Zobrazeno 1 - 10
of 29 166
pro vyhledávání: '"An, Jintao"'
Autor:
Cai, Xudong, Wang, Yongcai, Fan, Zhaoxin, Haoran, Deng, Wang, Shuo, Li, Wanting, Li, Deying, Luo, Lun, Wang, Minhang, Xu, Jintao
Photo-realistic scene reconstruction from sparse-view, uncalibrated images is highly required in practice. Although some successes have been made, existing methods are either Sparse-View but require accurate camera parameters (i.e., intrinsic and ext
Externí odkaz:
http://arxiv.org/abs/2412.19518
We study $\mathcal I$-maximal eventually different families of functions from the set of natural numbers into itself where $\mathcal I$ is an arbitrary ideal on the set of natural numbers that includes the ideal of all finite sets $\mathrm{fin}$. We
Externí odkaz:
http://arxiv.org/abs/2412.18987
In this paper, we study a system in which a sensor forwards status updates to a receiver through an error-prone channel, while the receiver sends the transmission results back to the sensor via a reliable channel. Both channels are subject to random
Externí odkaz:
http://arxiv.org/abs/2412.18119
Partial label learning (PLL) is a complicated weakly supervised multi-classification task compounded by class imbalance. Currently, existing methods only rely on inter-class pseudo-labeling from inter-class features, often overlooking the significant
Externí odkaz:
http://arxiv.org/abs/2412.14561
Autor:
Li, Jintao, Qian, Shuaijie
We consider the Merton's problem with proportional transaction costs. It is well-known that the optimal investment strategy is characterized by two trading boundaries, i.e., the buy boundary and the sell boundary, between which is the no-trading regi
Externí odkaz:
http://arxiv.org/abs/2412.13669
Contrastive Language-Image Pretraining (CLIP) has been widely used in vision tasks. Notably, CLIP has demonstrated promising performance in few-shot learning (FSL). However, existing CLIP-based methods in training-free FSL (i.e., without the requirem
Externí odkaz:
http://arxiv.org/abs/2412.11375
Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving videos, high-resolution images, or lengthy image-text documents. In our
Externí odkaz:
http://arxiv.org/abs/2412.09616
Autor:
Wang, Tianyang, Bi, Ziqian, Zhang, Yichao, Liu, Ming, Hsieh, Weiche, Feng, Pohsun, Yan, Lawrence K. Q., Wen, Yizhu, Peng, Benji, Liu, Junyu, Chen, Keyu, Zhang, Sen, Li, Ming, Jiang, Chuanqi, Song, Xinyuan, Yang, Junjie, Jing, Bowen, Ren, Jintao, Song, Junhao, Tseng, Hong-Ming, Chen, Silin, Wang, Yunze, Liang, Chia Xin, Xu, Jiawei, Pan, Xuanhe, Wang, Jinlang, Niu, Qian
Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms and impact o
Externí odkaz:
http://arxiv.org/abs/2412.08969
This study investigates the development dilemma of ride-sharing services using real-world mobility datasets from nine cities and calibrated customers' price and detour elasticity. Through massive numerical experiments, this study reveals that while r
Externí odkaz:
http://arxiv.org/abs/2412.08801
Animating human-scene interactions such as pick-and-place tasks in cluttered, complex layouts is a challenging task, with objects of a wide variation of geometries and articulation under scenarios with various obstacles. The main difficulty lies in t
Externí odkaz:
http://arxiv.org/abs/2412.06702