机构

• 计算技术研究所 [1]
• 长春光学精密机械与物... [1]
• 沈阳自动化研究所 [1]
• 软件研究所 [1]

采集方式

• OAI收割 [4]

内容类型

• 会议论文 [2]
• 期刊论文 [2]

发表日期

• 2023 [1]
• 2018 [1]
• 2010 [1]
• 2006 [1]

学科主题

筛选

浏览/检索结果: 共4条，第1-4条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择题名升序题名降序提交时间升序提交时间降序作者升序作者降序发表日期升序发表日期降序 Bi-STAN: bilinear spatial-temporal attention network for wearable human activity recognition 期刊论文  OAI收割 INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2023, 页码: 17 作者:  Gao, Chenlong;  Chen, Yiqiang;  Jiang, Xinlong;  Hu, Lisha;  Zhao, Zhicheng   |  收藏  |  浏览/下载：19/0  |  提交时间：2023/07/12 Human activity recognition  Spatial-temporal attention  Bilinear pooling  Low-redundancy   Online Similarity Learning for Big Data with Overfitting 期刊论文  OAI收割 IEEE Transactions on Big Data, 2018, 卷号: 4, 期号: 1, 页码: 78-89 作者:  Fan BJ(范保杰);  Zeng P(曾鹏);  Yu HB(于海斌);  Luo JB(罗杰波);  Cong Y(丛杨)   |  收藏  |  浏览/下载：43/0  |  提交时间：2017/12/21 online learning  similarity learning  low rank  sparse representation  feature selection  overfitting, redundancy   adaptive voice stream multicast over low-power wireless networks 会议论文  OAI收割 31st IEEE Real-Time Systems Symposium, RTSS 2010, San Diego, CA, 40850 Liqun Li; Guoliang Xing; Qi Han; Limin Sun 收藏  |  浏览/下载：21/0  |  提交时间：2011/03/31 ad hoc voice communication  adaptive voice stream multicast  coding redundancy ratio  coordination rules  disaster response  distributed admission control algorithm  forward error correction  forwarder selection  low-power wireless networks  security surveillance  tree-based opportunistic routing protocol  voice quality  ad hoc networks  audio streaming  forward error correction  multicast communication  routing protocols  telecommunication congestion control  voice communication   An improved two-dimensional entropy method for star trail tracing in deep sky (EI CONFERENCE) 会议论文  OAI收割 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China 作者:  Wang Y.-J.;  Yao Z.-J. 收藏  |  浏览/下载：30/0  |  提交时间：2013/03/25 The trace of star trail is an important component of deep sky detection. The stars are low contrast targets  and their self-rotation will make their brightness change in cycle. Above all  the trail trace is vulnerable to the block and disturbance of other stars. Traditional one-dimensional maximum entropy thresholding algorithm is vulnerable to the noise  and the calculation of two-dimensional entropy methods is too large and takes too much time. This paper proposes an improved two-dimensional entropy threshold algorithm. We use recursion iteration method to eliminate the redundancy calculation  and reduce the size of two-dimensional histogram based on the deep sky stars characteristic  such as low contrast  fuzziness and the centralized histogram. We also combine our algorithm with the space trail trace model to forecast the star trace. Experiments results show  when the star are blocked or they turn dark  the method still can well extrapolate the star trace. Our method improves the capability of trailing the ebb and small star  and increases the precision of tracing. It is also robust to the noise  so there is a good application foreground for the method.