English
Related papers

Related papers: Linear Span Network for Object Skeleton Detection

200 papers

To improve the efficiency and reduce the labour cost of the renovation process, this study presents a lightweight Convolutional Neural Network (CNN)-based architecture to extract crack-like features, such as cracks and joints. Moreover,…

Image and Video Processing · Electrical Eng. & Systems 2021-05-25 Jiesheng Yang , Fangzheng Lin , Yusheng Xiang , Peter Katranuschkov , Raimar J. Scherer

The Convolutional Neural Network (CNN) has achieved great success in image classification. The classification model can also be utilized at image or patch level for many other applications, such as object detection and segmentation. In this…

Computer Vision and Pattern Recognition · Computer Science 2014-12-23 Jun Yuan , Bingbing Ni , Ashraf A. Kassim

Skeleton-based human action recognition has recently attracted increasing attention thanks to the accessibility and the popularity of 3D skeleton data. One of the key challenges in skeleton-based action recognition lies in the large view…

Computer Vision and Pattern Recognition · Computer Science 2019-09-04 Pengfei Zhang , Cuiling Lan , Junliang Xing , Wenjun Zeng , Jianru Xue , Nanning Zheng

In this paper, we develop a new approach of spatially supervised recurrent convolutional neural networks for visual object tracking. Our recurrent convolutional network exploits the history of locations as well as the distinctive visual…

Computer Vision and Pattern Recognition · Computer Science 2016-07-21 Guanghan Ning , Zhi Zhang , Chen Huang , Zhihai He , Xiaobo Ren , Haohong Wang

The objective of hyperspectral remote sensing image salient object detection (HRSI-SOD) is to identify objects or regions that exhibit distinct spectrum contrasts with the background. This area holds significant promise for practical…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Peifu Liu , Huiyan Bai , Tingfa Xu , Jihui Wang , Huan Chen , Jianan Li

We propose an efficient Stereographic Projection Neural Network (SPNet) for learning representations of 3D objects. We first transform a 3D input volume into a 2D planar image using stereographic projection. We then present a shallow 2D…

Computer Vision and Pattern Recognition · Computer Science 2019-01-25 Mohsen Yavartanoo , Eu Young Kim , Kyoung Mu Lee

Object re-identification method is made up of backbone network, feature aggregation, and loss function. However, most backbone networks lack a special mechanism to handle rich scale variations and mine discriminative feature…

Computer Vision and Pattern Recognition · Computer Science 2022-11-11 Fei Shen , Mengwan Wei , Junchi Ren

Non-Line-of-Sight (NLOS) imaging aims at recovering the 3D geometry of objects that are hidden from the direct line of sight. In the past, this method has suffered from the weak available multibounce signal limiting scene size, capture…

Computer Vision and Pattern Recognition · Computer Science 2022-02-01 Ji Hyun Nam , Eric Brandt , Sebastian Bauer , Xiaochun Liu , Eftychios Sifakis , Andreas Velten

Recently, deep neural networks have achieved impressive performance in terms of both reconstruction accuracy and efficiency for single image super-resolution (SISR). However, the network model of these methods is a fully convolutional…

Computer Vision and Pattern Recognition · Computer Science 2019-05-20 Yongliang Tang , Jiashui Huang , Faen Zhang , Weiguo Gong

Recent studies have shown that aggregating convolutional features of a pre-trained Convolutional Neural Network (CNN) can obtain impressive performance for a variety of visual tasks. The symmetric Positive Definite (SPD) matrix becomes a…

Computer Vision and Pattern Recognition · Computer Science 2017-11-21 Zhi Gao , Yuwei Wu , Xingyuan Bu , Yunde Jia

Abstract--- Exploiting the spatial structure in scene images is a key research direction for scene recognition. Due to the large intra-class structural diversity, building and modeling flexible structural layout to adapt various image…

Computer Vision and Pattern Recognition · Computer Science 2020-06-24 Gongwei Chen , Xinhang Song , Haitao Zeng , Shuqiang Jiang

We present a method for skin lesion segmentation for the ISIC 2017 Skin Lesion Segmentation Challenge. Our approach is based on a Fully Convolutional Network architecture which is trained end to end, from scratch, on a limited dataset. Our…

Computer Vision and Pattern Recognition · Computer Science 2017-03-16 Dhanesh Ramachandram , Terrance DeVries

Deep neural networks face several challenges in hyperspectral image classification, including complex and sparse ground object distributions, small clustered structures, and elongated multi-branch features that often lead to missing…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Guandong Li , Mengxia Ye

In recent years, change point detection for high dimensional data has become increasingly important in many scientific fields. Most literature develop a variety of separate methods designed for specified models (e.g. mean shift model,…

Methodology · Statistics 2022-07-20 Yue Bai , Abolfazl Safikhani

Human action recognition from skeleton data, fueled by the Graph Convolutional Network (GCN), has attracted lots of attention, due to its powerful capability of modeling non-Euclidean structure data. However, many existing GCN methods…

Computer Vision and Pattern Recognition · Computer Science 2019-11-12 Wei Peng , Xiaopeng Hong , Haoyu Chen , Guoying Zhao

Porting state of the art deep learning algorithms to resource constrained compute platforms (e.g. VR, AR, wearables) is extremely challenging. We propose a fast, compact, and accurate model for convolutional neural networks that enables…

Computer Vision and Pattern Recognition · Computer Science 2017-06-14 Hessam Bagherinezhad , Mohammad Rastegari , Ali Farhadi

We propose a novel skeleton-based representation for 3D action recognition in videos using Deep Convolutional Neural Networks (D-CNNs). Two key issues have been addressed: First, how to construct a robust representation that easily captures…

Computer Vision and Pattern Recognition · Computer Science 2018-07-19 Huy Hieu Pham , Louahdi Khoudour , Alain Crouzil , Pablo Zegers , Sergio A. Velastin

We propose a novel cascaded framework, namely deep deformation network (DDN), for localizing landmarks in non-rigid objects. The hallmarks of DDN are its incorporation of geometric constraints within a convolutional neural network (CNN)…

Computer Vision and Pattern Recognition · Computer Science 2016-07-26 Xiang Yu , Feng Zhou , Manmohan Chandraker

In representation learning on the graph-structured data, under heterophily (or low homophily), many popular GNNs may fail to capture long-range dependencies, which leads to their performance degradation. To solve the above-mentioned issue,…

Machine Learning · Computer Science 2021-06-29 Mengying Jiang , Guizhong Liu , Yuanchao Su , Xinliang Wu

3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information. Conventional 2D convolutions are unsuitable for this task because they fail to capture local object and its scale…

Computer Vision and Pattern Recognition · Computer Science 2019-12-16 Mingyu Ding , Yuqi Huo , Hongwei Yi , Zhe Wang , Jianping Shi , Zhiwu Lu , Ping Luo