English
Related papers

Related papers: UCAN: Unified Convolutional Attention Network for …

200 papers

U-Net has become a cornerstone in various visual applications such as image segmentation and diffusion probability models. While numerous innovative designs and improvements have been introduced by incorporating transformers or MLPs, the…

Image and Video Processing · Electrical Eng. & Systems 2024-08-23 Chenxin Li , Xinyu Liu , Wuyang Li , Cheng Wang , Hengyu Liu , Yifan Liu , Zhen Chen , Yixuan Yuan

Under-display cameras (UDCs) allow for full-screen designs by positioning the imaging sensor underneath the display. Nonetheless, light diffraction and scattering through the various display layers result in spatially varying and complex…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Daehyun Kim , Youngmin Kim , Yoon Ju Oh , Tae Hyun Kim

Medical image segmentation is critical for accurate diagnostics and treatment planning, but remains challenging due to complex anatomical structures and limited annotated training data. CNN-based segmentation methods excel at local feature…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Nishchal Sapkota , Haoyan Shi , Yejia Zhang , Xianshi Ma , Bofang Zheng , Fabian Vazquez , Pengfei Gu , Danny Z. Chen

Vision transformers are effective deep learning models for vision tasks, including medical image segmentation. However, they lack efficiency and translational invariance, unlike convolutional neural networks (CNNs). To model long-range…

Image and Video Processing · Electrical Eng. & Systems 2023-08-15 Liam Chalcroft , Ruben Lourenço Pereira , Mikael Brudfors , Andrew S. Kayser , Mark D'Esposito , Cathy J. Price , Ioannis Pappas , John Ashburner

With the increased deployment of face recognition systems in our daily lives, face presentation attack detection (PAD) is attracting much attention and playing a key role in securing face recognition systems. Despite the great performance…

Computer Vision and Pattern Recognition · Computer Science 2021-11-03 Meiling Fang , Naser Damer , Florian Kirchbuchner , Arjan Kuijper

Many previous methods have showed the importance of considering semantically relevant objects for performing event recognition, yet none of the methods have exploited the power of deep convolutional neural networks to directly integrate…

Computer Vision and Pattern Recognition · Computer Science 2017-03-23 Sungmin Eum , Hyungtae Lee , Heesung Kwon , David Doermann

Medical image segmentation is crucial for the development of computer-aided diagnostic and therapeutic systems, but still faces numerous difficulties. In recent years, the commonly used encoder-decoder architecture based on CNNs has been…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Davoud Saadati , Omid Nejati Manzari , Sattar Mirzakuchaki

In this paper, we present a general framework for low-level vision tasks including image compression artifacts reduction and image denoising. Under this framework, a novel concatenated attention neural network (CANet) is specifically…

Image and Video Processing · Electrical Eng. & Systems 2020-06-22 Tian YingJie , Wang YiQi , Yang LinRui , Qi ZhiQuan

Convolutional-deconvolution networks can be adopted to perform end-to-end saliency detection. But, they do not work well with objects of multiple scales. To overcome such a limitation, in this work, we propose a recurrent attentional…

Computer Vision and Pattern Recognition · Computer Science 2016-04-13 Jason Kuen , Zhenhua Wang , Gang Wang

In recent years, convolutional neural networks (CNNs) have been successfully implemented to various image recognition applications, such as medical image analysis, object detection, and image segmentation. Many studies and applications have…

Image and Video Processing · Electrical Eng. & Systems 2021-05-06 Chi-Shiang Wang , Fang-Yi Su , Tsung-Lu Michael Lee , Yi-Shan Tsai , Jung-Hsien Chiang

Convolutional neural networks (CNNs) have long been the cornerstone of target detection, but they are often limited by limited receptive fields, which hinders their ability to capture global contextual information. We re-examined the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Haolin Wei

Deep convolutional neural networks (CNN) have recently been shown to generate promising results for aesthetics assessment. However, the performance of these deep CNN methods is often compromised by the constraint that the neural network…

Computer Vision and Pattern Recognition · Computer Science 2017-04-04 Shuang Ma , Jing Liu , Chang Wen Chen

Optical and hybrid convolutional neural networks (CNNs) recently have become of increasing interest to achieve low-latency, low-power image classification and computer vision tasks. However, implementing optical nonlinearity is challenging,…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Anna Wirth-Singh , Jinlin Xiang , Minho Choi , Johannes E. Fröch , Luocheng Huang , Shane Colburn , Eli Shlizerman , Arka Majumdar

Low-resolution image segmentation is crucial in real-world applications such as robotics, augmented reality, and large-scale scene understanding, where high-resolution data is often unavailable due to computational constraints. To address…

Computer Vision and Pattern Recognition · Computer Science 2025-05-09 Anzhe Cheng , Chenzhong Yin , Yu Chang , Heng Ping , Shixuan Li , Shahin Nazarian , Paul Bogdan

Convolutional neural network (CNN) has achieved great success on image super-resolution (SR). However, most deep CNN-based SR models take massive computations to obtain high performance. Downsampling features for multi-resolution fusion is…

Image and Video Processing · Electrical Eng. & Systems 2022-11-30 Bin Sun , Yulun Zhang , Songyao Jiang , Yun Fu

We present an efficient speech separation neural network, ARFDCN, which combines dilated convolutions, multi-scale fusion (MSF), and channel attention to overcome the limited receptive field of convolution-based networks and the high…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-12 Junyu Wang

Increasingly, convolution neural network (CNN) based super resolution models have been proposed for better reconstruction results, but their large model size and complicated structure inhibit their real-time hardware implementation. Current…

Hardware Architecture · Computer Science 2022-05-03 Dun-Hao Yang , Tian-Sheuan Chang

Automated liver segmentation from radiology scans (CT, MRI) can improve surgery and therapy planning and follow-up assessment in addition to conventional use for diagnosis and prognosis. Although convolutional neural networks (CNNs) have…

Image and Video Processing · Electrical Eng. & Systems 2022-05-31 Ugur Demir , Zheyuan Zhang , Bin Wang , Matthew Antalek , Elif Keles , Debesh Jha , Amir Borhani , Daniela Ladner , Ulas Bagci

Cone-beam computed tomography (CBCT) using only a few X-ray projection views enables faster scans with lower radiation dose, but the resulting severe under-sampling causes strong artifacts and poor spatial coverage. We address these…

Image and Video Processing · Electrical Eng. & Systems 2025-06-25 Minmin Yang , Huantao Ren , Senem Velipasalar

In this paper, we propose a novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images. We utilise the advantage of convolutional neural networks to automatically learn the…

Computer Vision and Pattern Recognition · Computer Science 2015-08-18 Hongyang Li , Huchuan Lu , Zhe Lin , Xiaohui Shen , Brian Price