Related papers: DSFormer: A Dual-Scale Cross-Learning Transformer …
Cross-view geo-localization aims to match images of the same target from different platforms, e.g., drone and satellite. It is a challenging task due to the changing appearance of targets and environmental content from different views. Most…
As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency. However, such power comes at a cost: it incurs a huge computation burden and heavy memory footprint as pairwise token…
Due to various and complicated snow degradations, single image desnowing is a challenging image restoration task. As prior arts can not handle it ideally, we propose a novel transformer, SnowFormer, which explores efficient cross-attentions…
We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks. DFormer has two new key innovations: 1) Unlike previous works that encode RGB-D information with RGB pretrained…
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…
Previous methods for dynamic facial expression recognition (DFER) in the wild are mainly based on Convolutional Neural Networks (CNNs), whose local operations ignore the long-range dependencies in videos. Transformer-based methods for DFER…
Multi-contrast MRI (MC-MRI) captures multiple complementary imaging modalities to aid in radiological decision-making. Given the need for lowering the time cost of multiple acquisitions, current deep accelerated MRI reconstruction networks…
One of the central challenges in visual place recognition (VPR) is learning a robust global representation that remains discriminative under large viewpoint changes, illumination variations, and severe domain shifts. While visual foundation…
In unknown cluttered and dynamic environments such as disaster scenes, mobile robots need to perform target-driven navigation in order to find people or objects of interest, while being solely guided by images of the targets. In this paper,…
Recent studies show that vision models pre-trained in generic visual learning tasks with large-scale data can provide useful feature representations for a wide range of visual perception problems. However, few attempts have been made to…
Remote physiological signal measurement based on facial videos, also known as remote photoplethysmography (rPPG), involves predicting changes in facial vascular blood flow from facial videos. While most deep learning-based methods have…
Image clustering, which involves grouping images into different clusters without labels, is a key task in unsupervised learning. Although previous deep clustering methods have achieved remarkable results, they only explore the intrinsic…
With the emergence of VR and AR, 360{\deg} data attracts increasing attention from the computer vision and multimedia communities. Typically, 360{\deg} data is projected into 2D ERP (equirectangular projection) images for feature…
Modern machine learning systems rely on large datasets to attain broad generalization, and this often poses a challenge in robot learning, where each robotic platform and task might have only a small dataset. By training a single policy…
Place recognition is a cornerstone of vehicle navigation and mapping, which is pivotal in enabling systems to determine whether a location has been previously visited. This capability is critical for tasks such as loop closure in…
Transformer-based networks have achieved strong performance in low-level vision tasks like image deraining by utilizing spatial or channel-wise self-attention. However, irregular rain patterns and complex geometric overlaps challenge…
Visual place recognition (VPR) using deep networks has achieved state-of-the-art performance. However, most of them require a training set with ground truth sensor poses to obtain positive and negative samples of each observation's spatial…
Convolutional neural network (CNN) based methods have achieved great successes in medical image segmentation, but their capability to learn global representations is still limited due to using small effective receptive fields of convolution…
Recently, a variety of vision transformers have been developed as their capability of modeling long-range dependency. In current transformer-based backbones for medical image segmentation, convolutional layers were replaced with pure…
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…