Results 11 to 20 of about 101,363 (247)

Multi-View Joint Learning and BEV Feature-Fusion Network for 3D Object Detection

Applied Sciences, 2023
Traditional 3D object detectors use BEV (bird’s eye view) feature maps to generate 3D object proposals, but in a single BEV feature map, there are inevitably the problems of high compression and information loss. To solve this problem, we propose a multi-
Qunming Liu, Xiaodong Li, Xiaofei Zhang, Xiaojun Tan, Bodong Shi   +4 more
doaj   +1 more source

Scene Uyghur Text Detection Based on Fine-Grained Feature Representation

Sensors, 2022
Scene text detection task aims to precisely localize text in natural environments. At present, the application scenarios of text detection topics have gradually shifted from plain document text to more complex natural scenarios.
Yiwen Wang, Hornisa Mamat, Xuebin Xu, Alimjan Aysa, Kurban Ubul   +4 more
doaj   +1 more source

Finger-Vein Verification Based on Multi-Features Fusion [PDF]

Sensors, 2013
This paper presents a new scheme to improve the performance of finger-vein identification systems. Firstly, a vein pattern extraction method to extract the finger-vein shape and orientation features is proposed. Secondly, to accommodate the potential local and global variations at the same time, a region-based matching scheme is investigated by ...
Huafeng Qin, Lan Qin, Lian Xue, Xiping He, Chengbo Yu, Xinyuan Liang   +5 more
openaire   +3 more sources

Research and prospect of standard for biometric multi-modal fusion used with mobile devices

Dianxin kexue, 2021
Aiming at the problem of inconsistent biometric multi-modal fusion technology framework for mobile devices and lack of standards, a unified technical framework of multi-modal fusion standards was proposed.Firstly, the current status of standardization ...
Guanchen LIN, Zhifei WANG
doaj   +2 more sources

Multi-person feature fusion transfer learning-based convolutional neural network for SSVEP-based collaborative BCI

Frontiers in Neuroscience, 2022
ObjectiveThe conventional single-person brain–computer interface (BCI) systems have some intrinsic deficiencies such as low signal-to-noise ratio, distinct individual differences, and volatile experimental effect.
Penghai Li, Jianxian Su, Abdelkader Nasreddine Belkacem, Longlong Cheng, Chao Chen   +4 more
doaj   +1 more source

ConCs-Fusion: A Context Clustering-Based Radar and Camera Fusion for Three-Dimensional Object Detection

Remote Sensing, 2023
Multi-modality three-dimensional (3D) object detection is a crucial technology for the safe and effective operation of environment perception systems in autonomous driving.
Wei He, Zhenmiao Deng, Yishan Ye, Pingping Pan   +3 more
doaj   +1 more source

Multiscale Feature Extraction and Fusion of Image and Text in VQA

International Journal of Computational Intelligence Systems, 2023
The Visual Question Answering (VQA) system is the process of finding useful information from images related to the question to answer the question correctly.
Siyu Lu, Yueming Ding, Mingzhe Liu, Zhengtong Yin, Lirong Yin, Wenfeng Zheng   +5 more
doaj   +1 more source

A Novel 2D-3D CNN with Spectral-Spatial Multi-Scale Feature Fusion for Hyperspectral Image Classification

Remote Sensing, 2021
Multifarious hyperspectral image (HSI) classification methods based on convolutional neural networks (CNN) have been gradually proposed and achieve a promising classification performance.
Dongxu Liu, Guangliang Han, Peixun Liu, Hang Yang, Xinglong Sun, Qingqing Li, Jiajia Wu   +6 more
doaj   +1 more source

Adaptive Feature Pyramid Networks for Object Detection

IEEE Access, 2021
In general object detection, scale variation is always a big challenge. At present, feature pyramid networks are employed in numerous methods to alleviate the problems caused by large scale range of objects in object detection, which makes use of multi ...
Chengyang Wang, Caiming Zhong
doaj   +1 more source

Adaptive Weighted Multi-Level Fusion of Multi-Scale Features: A New Approach to Pedestrian Detection

Future Internet, 2021
Great achievements have been made in pedestrian detection through deep learning. For detectors based on deep learning, making better use of features has become the key to their detection effect.
Yao Xu, Qin Yu
doaj   +1 more source