Related papers: DRFormer: A Dual-Regularized Bidirectional Transfo…

Visual Grounding aims to localize the referring object in an image given a natural language expression. Recent advancements in DETR-based visual grounding methods have attracted considerable attention, as they directly predict the…

Hyperspectral image classification (HSIC) has gained significant attention because of its potential in analyzing high-dimensional data with rich spectral and spatial information. In this work, we propose the Differential Spatial-Spectral…

This paper investigates the performance of transformer-based architectures for person identification in natural, face-to-face conversation scenario. We implement and evaluate a two-stream framework that separately models spatial…

Humans can often count unfamiliar objects by observing visual repetition and composition, rather than relying only on object categories. However, many exemplar-free counting models struggle in such situations and may overcount when objects…

Blind face restoration is to recover a high-quality face image from unknown degradations. As face image contains abundant contextual information, we propose a method, RestoreFormer, which explores fully-spatial attentions to model…

Recently, image restoration transformers have achieved comparable performance with previous state-of-the-art CNNs. However, how to efficiently leverage such architectures remains an open problem. In this work, we present Dual-former whose…

Cross-spectral person re-identification, which aims to associate identities to pedestrians across different spectra, faces a main challenge of the modality discrepancy. In this paper, we address the problem from both image-level and…

Human fashion understanding is one crucial computer vision task since it has comprehensive information for real-world applications. This focus on joint human fashion segmentation and attribute recognition. Contrary to the previous works…

Vision Transformer (ViT) models have demonstrated a breakthrough in a wide range of computer vision tasks. However, compared to the Convolutional Neural Network (CNN) models, it has been observed that the ViT models struggle to capture…

Person Re-identification (ReID) is to identify the same person across different cameras. It is a challenging task due to the large variations in person pose, occlusion, background clutter, etc How to extract powerful features is a…

Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies. However, the self-attention mechanism, which is the core part of the Transformer model, usually suffers from…

Since human-labeled samples are free for the target set, unsupervised person re-identification (Re-ID) has attracted much attention in recent years, by additionally exploiting the source set. However, due to the differences on camera…

Vision Transformers with various attention modules have demonstrated superior performance on vision tasks. While using sparsity-adaptive attention, such as in DAT, has yielded strong results in image classification, the key-value pairs…

Extracting effective and discriminative features is very important for addressing the challenging person re-identification (re-ID) task. Prevailing deep convolutional neural networks (CNNs) usually use high-level features for identifying…

Person identification (P-ID) under real unconstrained noisy environments is a huge challenge. In multiple-feature learning with Deep Convolutional Neural Networks (DCNNs) or Machine Learning method for large-scale person identification in…

Three-dimensional object detection is essential for autonomous driving and robotics, relying on effective fusion of multimodal data from cameras and radar. This work proposes RCDINO, a multimodal transformer-based model that enhances visual…

In RGB-D semantic segmentation for indoor scenes, a key challenge is effectively integrating the rich color information from RGB images with the spatial distance information from depth images. However, most existing methods overlook the…

Indoor semantic segmentation is fundamental to computer vision and robotics, supporting applications such as autonomous navigation, augmented reality, and smart environments. Although RGB-D fusion leverages complementary appearance and…

Dynamical systems models such as recurrent neural networks (RNNs) are increasingly popular in theoretical neuroscience for hypothesis-generation and data analysis. Evaluating the dynamics in such models is key to understanding their learned…

Vision Transformers face a fundamental limitation: standard self-attention jointly processes spatial and channel dimensions, leading to entangled representations that prevent independent modeling of structural and semantic dependencies.…