Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Bojin Zhuang"'
Publikováno v:
Neurocomputing. 363:35-45
Face datasets often exhibit highly-skewed class distribution, i.e., rich classes contain a plenty amount of instances, while only few images belong to poor classes. To mitigate this issue, we explore deep class-skewed learning from two aspects in thi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fab29ebc9cc7ae574c3fa339e6e97df0
https://doi.org/10.1016/j.neucom.2019.04.085
https://doi.org/10.1016/j.neucom.2019.04.085
Autor:
Li Du, Zixuan Wang, Nikolaos V. Boulgouris, Fei Su, Bojin Zhuang, Leiquan Wang, Zhicheng Zhao
Publikováno v:
IEEE Transactions on Vehicular Technology. 68:4249-4261
Predicting the state of dynamic objects in a real traffic environment is a key issue in autonomous driving vehicles. Various approaches have been proposed to learn the dynamics from visual observations with static background. However, minimal researc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::72738c14ff16873b9fac7b426846482e
https://doi.org/10.1109/tvt.2019.2905598
https://doi.org/10.1109/tvt.2019.2905598
Autor:
Yue Li, Pan Deng, Ruan Xiaowen, Wen He, Yuqi Liu, Xu Liang, Xuying Zhang, Jiaying Xu, Xie Jingwen, Na Li, Yifei Guo, Shan Yang, Jin Xiaohui, He Huang, Dongsheng Yuan, Xiao Jing, Heng Li, Mei Han, Yiyi Hu, Jiang Qian, Yingnan Wu, Zhenjie Cao, Bojin Zhuang, Dongyan Long, Li Xian
Publikováno v:
The Lancet Regional Health: Western Pacific
Background A universally applicable approach that provides standard HALE measurements for different regions has yet to be developed because of the difficulties of health information collection. In this study, we developed a natural language processin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6505c85f44ae96d90378c2c3815b1d15
http://europepmc.org/articles/PMC8315391
http://europepmc.org/articles/PMC8315391
Generating Reasonable Legal Text through the Combination of Language Modeling and Question Answering
Autor:
Shaojun Wang, Xianfeng Liao, Bojin Zhuang, Zhiqiang Xie, Xiao Jing, Jiang Qian, Weijing Huang
Publikováno v:
IJCAI
Due to the improvement of Language Modeling, the emerging NLP assistant tools aiming for text generation greatly reduce the human workload on writing documents. However, the generation of legal text faces greater challenges than ordinary texts becaus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a520e05ed7b444202bc429eb7bff4975
https://doi.org/10.24963/ijcai.2020/510
https://doi.org/10.24963/ijcai.2020/510
Publikováno v:
VCIP
In the field of autonomous driving, training an agent to watch and think similar to human drivers is an efficient way to solve self-driving problems. Inspired by NVIDIA’s frame-level command generation task [2] and the discovery of humans memory ca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c1003f754736ecb33603e1306790a7b
https://doi.org/10.1109/vcip47243.2019.8965824
https://doi.org/10.1109/vcip47243.2019.8965824
Autor:
Deng Liming, Xiao Jing, Hangming Liang, Bojin Zhuang, Zhiqiang Xie, Hui Chen, Shaojun Wang, Wang Jie
Publikováno v:
AAAI
Owing to its unique literal and aesthetical characteristics, automatic generation of Chinese poetry is still challenging in Artificial Intelligence, which can hardly be straightforwardly realized by end-to-end methods. In this paper, we propose a nov
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::61624af3187fc8a2ebae308c67636078
http://arxiv.org/abs/1911.13182
http://arxiv.org/abs/1911.13182
Publikováno v:
ICIP
Due to the large number and huge diversity of attributes, pedestrian attribute recognition in video surveillance scenarios is a challenging task in the field of computer vision. Different from most previous works which only focus on extremely imbalan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6157ed2600ceb81cef684764c1e78eeb
https://doi.org/10.1109/icip.2019.8803227
https://doi.org/10.1109/icip.2019.8803227
Publikováno v:
PRICAI 2019: Trends in Artificial Intelligence ISBN: 9783030298937
PRICAI (3)
PRICAI (3)
This paper presents a novel, syllable-structured Chinese lyrics generation model given a piece of original melody. Most previously reported lyrics generation models fail to include the relationship between lyrics and melody. In this work, we propose
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e7fb703788ee0365c4372e6354c1481e
https://doi.org/10.1007/978-3-030-29894-4_20
https://doi.org/10.1007/978-3-030-29894-4_20
Publikováno v:
PRICAI 2019: Trends in Artificial Intelligence ISBN: 9783030299071
PRICAI (1)
PRICAI (1)
As one of the quintessence of Chinese traditional culture, couplet compromises two syntactically symmetric clauses equal in length, namely, an antecedent and subsequent clause. Moreover, corresponding characters and phrases at the same position of th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5f86b360c2e0ae6b713cbef9dc8643cb
https://doi.org/10.1007/978-3-030-29908-8_25
https://doi.org/10.1007/978-3-030-29908-8_25
Publikováno v:
PRICAI 2019: Trends in Artificial Intelligence ISBN: 9783030298937
PRICAI (3)
PRICAI (3)
In this paper, we comprehensively study on context-aware generation of Chinese song lyrics. Conventional text generative models generate a sequence or sentence word by word, failing to consider the contextual relationship between sentences. Taking ac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3afd9183e30f5a142f76e45e031915bd
https://doi.org/10.1007/978-3-030-29894-4_23
https://doi.org/10.1007/978-3-030-29894-4_23