Recent advances in deep learning for object detection

X Wu, D Sahoo, SCH Hoi - Neurocomputing, 2020‏ - Elsevier
Object detection is a fundamental visual recognition problem in computer vision and has
been widely studied in the past decades. Visual object detection aims to find objects of …

Intelligent small object detection for digital twin in smart manufacturing with industrial cyber-physical systems

X Zhou, X Xu, W Liang, Z Zeng… - IEEE Transactions …, 2021‏ - ieeexplore.ieee.org
Recently, along with several technological advancements in cyber-physical systems, the
revolution of Industry 4.0 has brought in an emerging concept named digital twin (DT), which …

Reverse attention for salient object detection

S Chen, X Tan, B Wang, X Hu - Proceedings of the …, 2018‏ - openaccess.thecvf.com
Benefit from the quick development of deep learning techniques, salient object detection has
achieved remarkable progresses recently. However, there still exists following two major …

Ubernet: Training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory

I Kokkinos - Proceedings of the IEEE conference on …, 2017‏ - openaccess.thecvf.com
In this work we train in an end-to-end manner a convolutional neural network (CNN) that
jointly handles low-, mid-, and high-level vision tasks in a unified architecture. Such a …

Holistically-nested edge detection

S **e, Z Tu - … of the IEEE international conference on …, 2015‏ - openaccess.thecvf.com
We develop a new edge detection algorithm that addresses two critical issues in this long-
standing vision problem:(1) holistic image training; and (2) multi-scale feature learning. Our …

CrackFormer network for pavement crack segmentation

H Liu, J Yang, X Miao, C Mertz… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
In this paper, we rethink our earlier work on self-attention based crack segmentation, and
propose an upgraded CrackFormer network (CrackFormer-II) for pavement crack …

Dynamic feature integration for simultaneous detection of salient object, edge, and skeleton

JJ Liu, Q Hou, MM Cheng - IEEE Transactions on Image …, 2020‏ - ieeexplore.ieee.org
Salient object segmentation, edge detection, and skeleton extraction are three contrasting
low-level pixel-wise vision problems, where existing works mostly focused on designing …

RoadNet: Learning to comprehensively analyze road networks in complex urban scenes from high-resolution remotely sensed images

Y Liu, J Yao, X Lu, M **a, X Wang… - IEEE Transactions on …, 2018‏ - ieeexplore.ieee.org
It is a classical task to automatically extract road networks from very high-resolution (VHR)
images in remote sensing. This paper presents a novel method for extracting road networks …

Traffic sign detection and recognition using fully convolutional network guided proposals

Y Zhu, C Zhang, D Zhou, X Wang, X Bai, W Liu - Neurocomputing, 2016‏ - Elsevier
Detecting and recognizing traffic signs is a hot topic in the field of computer vision with lots of
applications, eg, safe driving, path planning, robot navigation etc. We propose a novel …

Decomposition and completion network for salient object detection

Z Wu, L Su, Q Huang - IEEE transactions on image processing, 2021‏ - ieeexplore.ieee.org
Recently, fully convolutional networks (FCNs) have made great progress in the task of
salient object detection and existing state-of-the-arts methods mainly focus on how to …