Zobrazeno 1 - 10
of 532
pro vyhledávání: '"Ma, Siqi"'
Autor:
Lin, Xinna, Ma, Siqi, Shan, Junjie, Zhang, Xiaojing, Hu, Shell Xu, Guo, Tiannan, Li, Stan Z., Yu, Kaicheng
Pursuing artificial intelligence for biomedical science, a.k.a. AI Scientist, draws increasing attention, where one common approach is to build a copilot agent driven by Large Language Models (LLMs). However, to evaluate such systems, people either r
Externí odkaz:
http://arxiv.org/abs/2407.00466
Autor:
Tan, Cheng, Lyu, Dongxin, Li, Siyuan, Gao, Zhangyang, Wei, Jingxuan, Ma, Siqi, Liu, Zicheng, Li, Stan Z.
Large Language Models (LLMs) have demonstrated wide-ranging applications across various fields and have shown significant potential in the academic peer-review process. However, existing applications are primarily limited to static review generation
Externí odkaz:
http://arxiv.org/abs/2406.05688
Adversarial training serves as one of the most popular and effective methods to defend against adversarial perturbations. However, most defense mechanisms only consider a single type of perturbation while various attack methods might be adopted to pe
Externí odkaz:
http://arxiv.org/abs/2309.16207
Deep neural networks (DNNs) have achieved state-of-the-art performance on face recognition (FR) tasks in the last decade. In real scenarios, the deployment of DNNs requires taking various face accessories into consideration, like glasses, hats, and m
Externí odkaz:
http://arxiv.org/abs/2309.09480
Autor:
Liu, Zian, Zhang, Zhi, Ma, Siqi, Liu, Dongxi, Zhang, Jun, Chen, Chao, Liu, Shigang, Ahmed, Muhammad Ejaz, Xiang, Yang
Binary similarity detection is a critical technique that has been applied in many real-world scenarios where source code is not available, e.g., bug search, malware analysis, and code plagiarism detection. Existing works are ineffective in detecting
Externí odkaz:
http://arxiv.org/abs/2308.01463
Autor:
Lu, Yawen, Wang, Qifan, Ma, Siqi, Geng, Tong, Chen, Yingjie Victor, Chen, Huaijin, Liu, Dongfang
Optical flow is an indispensable building block for various important computer vision tasks, including motion estimation, object tracking, and disparity measurement. In this work, we propose TransFlow, a pure transformer architecture for optical flow
Externí odkaz:
http://arxiv.org/abs/2304.11523
Facial forgery detection is a crucial but extremely challenging topic, with the fast development of forgery techniques making the synthetic artefact highly indistinguishable. Prior works show that by mining both spatial and frequency information the
Externí odkaz:
http://arxiv.org/abs/2302.10437
Forgery facial images and videos have increased the concern of digital security. It leads to the significant development of detecting forgery data recently. However, the data, especially the videos published on the Internet, are usually compressed wi
Externí odkaz:
http://arxiv.org/abs/2302.06183
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology (2022)
Instance segmentation in videos, which aims to segment and track multiple objects in video frames, has garnered a flurry of research attention in recent years. In this paper, we present a novel weakly supervised framework with \textbf{S}patio-\textbf
Externí odkaz:
http://arxiv.org/abs/2212.07592
Modern smart TVs often communicate with their remote controls (including those smart phone simulated ones) using multiple wireless channels (e.g., Infrared, Bluetooth, and Wi-Fi). However, this multi-channel remote control communication introduces a
Externí odkaz:
http://arxiv.org/abs/2210.03014