Zobrazeno 1 - 10
of 317
pro vyhledávání: '"Shi, DaChuan"'
Autor:
Fu, Yonggan, Yu, Zhongzhi, Li, Junwei, Qian, Jiayi, Zhang, Yongan, Yuan, Xiangchi, Shi, Dachuan, Yakunin, Roman, Lin, Yingyan Celine
Motivated by the transformative capabilities of large language models (LLMs) across various natural language tasks, there has been a growing demand to deploy these models effectively across diverse real-world applications and platforms. However, the
Externí odkaz:
http://arxiv.org/abs/2411.10606
Image-text training like CLIP has dominated the pretraining of vision foundation models in recent years. Subsequent efforts have been made to introduce region-level visual learning into CLIP's pretraining but face scalability challenges due to the la
Externí odkaz:
http://arxiv.org/abs/2401.10222
Recent vision-language models have achieved tremendous advances. However, their computational costs are also escalating dramatically, making model acceleration exceedingly critical. To pursue more efficient vision-language Transformers, this paper in
Externí odkaz:
http://arxiv.org/abs/2305.17455
Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities. Moreover, increasingly heavier models, \textit{e}.\textit{g}., Transformers, have attracted the attention of
Externí odkaz:
http://arxiv.org/abs/2301.13741
Knowledge distillation has been applied to various tasks successfully. The current distillation algorithm usually improves students' performance by imitating the output of the teacher. This paper shows that teachers can also improve students' represe
Externí odkaz:
http://arxiv.org/abs/2205.01529
Publikováno v:
In Journal of Manufacturing Systems December 2024 77:678-696
Publikováno v:
In Building and Environment 1 January 2025 267 Part B
Publikováno v:
In Science of the Total Environment 15 April 2024 921
Autor:
Bu, Yaohua, Ma, Tianyi, Li, Weijun, Zhou, Hang, Jia, Jia, Chen, Shengqi, Xu, Kaiyuan, Shi, Dachuan, Wu, Haozhe, Yang, Zhihan, Li, Kun, Wu, Zhiyong, Shi, Yuanchun, Lu, Xiaobo, Liu, Ziwei
Second language (L2) English learners often find it difficult to improve their pronunciations due to the lack of expressive and personalized corrective feedback. In this paper, we present Pronunciation Teacher (PTeacher), a Computer-Aided Pronunciati
Externí odkaz:
http://arxiv.org/abs/2105.05182
Autor:
Shi, Dachuan, Sabanovic, Eldar, Rizzetto, Luca, Skrickij, Viktor, Oliverio, Roberto, Kaviani, Nadia, Ye, Yunguang, Bureika, Gintautas, Ricci, Stefano, Hecht, Markus
In the application of computer-vision based displacement measurement, an optical target is usually required to prove the reference. In the case that the optical target cannot be attached to the measuring objective, edge detection, feature matching an
Externí odkaz:
http://arxiv.org/abs/2101.06702