Related papers: Discriminative multi-view Privileged Information l…
Multi-modal search engines have experienced significant growth and widespread use in recent years, making them the second most common internet use. While search engine systems offer a range of services, the image search field has recently…
Vehicle Re-identification aims to identify a specific vehicle across time and camera view. With the rapid growth of intelligent transportation systems and smart cities, vehicle Re-identification technology gets more and more attention.…
The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has…
Region of Interest (ROI)-based image compression optimizes bit allocation by prioritizing ROI for higher-quality reconstruction. However, as the users (including human clients and downstream machine tasks) become more diverse, ROI-based…
Research on continual learning in multi-modal tasks has been receiving increasing attention. However, most existing work overlooks the explicit cross-modal and cross-task interactions. In this paper, we innovatively propose the Low-rank…
Multi-view representation learning is essential for many multi-view tasks, such as clustering and classification. However, there are two challenging problems plaguing the community: i)how to learn robust multi-view representation from mass…
While metric learning is important for Person re-identification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires…
Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning…
We address the challenging problem of RGB image-based head pose estimation. We first reformulate head pose representation learning to constrain it to a bounded space. Head pose represented as vector projection or vector angles shows helpful…
Adversarial attacks have proved to be the major impediment in the progress on research towards reliable machine learning solutions. Carefully crafted perturbations, imperceptible to human vision, can be added to images to force…
We propose a weakly-supervised multi-view learning approach to learn category-specific surface mapping without dense annotations. We learn the underlying surface geometry of common categories, such as human faces, cars, and airplanes, given…
The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly.…
It is suggested that low-light image enhancement realizes one-to-many mapping since we have different definitions of NORMAL-light given application scenarios or users' aesthetic. However, most existing methods ignore subjectivity of the…
Image reconstruction from undersampled k-space data plays an important role in accelerating the acquisition of MR data, and a lot of deep learning-based methods have been exploited recently. Despite the achieved inspiring results, the…
Today, most methods for image understanding tasks rely on feed-forward neural networks. While this approach has allowed for empirical accuracy, efficiency, and task adaptation via fine-tuning, it also comes with fundamental disadvantages.…
Learning the ability to generalize knowledge between similar contexts is particularly important in medical imaging as data distributions can shift substantially from one hospital to another, or even from one machine to another. To…
Re-ranking is a process of rearranging ranking list to more effectively meet user demands by accounting for the interrelationships between items. Existing methods predominantly enhance the precision of search results, often at the expense…
We present an unsupervised approach for factorizing object appearance into highlight, shading, and albedo layers, trained by multi-view real images. To do so, we construct a multi-view dataset by collecting numerous customer product photos…
Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations. Yet such models are not…
Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional…