Zobrazeno 1 - 10
of 52 148
pro vyhledávání: '"Li-Xiang An"'
Autor:
Li, Yuxuan, Li, Xiang, Li, Yunheng, Zhang, Yicheng, Dai, Yimian, Hou, Qibin, Cheng, Ming-Ming, Yang, Jian
With the rapid advancement of remote sensing technology, high-resolution multi-modal imagery is now more widely accessible. Conventional Object detection models are trained on a single dataset, often restricted to a specific imaging modality and anno
Externí odkaz:
http://arxiv.org/abs/2412.20665
Autor:
Sun, Wenzhang, Li, Xiang, Di, Donglin, Liang, Zhuding, Zhang, Qiyuan, Li, Hao, Chen, Wei, Cui, Jianxun
Recently, animating portrait images using audio input is a popular task. Creating lifelike talking head videos requires flexible and natural movements, including facial and head dynamics, camera motion, realistic light and shadow effects. Existing me
Externí odkaz:
http://arxiv.org/abs/2412.19860
Column Generation (CG) is an effective and iterative algorithm to solve large-scale linear programs (LP). During each CG iteration, new columns are added to improve the solution of the LP. Typically, CG greedily selects one column with the most negat
Externí odkaz:
http://arxiv.org/abs/2412.19066
Autor:
Ge, Kuangzhi, Chen, Lingjun, Zhang, Kevin, Luo, Yulin, Shi, Tianyu, Fan, Liaoyuan, Li, Xiang, Wang, Guanqun, Zhang, Shanghang
Recently, significant advances have been made in Video Large Language Models (Video LLMs) in both academia and industry. However, methods to evaluate and benchmark the performance of different Video LLMs, especially their fine-grained, temporal visua
Externí odkaz:
http://arxiv.org/abs/2412.17637
In two-time-scale stochastic approximation (SA), two iterates are updated at different rates, governed by distinct step sizes, with each update influencing the other. Previous studies have demonstrated that the convergence rates of the error terms fo
Externí odkaz:
http://arxiv.org/abs/2412.17070
Long-term time-series forecasting is essential for planning and decision-making in economics, energy, and transportation, where long foresight is required. To obtain such long foresight, models must be both efficient and effective in processing long
Externí odkaz:
http://arxiv.org/abs/2412.16572
In this paper, we will prove some rigidity theorems for blow up limits to Type II singularities of Lagrangian mean curvature flow with zero Maslov class or almost calibrated Lagrangian mean curvature flows, especially for Lagrangian translating solit
Externí odkaz:
http://arxiv.org/abs/2412.15880
Autor:
Li, Wenqiao, Zheng, Bozhong, Xu, Xiaohao, Gan, Jinye, Lu, Fading, Li, Xiang, Ni, Na, Tian, Zheng, Huang, Xiaonan, Gao, Shenghua, Wu, Yingna
Object anomaly detection is essential for industrial quality inspection, yet traditional single-sensor methods face critical limitations. They fail to capture the wide range of anomaly types, as single sensors are often constrained to either external
Externí odkaz:
http://arxiv.org/abs/2412.14592
Strong correlation brings a rich array of emergent phenomena, as well as a daunting challenge to theoretical physics study. In condensed matter physics, the fractional quantum Hall effect is a prominent example of strong correlation, with Landau leve
Externí odkaz:
http://arxiv.org/abs/2412.14795
Autor:
Wu, Jiayi, Cai, Hengyi, Yan, Lingyong, Sun, Hao, Li, Xiang, Wang, Shuaiqiang, Yin, Dawei, Gao, Ming
The emergence of Retrieval-augmented generation (RAG) has alleviated the issues of outdated and hallucinatory content in the generation of large language models (LLMs), yet it still reveals numerous limitations. When a general-purpose LLM serves as t
Externí odkaz:
http://arxiv.org/abs/2412.14510