全部文献期刊学位论文会议报纸专利标准年鉴图书|学者科研项目
中外文文献  中文文献  外文文献
作者:Renzhen Ye , Xuelong Li
来源:[J].Journal of Computer Science and Technology(IF 0.477), 2017, Vol.32 (3), pp.470-479Springer
摘要:Abnormal event detection in crowded scenes is a hot topic in computer vision and information retrieval community. In this paper, we study the problems of detecting anomalous behaviors within the video, and propose a robust collective representation with multi-feature descriptors ...
作者:Xiao-Yu Du , Yang Yang , Liu Yang ...
来源:[J].Journal of Computer Science and Technology(IF 0.477), 2017, Vol.32 (3), pp.480-493Springer
摘要:Video captioning is the task of assigning complex high-level semantic descriptions (e.g., sentences or paragraphs) to video data. Different from previous video analysis techniques such as video annotation, video event detection and action recognition, video captioning is much clo...
来源:[J].Journal of Computer Science and Technology(IF 0.477), 2017, Vol.32 (5), pp.843-844Springer
作者:Yawar Abbas Bangash , Ling-Fang Zeng , Dan Feng
来源:[J].Journal of Computer Science and Technology(IF 0.477), 2017, Vol.32 (5), pp.991-1007Springer
摘要:In a wireless sensor network (WSN), sink node/base station (BS) gathers data from surrounding nodes and sends them to a remote server via a gateway. BS holds important data. Therefore, it is necessary to hide its location from an inside/outside attacker. Providing BS locatio...
作者:Hong-Zhi Wang , Zhi-Xin Qi , Ruo-Xi Shi ...
来源:[J].Journal of Computer Science and Technology(IF 0.477), 2017, Vol.32 (5), pp.845-857Springer
摘要:Missing value imputation with crowdsourcing is a novel method in data cleaning to capture missing values that could hardly be filled with automatic approaches. However, the time cost and overhead in crowdsourcing are high. Therefore, we have to reduce cost and guarantee the accur...
作者:Xin-Yu Ou , Ping Li , He-Fei Ling ...
来源:[J].Journal of Computer Science and Technology(IF 0.477), 2017, Vol.32 (4), pp.683-700Springer
摘要:Semantic segmentation has recently witnessed rapid progress, but existing methods only focus on identifying objects or instances. In this work, we aim to address the task of semantic understanding of scenes with deep learning. Different from many existing methods, our method...
作者:Ning Wang , Yu Gu , Jia Xu ...
来源:[J].Journal of Computer Science and Technology(IF 0.477), 2017, Vol.32 (5), pp.1008-1024Springer
摘要:The big data era is coming with strong and ever-growing demands on analyzing personal information and footprints in the cyber world. To enable such analysis without privacy leak risk, differential privacy (DP) has been quickly rising in recent years, as the first practical privac...
作者:Kai-Yuan Cui , Peng-Jie Ren , Zhu-Min Chen ...
来源:[J].Journal of Computer Science and Technology(IF 0.477), 2017, Vol.32 (4), pp.814-827Springer
摘要:Inferring semantic types of the entity mentions in a sentence is a necessary yet challenging task. Most of existing methods employ a very coarse-grained type taxonomy, which is too general and not exact enough for many tasks. However, the performances of the methods drop sharply ...
作者:Shu-Chang Zhou , Yu-Zhi Wang , He Wen ...
来源:[J].Journal of Computer Science and Technology(IF 0.477), 2017, Vol.32 (4), pp.667-682Springer
摘要:Quantized neural networks (QNNs), which use low bitwidth numbers for representing parameters and performing computations, have been proposed to reduce the computation complexity, storage size and memory usage. In QNNs, parameters and activations are uniformly quantized, such that...
作者:Zhi-Xu Li , Qiang Yang , An Liu ...
来源:[J].Journal of Computer Science and Technology(IF 0.477), 2017, Vol.32 (5), pp.858-876Springer
摘要:Entity matching (EM) identifies records referring to the same entity within or across databases. Existing methods using structured attribute values (such as digital, date or short string values) may fail when the structured information is not enough to reflect the matching relati...

我们正在为您处理中,这可能需要一些时间,请稍等。

资源合作:cnki.scholar@cnki.net, +86-10-82896619   意见反馈:scholar@cnki.net

×