Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Yingya Zhang"'
Publikováno v:
ISPRS International Journal of Geo-Information, Vol 5, Iss 5, p 71 (2016)
Traffic congestion clustering judgment is a fundamental problem in the study of traffic jam warning. However, it is not satisfactory to judge traffic congestion degrees using only vehicle speed. In this paper, we collect traffic flow information with
Externí odkaz:
https://doaj.org/article/86f40e3ebfe8483bbed914db9fea7ce5
Publikováno v:
Proceedings of the VLDB Endowment. 15:1-10
Thanks to the popularity of GPU and the growth of its computational power, more and more deep learning tasks, such as face recognition, image retrieval and word embedding, can take advantage of extreme classification to improve accuracy. However, it
Autor:
Qianyuan Ran, Xiaowei Jiang, Yingya Zhang, Shanyuan Gao, Pengcheng Li, Heng Pan, Lingbo Tang, Liuyihan Song, Jie Zhang, Pan Pan, Fei Feng, Hao Li, Yong Li, Shaochuang Wang, Zhisheng Xia, Guohui Wang, Jianbo Dong, Xin Long, Zheng Cao, Yiqun Guo
Publikováno v:
IEEE Micro. 41:85-92
Distributed systems have been widely adopted for deep neural networks model training. However, the scalability of distributed training systems is largely bounded by the communication cost. We design a highly efficient collective communication library
Autor:
Xiangzeng Zhou, Yingya Zhang, Wang Bin, Yu Liu, Ming Li, Pan Pan, Lianghua Huang, Ansheng You, Xu Yinghui
Publikováno v:
ACM Multimedia
Videos grow to be one of the largest mediums on the Internet. E-commerce platforms like Alibaba need to process millions of video data across multimedia (e.g., visual, audio, image, and text) and on a variety of tasks (e.g., retrieval, tagging, and s
Publikováno v:
KDD
In contrast to regular convolutions with local receptive fields, non-local operations have widely proven an effective method for modeling long-range dependencies. Although lots of prior works have been proposed, prohibitive computation and GPU memory
In the last decades, extreme classification has become an essential topic for deep learning. It has achieved great success in many areas, especially in computer vision and natural language processing (NLP). However, it is very challenging to train a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7679f55cee7fee693ebe3730bce11ba0
http://arxiv.org/abs/2102.06025
http://arxiv.org/abs/2102.06025
This paper introduces the large scale visual search algorithm and system infrastructure at Alibaba. The following challenges are discussed under the E-commercial circumstance at Alibaba (a) how to handle heterogeneous image data and bridge the gap be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eeba3096f9e84b6d355360285bfb9842
http://arxiv.org/abs/2102.04674
http://arxiv.org/abs/2102.04674
Publikováno v:
Chemical Communications. 54:3775-3778
A self-assembly technology allows metal-organic framework materials to constitute a honeycomb internal structure while being shaped into millimeter-scale spheres. The ZIF-8 load is up to 83 wt% through solidification of chitosan (CS). This approach c
Publikováno v:
Materials Letters. 206:233-236
Zeolitic imidazolate framework (ZIF-8) has attracted extensive application in gas adsorption, membrane separation and catalysis. It has been demonstrated that the morphology is crucial for the physical and chemical properties. In this work, ZIF-8 cry
Autor:
Yinghui Xu, Yingya Zhang, Kang Zhao, Yanhao Zhang, Pan Pan, Rong Jin, Yun Zheng, Changxu Wang
Publikováno v:
Proceedings of the 28th ACM International Conference on Information and Knowledge Management.
Graph-based approximate nearest neighbor search has attracted more and more attentions due to its online search advantages. Numbers of methods studying the enhancement of speed and recall have been put forward. However, few of them focus on the effic