Zobrazeno 1 - 10
of 347
pro vyhledávání: '"Yang, Kunlin"'
Autor:
Shi, Pengyuan, Wang, Xiaoyu, Zhang, Lihao, Song, Wenqin, Yang, Kunlin, Wang, Shuxi, Zhang, Ruisheng, Zhang, Liangliang, Taniguchi, Takashi, Watanabe, Kenji, Yang, Sen, Zhang, Lei, Wang, Lei, Shi, Wu, Pan, Jie, Wang, Zhe
Magnetoresistance (MR) oscillations serve as a hallmark of intrinsic quantum behavior, traditionally observed only in conducting systems. Here we report the discovery of MR oscillations in an insulating system, the vertical junctions of CrPS$_4$ whic
Externí odkaz:
http://arxiv.org/abs/2410.18258
Autor:
Zhao, Wayne Xin, He, Gaole, Yang, Kunlin, Dou, Hongjian, Huang, Jin, Ouyang, Siqi, Wen, Ji-Rong
Publikováno v:
Data Intelligence, Vol 1, Iss 2, Pp 121-136 (2019)
To develop a knowledge-aware recommender system, a key issue is how to obtain rich and structured knowledge base (KB) information for recommender system (RS) items. Existing data sets or methods either use side information from original RSs (containi
Externí odkaz:
https://doaj.org/article/1136ab1dd74e447b9339c4a4b942f25c
Autor:
Bai, Sikai, Li, Shuaicheng, Zhuang, Weiming, Zhang, Jie, Guo, Song, Yang, Kunlin, Hou, Jun, Zhang, Shuai, Gao, Junyu, Yi, Shuai
Publikováno v:
The 38th Annual AAAI Conference on Artificial Intelligence, 2024
Federated learning has become a popular method to learn from decentralized heterogeneous data. Federated semi-supervised learning (FSSL) emerges to train models from a small fraction of labeled data due to label scarcity on decentralized clients. Exi
Externí odkaz:
http://arxiv.org/abs/2307.05358
Video highlight detection is a crucial yet challenging problem that aims to identify the interesting moments in untrimmed videos. The key to this task lies in effective video representations that jointly pursue two goals, \textit{i.e.}, cross-modal r
Externí odkaz:
http://arxiv.org/abs/2206.10157
It has been found that temporal action proposal generation, which aims to discover the temporal action instances within the range of the start and end frames in the untrimmed videos, can largely benefit from proper temporal and semantic context explo
Externí odkaz:
http://arxiv.org/abs/2206.10095
Knowledge distillation (KD) has shown very promising capabilities in transferring learning representations from large models (teachers) to small models (students). However, as the capacity gap between students and teachers becomes larger, existing KD
Externí odkaz:
http://arxiv.org/abs/2206.06067
Publikováno v:
In Atmospheric Research 15 August 2024 306
Group activity recognition is a crucial yet challenging problem, whose core lies in fully exploring spatial-temporal interactions among individuals and generating reasonable group representations. However, previous methods either model spatial and te
Externí odkaz:
http://arxiv.org/abs/2108.12630
Autor:
Li, Haopeng, Liu, Lingbo, Yang, Kunlin, Liu, Shinan, Gao, Junyu, Zhao, Bin, Zhang, Rui, Hou, Jun
Video crowd localization is a crucial yet challenging task, which aims to estimate exact locations of human heads in the given crowded videos. To model spatial-temporal dependencies of human mobility, we propose a multi-focus Gaussian neighborhood at
Externí odkaz:
http://arxiv.org/abs/2107.08645
Neural architecture search, which aims to automatically search for architectures (e.g., convolution, max pooling) of neural networks that maximize validation performance, has achieved remarkable progress recently. In many application scenarios, sever
Externí odkaz:
http://arxiv.org/abs/2006.10559