Results 51 to 60 of about 5,326,339 (296)
Fully Convolutional Adaptation Networks for Semantic Segmentation [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018 The recent advances in deep neural networks have convincingly demonstrated high capability in learning vision models on large datasets. Nevertheless, collecting expert labeled datasets especially with pixel-level annotations is an extremely expensive process.
Yiheng Zhang +4 more
openaire +4 more sources
Fully convolutional networks for action recognition
IET Computer Vision, 2017 Human action recognition is an important and challenging topic in computer vision. Recently, convolutional neural networks (CNNs) have established impressive results for many image recognition tasks. The CNNs usually contain million parameters which prone to overfit when training on small datasets.
Sheng Yu +3 more
openaire +2 more sources
Speech Dereverberation Using Fully Convolutional Networks [PDF]
2018 26th European Signal Processing Conference (EUSIPCO), 2018 Speech derverberation using a single microphone is addressed in this paper. Motivated by the recent success of the fully convolutional networks (FCN) in many image processing applications, we investigate their applicability to enhance the speech signal represented by short-time Fourier transform (STFT) images. We present two variations: a "U-Net" which
Ori Ernst +3 more
openaire +2 more sources
Fast Image Processing with Fully-Convolutional Networks [PDF]
2017 IEEE International Conference on Computer Vision (ICCV), 2017 We present an approach to accelerating a wide variety of image processing operators. Our approach uses a fully-convolutional network that is trained on input-output pairs that demonstrate the operator's action. After training, the original operator need not be run at all. The trained network operates at full resolution and runs in constant time.
Qifeng Chen 0001 +2 more
openaire +3 more sources
Fully Convolutional Siamese Networks for Change Detection [PDF]
2018 25th IEEE International Conference on Image Processing (ICIP), 2018 To appear inProc.
Rodrigo Caye Daudt +2 more
openaire +4 more sources
Vehicle Detection from 3D Lidar Using Fully Convolutional Network [PDF]
, 2020 -Convolutional network techniques have recently achieved great success in vision based detection tasks. This paper introduces the recent development of our research on transplanting the fully convolutional network technique to the detection tasks on 3D ...
Bo Li, Tian Xia, Tianlei Zhang
core
Multiscale fully convolutional network‐based approach for multilingual character segmentation
IET Computer Vision, 2021 Character segmentation is a challenging task for optical character recognition systems. Traditional methods usually utilize rule‐based algorithms but most of them are not applicable in modern intelligent recognition applications that require high ...
Chao Yu, Jin Liu, Yunhui Li
doaj +1 more source
Fully Convolutional Neural Networks for Crowd Segmentation
CoRR, 2014 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 segmentation maps by one pass of forward propagation.
Kai Kang, Xiaogang Wang
openaire +2 more sources
EFFICIENT LARGE-SCALE AIRBORNE LIDAR DATA CLASSIFICATION VIA FULLY CONVOLUTIONAL NETWORK [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2020 Nowadays, we are witnessing an increasing availability of large-scale airborne LiDAR (Light Detection and Ranging) data, that greatly improve our knowledge of urban areas and natural environment.
E. Maset, B. Padova, A. Fusiello
doaj +1 more source
Self-supervised Learning with Fully Convolutional Networks
CoRR, 2020 Although deep learning based methods have achieved great success in many computer vision tasks, their performance relies on a large number of densely annotated samples that are typically difficult to obtain. In this paper, we focus on the problem of learning representation from unlabeled data for semantic segmentation.
Zhengeng Yang +4 more
openaire +2 more sources