English
Related papers

Related papers: Deep Learning for Robust Motion Segmentation with …

200 papers

We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view. We emphasize the importance of inherent correlation among video frames and…

Computer Vision and Pattern Recognition · Computer Science 2020-01-22 Xiankai Lu , Wenguan Wang , Chao Ma , Jianbing Shen , Ling Shao , Fatih Porikli

The capability to perform facial analysis from video sequences has significant potential to positively impact in many areas of life. One such area relates to the medical domain to specifically aid in the diagnosis and rehabilitation of…

Computer Vision and Pattern Recognition · Computer Science 2019-07-30 Gary Storey , Richard Jiang , Shelagh Keogh , Ahmed Bouridane , Chang-Tsun Li

Classical monocular vSLAM/VO methods suffer from the scale ambiguity problem. Hybrid approaches solve this problem by adding deep learning methods, for example by using depth maps which are predicted by a CNN. We suggest that it is better…

Computer Vision and Pattern Recognition · Computer Science 2019-04-18 Robin Kreuzig , Matthias Ochs , Rudolf Mester

Registration plays an important role in medical image analysis. Deep learning-based methods have been studied for medical image registration, which leverage convolutional neural networks (CNNs) for efficiently regressing a dense deformation…

Computer Vision and Pattern Recognition · Computer Science 2022-08-16 Xiaoru Gao , GuoYan Zheng

Inspired by recent advances of deep learning in instance segmentation and object tracking, we introduce video object segmentation problem as a concept of guided instance segmentation. Our model proceeds on a per-frame basis, guided by the…

Computer Vision and Pattern Recognition · Computer Science 2019-02-05 Anna Khoreva , Federico Perazzi , Rodrigo Benenson , Bernt Schiele , Alexander Sorkine-Hornung

In this paper, we evaluate convolutional neural network (CNN) features using the AlexNet architecture and very deep convolutional network (VGGNet) architecture. To date, most CNN researchers have employed the last layers before output,…

Computer Vision and Pattern Recognition · Computer Science 2015-09-28 Hirokatsu Kataoka , Kenji Iwata , Yutaka Satoh

Dynamic imaging is a recently proposed action description paradigm for simultaneously capturing motion and temporal evolution information, particularly in the context of deep convolutional neural networks (CNNs). Compared with optical flow…

Computer Vision and Pattern Recognition · Computer Science 2018-12-31 Yang Xiao , Jun Chen , Yancheng Wang , Zhiguo Cao , Joey Tianyi Zhou , Xiang Bai

The UNet model consists of fully convolutional network (FCN) layers arranged as contracting encoder and upsampling decoder maps. Nested arrangements of these encoder and decoder maps give rise to extensions of the UNet model, such as UNete…

Image and Video Processing · Electrical Eng. & Systems 2023-04-11 Yilong Yang , Srinandan Dasmahapatra , Sasan Mahmoodi

Moving Object Detection (MOD) is a fundamental step for many computer vision applications. MOD becomes very challenging when a video sequence captured from a static or moving camera suffers from the challenges: camouflage, shadow, dynamic…

Computer Vision and Pattern Recognition · Computer Science 2022-07-15 Jhony H. Giraldo , Sajid Javed , Naoufel Werghi , Thierry Bouwmans

Scene understanding based on LiDAR point cloud is an essential task for autonomous cars to drive safely, which often employs spherical projection to map 3D point cloud into multi-channel 2D images for semantic segmentation. Most existing…

Computer Vision and Pattern Recognition · Computer Science 2021-07-19 Aoran Xiao , Xiaofei Yang , Shijian Lu , Dayan Guan , Jiaxing Huang

Convolutional neural network (CNN) slides a kernel over the whole image to produce an output map. This kernel scheme reduces the number of parameters with respect to a fully connected neural network (NN). While CNN has proven to be an…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Ihsan Ullah , Alfredo Petrosino

Medical image segmentation, particularly in multi-domain scenarios, requires precise preservation of anatomical structures across diverse representations. While deep learning has advanced this field, existing models often struggle with…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Afshin Bozorgpour , Sina Ghorbani Kolahi , Reza Azad , Ilker Hacihaliloglu , Dorit Merhof

For safety-critical robotics applications such as autonomous driving, it is important to detect all required objects accurately in real-time. Motion segmentation offers a solution by identifying dynamic objects from the scene in a…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Riku Inoue , Masamitsu Tsuchiya , Yuji Yasui

In this paper, we propose a fast fully convolutional neural network (FCNN) for crowd segmentation. By replacing the fully connected layers in CNN with 1 by 1 convolution kernels, FCNN takes whole images as inputs and directly outputs…

Computer Vision and Pattern Recognition · Computer Science 2014-11-18 Kai Kang , Xiaogang Wang

In this paper, we present RegNet, the first deep convolutional neural network (CNN) to infer a 6 degrees of freedom (DOF) extrinsic calibration between multimodal sensors, exemplified using a scanning LiDAR and a monocular camera. Compared…

Computer Vision and Pattern Recognition · Computer Science 2017-07-12 Nick Schneider , Florian Piewak , Christoph Stiller , Uwe Franke

We propose a novel deep learning model named ACLNet, for cloud segmentation from ground images. ACLNet uses both deep neural network and machine learning (ML) algorithm to extract complementary features. Specifically, it uses…

Computer Vision and Pattern Recognition · Computer Science 2022-07-14 Dhruv Makwana , Subhrajit Nag , Onkar Susladkar , Gayatri Deshmukh , Sai Chandra Teja R , Sparsh Mittal , C Krishna Mohan

We present a new model DrNET that learns disentangled image representations from video. Our approach leverages the temporal coherence of video and a novel adversarial loss to learn a representation that factorizes each frame into a…

Machine Learning · Computer Science 2024-03-15 Remi Denton , Vighnesh Birodkar

In the current monocular depth research, the dominant approach is to employ unsupervised training on large datasets, driven by warped photometric consistency. Such approaches lack robustness and are unable to generalize to challenging…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Jaime Spencer , Richard Bowden , Simon Hadfield

In the segmentation of remotely sensed images, deep learning models are typically pre-trained using large image databases like ImageNet before fine-tuned on domain-specific datasets. However, the performance of these fine-tuned models is…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Yuan Fang , Yuanzhi Cai , Jagannath Aryal , Qinfeng Zhu , Hong Huang , Cheng Zhang , Lei Fan

Previous deep image registration methods that employ single homography, multi-grid homography, or thin-plate spline often struggle with real scenes containing depth disparities due to their inherent limitations. To address this, we propose…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Haokai Zhu , Bo Qu , Si-Yuan Cao , Runmin Zhang , Shujie Chen , Bailin Yang , Hui-Liang Shen