Related papers: Efficient Multi-Purpose Cross-Attention Based Imag…

Crowd counting research has made significant advancements in real-world applications, but it remains a formidable challenge in cross-modal settings. Most existing methods rely solely on the optical features of RGB images, ignoring the…

Abnormality detection in medical imaging is a critical task requiring both high efficiency and accuracy to support effective diagnosis. While convolutional neural networks (CNNs) and Transformer-based models are widely used, both face…

Mamba has recently gained widespread attention as a backbone model for point cloud modeling, leveraging a state-space architecture that enables efficient global sequence modeling with linear complexity. However, its lack of local inductive…

A core component of all Structure from Motion (SfM) approaches is bundle adjustment. As the latter is a computational bottleneck for larger blocks, parallel bundle adjustment has become an active area of research. Particularly,…

The rapid advances in deep learning have significantly enhanced the accuracy of multimodal 3D human pose estimation (HPE). However, the state-of-the-art (SOTA) HPE pipelines still rely on Transformers, whose quadratic complexity makes…

With the growing adoption of deep learning for on-device TinyML applications, there has been an ever-increasing demand for efficient neural network backbones optimized for the edge. Recently, the introduction of attention condenser networks…

Breast ultrasound imaging is a valuable tool for early breast cancer detection, but automated tumor segmentation is challenging due to inherent noise, variations in scale of lesions, and fuzzy boundaries. To address these challenges, we…

In this work, we propose a novel Mamba block DenVisCoM, as well as a novel hybrid architecture specifically tailored for accurate and real-time estimation of optical flow and disparity estimation. Given that such multi-view geometry and…

Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent UDA methods based on Vision Transformers (ViTs) have achieved strong performance through attention-based…

Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechanisms presents scalability challenges. To address these…

Pan-sharpening aims to generate high-resolution multispectral (HRMS) images by integrating a high-resolution panchromatic (PAN) image with its corresponding low-resolution multispectral (MS) image. To achieve effective fusion, it is crucial…

Multi-image super-resolution (MISR) can achieve higher image quality than single-image super-resolution (SISR) by aggregating sub-pixel information from multiple spatially shifted frames. Among MISR tasks, burst super-resolution (BurstSR)…

Meta learning approaches to few-shot classification are computationally efficient at test time, requiring just a few optimization steps or single forward pass to learn a new task, but they remain highly memory-intensive to train. This…

Multimodal visual information fusion aims to integrate the multi-sensor data into a single image which contains more complementary information and less redundant features. However the complementary information is hard to extract, especially…

Transformers have recently gained significant attention in the computer vision community. However, the lack of scalability of self-attention mechanisms with respect to image size has limited their wide adoption in state-of-the-art vision…

Transformer-based deep learning models are increasingly deployed on energy, and DRAM bandwidth constrained devices such as laptops and gaming consoles, which presents significant challenges in meeting the latency requirements of the models.…

Outdoor images often suffer from severe degradation due to rain, haze, and noise, impairing image quality and challenging high-level tasks. Current image restoration methods struggle to handle complex degradation while maintaining…

In multi-task learning (MTL) for visual scene understanding, it is crucial to transfer useful information between multiple tasks with minimal interferences. In this paper, we propose a novel architecture that effectively transfers…

In the research area of image super-resolution, Swin-transformer-based models are favored for their global spatial modeling and shifting window attention mechanism. However, existing methods often limit self-attention to non overlapping…

Image restoration is a long-standing task that seeks to recover the latent sharp image from its deteriorated counterpart. Due to the robust capacity of self-attention to capture long-range dependencies, transformer-based methods or some…