Related papers: Interpretable and Generalizable Person Re-Identifi…
Due to some complex factors (e.g., occlusion, pose variation and diverse camera perspectives), extracting stronger feature representation in person re-identification remains a challenging task. In this paper, we proposed a novel…
Large vision models based in deep learning architectures have been consistently advancing the state-of-the-art in biometric recognition. However, three weaknesses are commonly reported for such kind of approaches: 1) their extreme demands…
Existing lifting networks for regressing 3D human poses from 2D single-view poses are typically constructed with linear layers based on graph-structured representation learning. In sharp contrast to them, this paper presents Grid…
Existing unsupervised person re-identification (ReID) methods focus on adapting a model trained on a source domain to a fixed target domain. However, an adapted ReID model usually only works well on a certain target domain, but can hardly…
Video-based person re-identification aims to match pedestrians from video sequences across non-overlapping camera views. The key factor for video person re-identification is to effectively exploit both spatial and temporal clues from video…
There are two types of information in each handwritten word image: explicit information which can be easily read or derived directly, such as lexical content or word length, and implicit attributes such as the author's identity. Whether…
In this paper, we present a novel person reidentification (PRe-ID) system that based on tensor feature representation and multilinear subspace learning. Our approach utilizes pretrained CNNs for high-level feature extraction, along with…
Person re-identification (re-ID) aims at matching images of the same person across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected, which would degrade re-ID performance in…
As convolution has empowered many smart applications, dynamic convolution further equips it with the ability to adapt to diverse inputs. However, the static and dynamic convolutions are either layout-agnostic or computation-heavy, making it…
Deep learning has achieved remarkable success in processing and managing unstructured data. However, its "black box" nature imposes significant limitations, particularly in sensitive application domains. While existing interpretable machine…
Vision-language foundation models such as CLIP have achieved tremendous results in global vision-language alignment, but still show some limitations in creating representations for specific image regions. % To address this problem, we…
The ability to estimate the perceptual error between images is an important problem in computer vision with many applications. Although it has been studied extensively, however, no method currently exists that can robustly predict visual…
While attributes have been widely used for person re-identification (Re-ID) which aims at matching the same person images across disjoint camera views, they are used either as extra features or for performing multi-task learning to assist…
Image memorability refers to the phenomenon where certain images are more likely to be remembered than others. It is a quantifiable and intrinsic image attribute, defined as the likelihood of an image being remembered upon a single…
Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network relies on learning high-level concepts, are valued because of closeness of…
Person re-identification aims to match a person's identity across multiple camera streams. Deep neural networks have been successfully applied to the challenging person re-identification task. One remarkable bottleneck is that the existing…
Person re-identification is being widely used in the forensic, and security and surveillance system, but person re-identification is a challenging task in real life scenario. Hence, in this work, a new feature descriptor model has been…
The performance of person re-identification (Re-ID) has been seriously effected by the large cross-view appearance variations caused by mutual occlusions and background clutters. Hence learning a feature representation that can adaptively…
Deep image prior (DIP) is a recently proposed technique for solving imaging inverse problems by fitting the reconstructed images to the output of an untrained convolutional neural network. Unlike pretrained feedforward neural networks, the…
Face recognition performance evaluation has traditionally focused on one-to-one verification, popularized by the Labeled Faces in the Wild dataset for imagery and the YouTubeFaces dataset for videos. In contrast, the newly released IJB-A…