Yahoo Search Búsqueda en la Web

Resultado de búsqueda

  1. Reality is wrong. Dreams are for real. · Experience: AlixPartners · Education: Carnegie Mellon University · Location: Pittsburgh · 410 connections on LinkedIn. View Jiaxiang Wu, CPA’s ...

  2. Quantized-CNN for Mobile Devices. Quantized-CNN is a novel framework of convolutional neural network (CNN) with simultaneous computation acceleration and model compression in the test-phase. Mobile devices can perform efficient on-site image classification via our Quantized-CNN, with only negligible loss in accuracy.

  3. Jiaxiang Wu 0002 — Youtu Lab, Tencent, Shanghai, China (and 1 more); Jiaxiang Wu 0003 — Nanyang Technological University, Singapore; Jiaxiang Wu 0004 — Huaqiao University, Quanzhou, China; Jiaxiang Wu 0005 — Beijing Institute of Technology, School of Automation, China; Jiaxiang Wu 0006 — Chang'an University, MOE Key Laboratory of Road Construction Technology and Equipment, China

  4. Jiaxiang Wu. XVERSE. Verified email at xverse.cn. Machine Learning Computer Vision Bioinformatics. Articles Cited by Public access Co-authors. Title. Sort. ... J Wu, Y Zhang, H Bai, H Zhong, J Hou, W Liu, W Huang, J Huang. 28: 2018: The system can't perform the operation now. Try again later.

  5. Address: Hall for Discovery and Learning Research 207 S. Martin Juschke Drive West Lafayette, IN 47907

  6. Jiaxiang County (simplified Chinese: 嘉祥县; traditional Chinese: 嘉祥縣; pinyin: Jiāxiáng Xiàn) is a county in the southwest of Shandong province, People's Republic of China. It is under the administration of Jining City.. The population was 871,920 in 2011. The cultural heritage site of the Carved Stones in the Tombs of the Wu Family is in this county.

  7. Shuaicheng Niu* 1 2 Jiaxiang Wu* 3 Yifan Zhang* 4 Yaofo Chen1 Shijian Zheng1 Peilin Zhao3 Mingkui Tan1 5 Abstract Test-time adaptation (TTA) seeks to tackle po-tential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly impor-tant for deep models when the test ...