Zobrazeno 1 - 10
of 2 086
pro vyhledávání: '"Zhang, Weiming"'
Image steganography is a technique to conceal secret messages within digital images. Steganalysis, on the contrary, aims to detect the presence of secret messages within images. Recently, deep-learning-based steganalysis methods have achieved excelle
Externí odkaz:
http://arxiv.org/abs/2409.04968
Autor:
Tang, Kunsheng, Zhou, Wenbo, Zhang, Jie, Liu, Aishan, Deng, Gelei, Li, Shuai, Qi, Peigui, Zhang, Weiming, Zhang, Tianwei, Yu, Nenghai
Large language models (LLMs) have exhibited remarkable capabilities in natural language generation, but they have also been observed to magnify societal biases, particularly those related to gender. In response to this issue, several benchmarks have
Externí odkaz:
http://arxiv.org/abs/2408.12494
This paper presents GoodSAM++, a novel framework utilizing the powerful zero-shot instance segmentation capability of SAM (i.e., teacher) to learn a compact panoramic semantic segmentation model, i.e., student, without requiring any labeled data. Goo
Externí odkaz:
http://arxiv.org/abs/2408.09115
In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerable to jailbreak attacks, where adversaries can induce the generation of
Externí odkaz:
http://arxiv.org/abs/2408.08924
Autor:
Fang, Ziyuan, Zhao, Hanqing, Wei, Tianyi, Zhou, Wenbo, Wan, Ming, Wang, Zhanyi, Zhang, Weiming, Yu, Nenghai
Previous deepfake detection methods mostly depend on low-level textural features vulnerable to perturbations and fall short of detecting unseen forgery methods. In contrast, high-level semantic features are less susceptible to perturbations and not l
Externí odkaz:
http://arxiv.org/abs/2407.19079
Autor:
Sun, Ke, Cao, Jian, Wang, Qi, Tian, Linrui, Zhang, Xindi, Zhuo, Lian, Zhang, Bang, Bo, Liefeng, Zhou, Wenbo, Zhang, Weiming, Gao, Daiheng
Virtual Try-On (VTON) has become a transformative technology, empowering users to experiment with fashion without ever having to physically try on clothing. However, existing methods often struggle with generating high-fidelity and detail-consistent
Externí odkaz:
http://arxiv.org/abs/2407.16224
Autor:
Xia, Deguo, Zhang, Weiming, Liu, Xiyan, Zhang, Wei, Gong, Chenting, Huang, Jizhou, Yang, Mengmeng, Yang, Diange
Generating city-scale lane-level maps faces significant challenges due to the intricate urban environments, such as blurred or absent lane markings. Additionally, a standard lane-level map requires a comprehensive organization of lane groupings, enco
Externí odkaz:
http://arxiv.org/abs/2406.14255
Recently, Depth Anything Model (DAM) - a type of depth foundation model - reveals impressive zero-shot capacity for diverse perspective images. Despite its success, it remains an open question regarding DAM's performance on 360 images that enjoy a la
Externí odkaz:
http://arxiv.org/abs/2406.13378
Autor:
Zhou, Xinghui, Zhou, Wenbo, Wei, Tianyi, Chen, Shen, Yao, Taiping, Ding, Shouhong, Zhang, Weiming, Yu, Nenghai
Face swapping has become a prominent research area in computer vision and image processing due to rapid technological advancements. The metric of measuring the quality in most face swapping methods relies on several distances between the manipulated
Externí odkaz:
http://arxiv.org/abs/2406.01884
Autor:
Feng, Weitao, Zhou, Wenbo, He, Jiyan, Zhang, Jie, Wei, Tianyi, Li, Guanlin, Zhang, Tianwei, Zhang, Weiming, Yu, Nenghai
Diffusion models have achieved remarkable success in generating high-quality images. Recently, the open-source models represented by Stable Diffusion (SD) are thriving and are accessible for customization, giving rise to a vibrant community of creato
Externí odkaz:
http://arxiv.org/abs/2405.11135