Related papers: Domain Adaptation through Synthesis for Unsupervis…
While recent person re-identification (ReID) methods achieve high accuracy in a supervised setting, their generalization to an unlabelled domain is still an open problem. In this paper, we introduce a novel unsupervised disentanglement…
Person re-identification (re-id) is a cross-camera retrieval task which establishes a correspondence between images of a person from multiple cameras. Deep Learning methods have been successfully applied to this problem and have achieved…
Given a portrait image of a person and an environment map of the target lighting, portrait relighting aims to re-illuminate the person in the image as if the person appeared in an environment with the target lighting. To achieve…
Low light conditions not only degrade human visual experience, but also reduce the performance of downstream machine analytics. Although many works have been designed for low-light enhancement or domain adaptive machine analytics, the…
Outdoor scene relighting is a challenging problem that requires good understanding of the scene geometry, illumination and albedo. Current techniques are completely supervised, requiring high quality synthetic renderings to train a…
The extremes of lighting (e.g. too much or too little light) usually cause many troubles for machine and human vision. Many recent works have mainly focused on under-exposure cases where images are often captured in low-light conditions…
Most video person re-identification (re-ID) methods are mainly based on supervised learning, which requires cross-camera ID labeling. Since the cost of labeling increases dramatically as the number of cameras increases, it is difficult to…
Deep learning in computer vision has achieved great success with the price of large-scale labeled training data. However, exhaustive data annotation is impracticable for each task of all domains of interest, due to high labor costs and…
Person re-identification (re-ID) aims at recognizing the same person from images taken across different cameras. To address this challenging task, existing re-ID models typically rely on a large amount of labeled training data, which is not…
Domain adaptation (DA) addresses the real-world image classification problem of discrepancy between training (source) and testing (target) data distributions. We propose an unsupervised DA method that considers the presence of only…
Unsupervised learning of identity-discriminative visual feature is appealing in real-world tasks where manual labelling is costly. However, the images of an identity can be visually discrepant when images are taken under different states,…
Unsupervised cross-domain person re-identification (Re-ID) aims to adapt the information from the labelled source domain to an unlabelled target domain. Due to the lack of supervision in the target domain, it is crucial to identify the…
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…
Existing person re-identification (re-ID) research mainly focuses on pedestrian identity matching across cameras in adjacent areas. However, in reality, it is inevitable to face the problem of pedestrian identity matching across…
In the absence of labeled target data, unsupervised domain adaptation approaches seek to align the marginal distributions of the source and target domains in order to train a classifier for the target. Unsupervised domain alignment…
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…
Most existing person re-identification (re-id) methods rely on supervised model learning on per-camera-pair manually labelled pairwise training data. This leads to poor scalability in a practical re-id deployment, due to the lack of…
Supervised person re-identification methods rely heavily on high-quality cross-camera training label. This significantly hinders the deployment of re-ID models in real-world applications. The unsupervised person re-ID methods can reduce the…
Domain adaptation in person re-identification (re-ID) has always been a challenging task. In this work, we explore how to harness the natural similar characteristics existing in the samples from the target domain for learning to conduct…
In video surveillance, person re-identification is the task of searching person images in non-overlapping cameras. Though supervised methods for person re-identification have attained impressive performance, obtaining large scale cross-view…