Zobrazeno 1 - 10
of 199
pro vyhledávání: '"Jiafeng GUO"'
Autor:
Qingyao Ai, Ting Bai, Zhao Cao, Yi Chang, Jiawei Chen, Zhumin Chen, Zhiyong Cheng, Shoubin Dong, Zhicheng Dou, Fuli Feng, Shen Gao, Jiafeng Guo, Xiangnan He, Yanyan Lan, Chenliang Li, Yiqun Liu, Ziyu Lyu, Weizhi Ma, Jun Ma, Zhaochun Ren, Pengjie Ren, Zhiqiang Wang, Mingwen Wang, Ji-Rong Wen, Le Wu, Xin Xin, Jun Xu, Dawei Yin, Peng Zhang, Fan Zhang, Weinan Zhang, Min Zhang, Xiaofei Zhu
Publikováno v:
AI Open, Vol 4, Iss , Pp 80-90 (2023)
The research field of Information Retrieval (IR) has evolved significantly, expanding beyond traditional search to meet diverse user information needs. Recently, Large Language Models (LLMs) have demonstrated exceptional capabilities in text understa
Externí odkaz:
https://doaj.org/article/eb4eadd07c0a4203b546205d0388b406
Publikováno v:
Taiyuan Ligong Daxue xuebao, Vol 53, Iss 2, Pp 248-256 (2022)
We proposed Reinforced Dependency Graph for Aspect-based Sentiment Classification (RDGSC), a reinforced dependency graph model for aspect-based sentiment classification. In this framework, we train a policy network using deep reinforcement learning a
Externí odkaz:
https://doaj.org/article/5711b79847e74122b63d444a0d826705
Publikováno v:
Toxics, Vol 11, Iss 10, p 824 (2023)
An economical and effective method is still lacking for cadmium (Cd) toxicity reduction and food product safety improvement in soil–vegetable systems. Therefore, this study aimed to reduce the Cd toxicity to pak choi (Brassica campestris L.) by joi
Externí odkaz:
https://doaj.org/article/e6d045103afd47f7bd13dcdf8898ddea
Publikováno v:
IEEE Access, Vol 9, Pp 47380-47390 (2021)
The deep convolutional networks have a great success in vision classification tasks. For object detection, tasks are divided into two subtasks: localization and classification. The detectors scan the whole image to generate object proposals relying o
Externí odkaz:
https://doaj.org/article/5b4f209b0d5841fd9eb729151198605c
Publikováno v:
IEEE Access, Vol 9, Pp 62946-62955 (2021)
Recent years have witnessed rapid developments on computer vision, however, there are still challenges in detecting tiny objects in a large-scale background. The tiny objects knowledge become sparse and weak due to their tiny size, which makes the ti
Externí odkaz:
https://doaj.org/article/0178bc9a1b7148efb40742c6238fcc8f
Publikováno v:
IEEE Access, Vol 7, Pp 156848-156859 (2019)
Stochastic gradient descent(SGD) is the fundamental sequential method in training large scale machine learning models. To accelerate the training process, researchers proposed to use the asynchronous stochastic gradient descent (A-SGD) method in mode
Externí odkaz:
https://doaj.org/article/699670981a294949a6a0f6d6b8e9a23f
Publikováno v:
Information Sciences. 624:324-343
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::576cc08a3dc5a29cda57e38cc41ab658
https://doi.org/10.1016/j.ins.2022.10.025
https://doi.org/10.1016/j.ins.2022.10.025
Publikováno v:
Journal of Intelligent Information Systems. 60:97-117
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::993ca74eab3988737a77b0807ffdcfe1
https://doi.org/10.1007/s10844-022-00729-1
https://doi.org/10.1007/s10844-022-00729-1
Publikováno v:
Neurocomputing. 464:141-150
Microblog text is usually very short, thereby challenging existing sentiment classification methods by providing models with little context. Recently, historical user information has been widely used in many real-world applications, such as recommend
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1e8dc27a1c06d8d786800f2b257eaa94
https://doi.org/10.1016/j.neucom.2021.08.089
https://doi.org/10.1016/j.neucom.2021.08.089
Most existing visual reasoning tasks, such as CLEVR in VQA, ignore an important factor, i.e.~transformation. They are solely defined to test how well machines understand concepts and relations within static settings, like one image. Such \textbf{stat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::90680453e75384428a03fbf5393784a4
