English
Related papers

Related papers: D3Net: Densely connected multidilated DenseNet for…

200 papers

In recent years, decentralized sensor networks have garnered significant attention in the field of state estimation owing to enhanced robustness, scalability, and fault tolerance. Optimal fusion performance can be achieved under fully…

Signal Processing · Electrical Eng. & Systems 2025-08-27 Ruifeng Dong , Ming Wang , Ning Liu , Tong Guo , Jiayi Kang , Xiaojing Shen , Yao Mao

One of the practical choices for making a lightweight semantic segmentation model is to combine a depth-wise separable convolution with a dilated convolution. However, the simple combination of these two methods results in an…

Computer Vision and Pattern Recognition · Computer Science 2019-07-30 Hyojin Park , Youngjoon Yoo , Geonseok Seo , Dongyoon Han , Sangdoo Yun , Nojun Kwak

The advent of deep learning has led to the prevalence of deep neural network architectures for monaural music source separation, with end-to-end approaches that operate directly on the waveform level increasingly receiving research…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-09 Christos Garoufis , Athanasia Zlatintsi , Petros Maragos

We present Deep Mesh Denoising Network (DMD-Net), an end-to-end deep learning framework, for solving the mesh denoising problem. DMD-Net consists of a Graph Convolutional Neural Network in which aggregation is performed in both the primal…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Aalok Gangopadhyay , Shashikant Verma , Shanmuganathan Raman

Time Delay Neural Networks (TDNN)-based methods are widely used in dialect identification. However, in previous work with TDNN application, subtle variant is being neglected in different feature scales. To address this issue, we propose a…

Computation and Language · Computer Science 2021-08-18 Tianlong Kong , Shouyi Yin , Dawei Zhang , Wang Geng , Xin Wang , Dandan Song , Jinwen Huang , Huiyu Shi , Xiaorui Wang

We study the single-channel source separation problem involving orthogonal frequency-division multiplexing (OFDM) signals, which are ubiquitous in many modern-day digital communication systems. Related efforts have been pursued in monaural…

Signal Processing · Electrical Eng. & Systems 2023-06-28 Gary C. F. Lee , Amir Weiss , Alejandro Lancho , Yury Polyanskiy , Gregory W. Wornell

Convolutional Neural Networks (CNNs) constitute a class of Deep Learning models which have been used in the recent past to resolve many problems in computer vision, in particular optical flow estimation. Measuring displacement and strain…

Image and Video Processing · Electrical Eng. & Systems 2020-09-10 S. Boukhtache , K. Abdelouahab , F. Berry , B. Blaysat , M. Grediac , F. Sur

Disparity prediction from stereo images is essential to computer vision applications including autonomous driving, 3D model reconstruction, and object detection. To predict accurate disparity map, we propose a novel deep learning…

Computer Vision and Pattern Recognition · Computer Science 2019-05-01 Zhibo Rao , Mingyi He , Yuchao Dai , Zhidong Zhu , Bo Li , Renjie He

With joint learning of sampling and recovery, the deep learning-based compressive sensing (DCS) has shown significant improvement in performance and running time reduction. Its reconstructed image, however, losses high-frequency content…

Computer Vision and Pattern Recognition · Computer Science 2018-09-19 Thuong Nguyen Canh , Byeungwoo Jeon

The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of computational cost. Recently, dilated filtering has…

Computer Vision and Pattern Recognition · Computer Science 2018-05-23 Pengju Liu , Hongzhi Zhang , Kai Zhang , Liang Lin , Wangmeng Zuo

Deep diffeomorphic registration faces significant challenges for high-dimensional images, especially in terms of memory limits. Existing approaches either downsample original images, or approximate underlying transformations, or reduce…

Image and Video Processing · Electrical Eng. & Systems 2021-05-25 Ankita Joshi , Yi Hong

We present a CNN architecture for speech enhancement from multichannel first-order Ambisonics mixtures. The data-dependent spatial filters, deduced from a mask-based approach, are used to help an automatic speech recognition engine to face…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-03 Amélie Bosca , Alexandre Guérin , Lauréline Perotin , Srđan Kitić

In recent years, deep neural networks (DNNs) based approaches have achieved the start-of-the-art performance for music source separation (MSS). Although previous methods have addressed the large receptive field modeling using various…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-05 Lianwu Chen , Xiguang Zheng , Chen Zhang , Liang Guo , Bing Yu

Residual network (ResNet) and densely connected network (DenseNet) have significantly improved the training efficiency and performance of deep convolutional neural networks (DCNNs) mainly for object classification tasks. In this paper, we…

Image and Video Processing · Electrical Eng. & Systems 2020-04-29 Mina Jafari , Dorothee Auer , Susan Francis , Jonathan Garibaldi , Xin Chen

Supervised deep learning approaches to underdetermined audio source separation achieve state-of-the-art performance but require a dataset of mixtures along with their corresponding isolated source signals. Such datasets can be extremely…

Realistic speech-driven 3D facial animation is a challenging problem due to the complex relationship between speech and face. In this paper, we propose a deep architecture, called Geometry-guided Dense Perspective Network (GDPnet), to…

Graphics · Computer Science 2020-08-25 Jingying Liu , Binyuan Hui , Kun Li , Yunke Liu , Yu-Kun Lai , Yuxiang Zhang , Yebin Liu , Jingyu Yang

Audio-visual saliency prediction can draw support from diverse modality complements, but further performance enhancement is still challenged by customized architectures as well as task-specific loss functions. In recent studies, denoising…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Junwen Xiong , Peng Zhang , Tao You , Chuanyue Li , Wei Huang , Yufei Zha

Face recognition is one of the most active tasks in computer vision and has been widely used in the real world. With great advances made in convolutional neural networks (CNN), lots of face recognition algorithms have achieved high accuracy…

Computer Vision and Pattern Recognition · Computer Science 2022-06-01 Jiehua Zhang , Zhuo Su , Li Liu

Past few years have witnessed exponential growth of interest in deep learning methodologies with rapidly improving accuracies and reduced computational complexity. In particular, architectures using Convolutional Neural Networks (CNNs) have…

Computer Vision and Pattern Recognition · Computer Science 2018-05-11 Sai Samarth R Phaye , Apoorva Sikka , Abhinav Dhall , Deepti Bathula

In computer vision, convolutional neural networks (CNN) such as ConvNeXt, have been able to surpass state-of-the-art transformers, partly thanks to depthwise separable convolutions (DSC). DSC, as an approximation of the regular convolution,…