Related papers: Augmented Hard Example Mining for Generalizable Pe…

Learning identity-discriminative representations with multi-scene generality has become a critical objective in person re-identification (ReID). However, mainstream perception-driven paradigms tend to identify fitting from massive annotated…

Recently unsupervised person re-identification (re-ID) has drawn much attention due to its open-world scenario settings where limited annotated data is available. Existing supervised methods often fail to generalize well on unseen domains,…

Person re-identification (Re-ID) has achieved great improvement with deep learning and a large amount of labelled training data. However, it remains a challenging task for adapting a model trained in a source domain of labelled data to a…

Data augmentation is a popular pre-processing trick to improve generalization accuracy. It is believed that by processing augmented inputs in tandem with the original ones, the model learns a more robust set of features which are shared…

Person re-identification (Re-ID) aims at retrieving an input person image from a set of images captured by multiple cameras. Although recent Re-ID methods have made great success, most of them extract features in terms of the attributes of…

Employing clustering strategy to assign unlabeled target images with pseudo labels has become a trend for person re-identification (re-ID) algorithms in domain adaptation. A potential limitation of these clustering-based methods is that…

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,…

We consider a scenario where we have access to the target domain, but cannot afford on-the-fly training data annotation, and instead would like to construct an alternative training set from a large-scale data pool such that a competitive…

Existing person re-identification (re-id) methods mostly exploit a large set of cross-camera identity labelled training data. This requires a tedious data collection and annotation process, leading to poor scalability in practical re-id…

Text de-identification techniques are often used to mask personally identifiable information (PII) from documents. Their ability to conceal the identity of the individuals mentioned in a text is, however, hard to measure. Recent work has…

Unsupervised domain adaptive person Re-IDentification (ReID) is challenging because of the large domain gap between source and target domains, as well as the lackage of labeled data on the target domain. This paper tackles this challenge…

With the assistance of sophisticated training methods applied to single labeled datasets, the performance of fully-supervised person re-identification (Person Re-ID) has been improved significantly in recent years. However, these models…

The performance of a model trained with noisy labels is often improved by simply \textit{retraining} the model with its \textit{own predicted hard labels} (i.e., 1/0 labels). Yet, a detailed theoretical characterization of this phenomenon…

Domain generalization in person re-identification is a highly important meaningful and practical task in which a model trained with data from several source domains is expected to generalize well to unseen target domains. Domain adversarial…

The task of person re-identification has recently received rising attention due to the high performance achieved by new methods based on deep learning. In particular, in the context of video-based re-identification, many state-of-the-art…

Targeted training-set attacks inject malicious instances into the training set to cause a trained model to mislabel one or more specific test instances. This work proposes the task of target identification, which determines whether a…

Given a target image as query, person re-identification systems retrieve a ranked list of candidate matches on a per-camera basis. In deployed systems, a human operator scans these lists and labels sighted targets by touch or mouse-based…

In real applications, person re-identification (ReID) is expected to retrieve the target person at any time, including both daytime and nighttime, ranging from short-term to long-term. However, existing ReID tasks and datasets can not meet…

Unsupervised person re-identification (Re-ID) aims to retrieve person images across cameras without any identity labels. Most clustering-based methods roughly divide image features into clusters and neglect the feature distribution noise…

Modern data augmentation using a mixture-based technique can regularize the models from overfitting to the training data in various computer vision applications, but a proper data augmentation technique tailored for the part-based…