Zobrazeno 1 - 10
of 4 714
pro vyhledávání: '"Deng, Xin"'
The discovery of drug-target interactions (DTIs) plays a crucial role in pharmaceutical development. The deep learning model achieves more accurate results in DTI prediction due to its ability to extract robust and expressive features from drug and t
Externí odkaz:
http://arxiv.org/abs/2404.10561
Existing quality enhancement methods for compressed images focus on aligning the enhancement domain with the raw domain to yield realistic images. However, these methods exhibit a pervasive enhancement bias towards the compression domain, inadvertent
Externí odkaz:
http://arxiv.org/abs/2402.17200
Autor:
Zhang, Wenyu, Deng, Xin, Jia, Baojun, Yu, Xingtong, Chen, Yifan, Ma, jin, Ding, Qing, Zhang, Xinming
Publikováno v:
ACM Multimedia 2023
Current Scene text image super-resolution approaches primarily focus on extracting robust features, acquiring text information, and complex training strategies to generate super-resolution images. However, the upsampling module, which is crucial in t
Externí odkaz:
http://arxiv.org/abs/2309.08919
Autor:
Jing, Junpeng, Li, Jiankun, Xiong, Pengfei, Liu, Jiangyu, Liu, Shuaicheng, Guo, Yichen, Deng, Xin, Xu, Mai, Jiang, Lai, Sigal, Leonid
Correlation based stereo matching has achieved outstanding performance, which pursues cost volume between two feature maps. Unfortunately, current methods with a fixed model do not work uniformly well across various datasets, greatly limiting their r
Externí odkaz:
http://arxiv.org/abs/2307.14071
Autor:
Mehta, Nikhil, Teruel, Milagro, Sanz, Patricio Figueroa, Deng, Xin, Awadallah, Ahmed Hassan, Kiseleva, Julia
Many approaches to Natural Language Processing (NLP) tasks often treat them as single-step problems, where an agent receives an instruction, executes it, and is evaluated based on the final outcome. However, human language is inherently interactive,
Externí odkaz:
http://arxiv.org/abs/2304.10750
Image defocus is inherent in the physics of image formation caused by the optical aberration of lenses, providing plentiful information on image quality. Unfortunately, existing quality enhancement approaches for compressed images neglect the inheren
Externí odkaz:
http://arxiv.org/abs/2211.10984
Publikováno v:
Geophysical Research Letters 49 (2022)
Subduction zones transport water into Earth's deep interior through slab subduction. Serpentine minerals, the primary hydration product of ultramafic peridotite, are abundant in most subduction zones. Characterization of their high-temperature elasti
Externí odkaz:
http://arxiv.org/abs/2209.09783
In point cloud analysis, point-based methods have rapidly developed in recent years. These methods have recently focused on concise MLP structures, such as PointNeXt, which have demonstrated competitiveness with Convolutional and Transformer structur
Externí odkaz:
http://arxiv.org/abs/2205.10528
Autor:
Ahmadvand, Ali, Arabzadeh, Negar, Kiseleva, Julia, Sanz, Patricio Figueroa, Deng, Xin, Jauhar, Sujay, Gamon, Michael, Agichtein, Eugene, Friend, Ned, Aniruddha
Current interactive systems with natural language interfaces lack the ability to understand a complex information-seeking request which expresses several implicit constraints at once, and there is no prior information about user preferences e.g.,"fin
Externí odkaz:
http://arxiv.org/abs/2205.00584