
Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims at learning modality-invariant features from unlabeled cross-modality dataset, which is crucial for practical applications in video surveillance systems. The…
Fully-unsupervised Person and Vehicle Re-Identification have received increasing attention due to their broad applicability in surveillance, forensics, event understanding, and smart cities, without requiring any manual annotation. However,…
Domain generalization studies the problem of training a model with samples from several domains (or distributions) and then testing the model with samples from a new, unseen domain. In this paper, we propose a novel approach for domain…
Current person re-identification (re-id) methods assume that (1) pre-labelled training data are available for every camera pair, (2) the gallery size for re-identification is moderate. Both assumptions scale poorly to real-world…
Existing person re-identification (re-id) methods mostly rely on supervised model learning from a large set of person identity labelled training data per domain. This limits their scalability and usability in large scale deployments. In…
Person re-identification (Re-ID) aims to match identities across non-overlapping camera views. Researchers have proposed many supervised Re-ID models which require quantities of cross-view pairwise labelled data. This limits their…