Advances in adversarial attacks and defenses in computer vision: A survey

N Akhtar, A Mian, N Kardan, M Shah - IEEE Access, 2021 - ieeexplore.ieee.org
Deep Learning is the most widely used tool in the contemporary field of computer vision. Its
ability to accurately solve complex problems is employed in vision research to learn deep …

Threat of adversarial attacks on deep learning in computer vision: A survey

N Akhtar, A Mian - Ieee Access, 2018 - ieeexplore.ieee.org
Deep learning is at the heart of the current rise of artificial intelligence. In the field of
computer vision, it has become the workhorse for applications ranging from self-driving cars …

Deeprhythm: Exposing deepfakes with attentional visual heartbeat rhythms

H Qi, Q Guo, F Juefei-Xu, X Xie, L Ma, W Feng… - Proceedings of the 28th …, 2020 - dl.acm.org
As the GAN-based face image and video generation techniques, widely known as
DeepFakes, have become more and more matured and realistic, there comes a pressing …

Siammask: A framework for fast online object tracking and segmentation

W Hu, Q Wang, L Zhang, L Bertinetto… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
In this article, we introduce SiamMask, a framework to perform both visual object tracking
and video object segmentation, in real-time, with the same simple method. We improve the …

Auto-exposure fusion for single-image shadow removal

L Fu, C Zhou, Q Guo, F Juefei-Xu… - Proceedings of the …, 2021 - openaccess.thecvf.com
Shadow removal is still a challenging task due to its inherent background-dependent and
spatial-variant properties, leading to unknown and diverse shadow patterns. Even powerful …

Single object tracking research: A survey

R Han, W Feng, Q Guo, Q Hu - arXiv preprint arXiv:2204.11410, 2022 - arxiv.org
Visual object tracking is an important task in computer vision, which has many real-world
applications, eg, video surveillance, visual navigation. Visual object tracking also has many …

Efficientderain: Learning pixel-wise dilation filtering for high-efficiency single-image deraining

Q Guo, J Sun, F Juefei-Xu, L Ma, X Xie… - Proceedings of the …, 2021 - ojs.aaai.org
Single-image deraining is rather challenging due to the unknown rain model. Existing
methods often make specific assumptions of the rain model, which can hardly cover many …

Npc: N euron p ath c overage via characterizing decision logic of deep neural networks

X Xie, T Li, J Wang, L Ma, Q Guo, F Juefei-Xu… - ACM Transactions on …, 2022 - dl.acm.org
Deep learning has recently been widely applied to many applications across different
domains, eg, image classification and audio recognition. However, the quality of Deep …

Cats are not fish: Deep learning testing calls for out-of-distribution awareness

D Berend, X Xie, L Ma, L Zhou, Y Liu, C Xu… - Proceedings of the 35th …, 2020 - dl.acm.org
As Deep Learning (DL) is continuously adopted in many industrial applications, its quality
and reliability start to raise concerns. Similar to the traditional software development …

Learning to adversarially blur visual object tracking

Q Guo, Z Cheng, F Juefei-Xu, L Ma… - Proceedings of the …, 2021 - openaccess.thecvf.com
Motion blur caused by the moving of the object or camera during the exposure can be a key
challenge for visual object tracking, affecting tracking accuracy significantly. In this work, we …