Zobrazeno 1 - 10
of 490
pro vyhledávání: '"Wei, Mingqiang"'
Autor:
Liu, Yun, Li, Peng, Yan, Xuefeng, Nan, Liangliang, Wang, Bing, Chen, Honghua, Gong, Lina, Zhao, Wei, Wei, Mingqiang
The core of self-supervised point cloud learning lies in setting up appropriate pretext tasks, to construct a pre-training framework that enables the encoder to perceive 3D objects effectively. In this paper, we integrate two prevalent methods, maske
Externí odkaz:
http://arxiv.org/abs/2411.06041
Software defect prediction (SDP) aims to identify high-risk defect modules in software development, optimizing resource allocation. While previous studies show that dependency network metrics improve defect prediction, most methods focus on code-base
Externí odkaz:
http://arxiv.org/abs/2410.19550
Current automatic deep learning (i.e., AutoDL) frameworks rely on training feedback from actual runs, which often hinder their ability to provide quick and clear performance predictions for selecting suitable DL systems. To address this issue, we pro
Externí odkaz:
http://arxiv.org/abs/2410.14743
Images captured in hazy outdoor conditions often suffer from colour distortion, low contrast, and loss of detail, which impair high-level vision tasks. Single image dehazing is essential for applications such as autonomous driving and surveillance, w
Externí odkaz:
http://arxiv.org/abs/2410.04762
Autor:
Gu, Lipeng, Wei, Mingqiang, Yan, Xuefeng, Zhu, Dingkun, Zhao, Wei, Xie, Haoran, Liu, Yong-Jin
Multi-modal 3D multi-object tracking (MOT) typically necessitates extensive computational costs of deep neural networks (DNNs) to extract multi-modal representations. In this paper, we propose an intriguing question: May we learn from multiple modali
Externí odkaz:
http://arxiv.org/abs/2409.00618
Vulnerability detection is garnering increasing attention in software engineering, since code vulnerabilities possibly pose significant security. Recently, reusing various code pre-trained models has become common for code embedding without providing
Externí odkaz:
http://arxiv.org/abs/2408.04863
Many targets are often very small in infrared images due to the long-distance imaging meachnism. UNet and its variants, as popular detection backbone networks, downsample the local features early and cause the irreversible loss of these local feature
Externí odkaz:
http://arxiv.org/abs/2406.13445
Publikováno v:
Computer Graphics Forum 2024
Spherical harmonics are a favorable technique for 3D representation, employing a frequency-based approach through the spherical harmonic transform (SHT). Typically, SHT is performed using equiangular sampling grids. However, these grids are non-unifo
Externí odkaz:
http://arxiv.org/abs/2406.08308
Haze severely degrades the visual quality of remote sensing images and hampers the performance of road extraction, vehicle detection, and traffic flow monitoring. The emerging denoising diffusion probabilistic model (DDPM) exhibits the significant po
Externí odkaz:
http://arxiv.org/abs/2405.09083
In this paper, we propose a physics-inspired contrastive learning paradigm for low-light enhancement, called PIE. PIE primarily addresses three issues: (i) To resolve the problem of existing learning-based methods often training a LLE model with stri
Externí odkaz:
http://arxiv.org/abs/2404.04586