Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Jiang, Kaixun"'
Autor:
Guo, Pinxue, Li, Wanyun, Huang, Hao, Hong, Lingyi, Zhou, Xinyu, Chen, Zhaoyu, Li, Jinglun, Jiang, Kaixun, Zhang, Wei, Zhang, Wenqiang
Multi-modal Video Object Segmentation (VOS), including RGB-Thermal, RGB-Depth, and RGB-Event, has garnered attention due to its capability to address challenging scenarios where traditional VOS methods struggle, such as extreme illumination, rapid mo
Externí odkaz:
http://arxiv.org/abs/2409.19342
Autor:
Hong, Lingyi, Li, Jinglun, Zhou, Xinyu, Yan, Shilin, Guo, Pinxue, Jiang, Kaixun, Chen, Zhaoyu, Gao, Shuyong, Zhang, Wei, Lu, Hong, Zhang, Wenqiang
Transformer-based trackers have established a dominant role in the field of visual object tracking. While these trackers exhibit promising performance, their deployment on resource-constrained devices remains challenging due to inefficiencies. To imp
Externí odkaz:
http://arxiv.org/abs/2409.17564
Autor:
Li, Jinglun, Zhou, Xinyu, Jiang, Kaixun, Hong, Lingyi, Guo, Pinxue, Chen, Zhaoyu, Ge, Weifeng, Zhang, Wenqiang
Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area where AI
Externí odkaz:
http://arxiv.org/abs/2408.15566
Autor:
Guo, Haijing, Wang, Jiafeng, Chen, Zhaoyu, Jiang, Kaixun, Hong, Lingyi, Guo, Pinxue, Li, Jinglun, Zhang, Wenqiang
Deep neural networks (DNNs) are known to be susceptible to adversarial examples, leading to significant performance degradation. In black-box attack scenarios, a considerable attack performance gap between the surrogate model and the target model per
Externí odkaz:
http://arxiv.org/abs/2408.05745
Vision foundation models are increasingly employed in autonomous driving systems due to their advanced capabilities. However, these models are susceptible to adversarial attacks, posing significant risks to the reliability and safety of autonomous ve
Externí odkaz:
http://arxiv.org/abs/2407.13111
Autor:
Fu, Jiyuan, Chen, Zhaoyu, Jiang, Kaixun, Guo, Haijing, Wang, Jiafeng, Gao, Shuyong, Zhang, Wenqiang
Despite the substantial advancements in Vision-Language Pre-training (VLP) models, their susceptibility to adversarial attacks poses a significant challenge. Existing work rarely studies the transferability of attacks on VLP models, resulting in a su
Externí odkaz:
http://arxiv.org/abs/2403.10883
Autor:
Hong, Lingyi, Yan, Shilin, Zhang, Renrui, Li, Wanyun, Zhou, Xinyu, Guo, Pinxue, Jiang, Kaixun, Chen, Yiting, Li, Jinglun, Chen, Zhaoyu, Zhang, Wenqiang
Visual object tracking aims to localize the target object of each frame based on its initial appearance in the first frame. Depending on the input modility, tracking tasks can be divided into RGB tracking and RGB+X (e.g. RGB+N, and RGB+D) tracking. D
Externí odkaz:
http://arxiv.org/abs/2403.09634
Autor:
Chen, Zhaoyu, Shan, Zhengyang, Chang, Jingwen, Jiang, Kaixun, Yang, Dingkang, Cheng, Yiting, Zhang, Wenqiang
Semantic segmentation is a fundamental visual task that finds extensive deployment in applications with security-sensitive considerations. Nonetheless, recent work illustrates the adversarial vulnerability of semantic segmentation models to white-box
Externí odkaz:
http://arxiv.org/abs/2402.01220
Face forgery generation technologies generate vivid faces, which have raised public concerns about security and privacy. Many intelligent systems, such as electronic payment and identity verification, rely on face forgery detection. Although face for
Externí odkaz:
http://arxiv.org/abs/2310.12017
Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to deceive human perception and dee
Externí odkaz:
http://arxiv.org/abs/2305.10665