Zobrazeno 1 - 10
of 4 366
pro vyhledávání: '"Shu, Tao"'
Multi-view image compression is vital for 3D-related applications. To effectively model correlations between views, existing methods typically predict disparity between two views on a 2D plane, which works well for small disparities, such as in stere
Externí odkaz:
http://arxiv.org/abs/2409.04013
Autor:
Xu, Yiran, Zhong, Haoxiang, Wu, Kai, Li, Jialin, Liu, Yong, Wang, Chengjie, Xia, Shu-Tao, Liao, Hongen
Object detectors have shown outstanding performance on various public datasets. However, annotating a new dataset for a new task is usually unavoidable in real, since 1) a single existing dataset usually does not contain all object categories needed;
Externí odkaz:
http://arxiv.org/abs/2408.16247
Recently, image-to-3D approaches have significantly advanced the generation quality and speed of 3D assets based on large reconstruction models, particularly 3D Gaussian reconstruction models. Existing large 3D Gaussian models directly map 2D image t
Externí odkaz:
http://arxiv.org/abs/2408.10935
Model Inversion (MI) attacks aim to reconstruct privacy-sensitive training data from released models by utilizing output information, raising extensive concerns about the security of Deep Neural Networks (DNNs). Recent advances in generative adversar
Externí odkaz:
http://arxiv.org/abs/2407.13863
Transferable targeted adversarial attacks aim to mislead models into outputting adversary-specified predictions in black-box scenarios. Recent studies have introduced \textit{single-target} generative attacks that train a generator for each target cl
Externí odkaz:
http://arxiv.org/abs/2407.10179
The pre-trained point cloud model based on Masked Point Modeling (MPM) has exhibited substantial improvements across various tasks. However, two drawbacks hinder their practical application. Firstly, the positional embedding of masked patches in the
Externí odkaz:
http://arxiv.org/abs/2407.09344
Autor:
Zhang, Taolin, Bai, Jiawang, Lu, Zhihe, Lian, Dongze, Wang, Genping, Wang, Xinchao, Xia, Shu-Tao
Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new structures into the
Externí odkaz:
http://arxiv.org/abs/2407.06964
The advent of video-based Large Language Models (LLMs) has significantly enhanced video understanding. However, it has also raised some safety concerns regarding data protection, as videos can be more easily annotated, even without authorization. Thi
Externí odkaz:
http://arxiv.org/abs/2407.02411
Autor:
Peng, Yuang, Cui, Yuxin, Tang, Haomiao, Qi, Zekun, Dong, Runpei, Bai, Jing, Han, Chunrui, Ge, Zheng, Zhang, Xiangyu, Xia, Shu-Tao
Personalized image generation holds great promise in assisting humans in everyday work and life due to its impressive function in creatively generating personalized content. However, current evaluations either are automated but misalign with humans o
Externí odkaz:
http://arxiv.org/abs/2406.16855
Dataset distillation is an emerging dataset reduction method, which condenses large-scale datasets while maintaining task accuracy. Current methods have integrated parameterization techniques to boost synthetic dataset performance by shifting the opt
Externí odkaz:
http://arxiv.org/abs/2406.05704