Zobrazeno 1 - 10
of 328
pro vyhledávání: '"Zhang, ZhenLiang"'
Autor:
Cheng, Daixuan, Huang, Shaohan, Zhu, Ziyu, Zhang, Xintong, Zhao, Wayne Xin, Luan, Zhongzhi, Dai, Bo, Zhang, Zhenliang
Recent years have witnessed the rapid development of general multimodal large language models (MLLMs). However, adapting general MLLMs to specific domains, such as scientific fields and industrial applications, remains less explored. This paper syste
Externí odkaz:
http://arxiv.org/abs/2411.19930
Human Action Recognition (HAR) is a very crucial task in computer vision. It helps to carry out a series of downstream tasks, like understanding human behaviors. Due to the complexity of human behaviors, many highly valuable behaviors are not yet enc
Externí odkaz:
http://arxiv.org/abs/2408.13463
Human-computer symbiosis is a crucial direction for the development of artificial intelligence. As intelligent systems become increasingly prevalent in our work and personal lives, it is important to develop strategies to support users across physica
Externí odkaz:
http://arxiv.org/abs/2403.18331
Autor:
Zhang, Zhenliang, Zhang, Zeyu, Jiao, Ziyuan, Su, Yao, Liu, Hangxin, Wang, Wei, Zhu, Song-Chun
Artificial intelligence (AI) has revolutionized human cognitive abilities and facilitated the development of new AI entities capable of interacting with humans in both physical and virtual environments. Despite the existence of virtual reality, mixed
Externí odkaz:
http://arxiv.org/abs/2401.15132
We introduce Bongard-OpenWorld, a new benchmark for evaluating real-world few-shot reasoning for machine vision. It originates from the classical Bongard Problems (BPs): Given two sets of images (positive and negative), the model needs to identify th
Externí odkaz:
http://arxiv.org/abs/2310.10207
Autor:
Liu, Hangxin, Zhang, Zeyu, Jiao, Ziyuan, Zhang, Zhenliang, Li, Minchen, Jiang, Chenfanfu, Zhu, Yixin, Zhu, Song-Chun
In this work, we present a reconfigurable data glove design to capture different modes of human hand-object interactions, which are critical in training embodied artificial intelligence (AI) agents for fine manipulation tasks. To achieve various down
Externí odkaz:
http://arxiv.org/abs/2301.05821
Publikováno v:
In Pattern Recognition November 2024 155
Publikováno v:
In Journal of Mathematical Analysis and Applications 1 July 2024 535(1)
Publikováno v:
Applied and Computational Harmonic Analysis, 60 (2022): 242-266
We study zeroth-order optimization for convex functions where we further assume that function evaluations are unavailable. Instead, one only has access to a $\textit{comparison oracle}$, which given two points $x$ and $y$ returns a single bit of info
Externí odkaz:
http://arxiv.org/abs/2010.02479
Publikováno v:
SIAM Journal on Optimization 32, no. 2 (2022): 687-714
We consider the problem of minimizing a high-dimensional objective function, which may include a regularization term, using (possibly noisy) evaluations of the function. Such optimization is also called derivative-free, zeroth-order, or black-box opt
Externí odkaz:
http://arxiv.org/abs/2003.13001