期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
多标记收缩哈希方法的人脸属性检索 被引量:1
1
作者 赵轩 谭晓阳 宋歌 《模式识别与人工智能》 EI CSCD 北大核心 2017年第12期1108-1113,共6页
哈希方法具有存储成本低、查询速度快等优点.但是,大多数哈希方法只用于处理单标记问题,较少用于图像多标记问题.因此,文中提出多标记收缩哈希方法(MLCH),可以保留多标记图像的多水平语义相似性.MLCH利用数据的多标记作为监督信息,依据... 哈希方法具有存储成本低、查询速度快等优点.但是,大多数哈希方法只用于处理单标记问题,较少用于图像多标记问题.因此,文中提出多标记收缩哈希方法(MLCH),可以保留多标记图像的多水平语义相似性.MLCH利用数据的多标记作为监督信息,依据优化选择算法选取三元组,并加入收缩约束项以获取更饱和的二进制编码.在数据库Celeb A和Pub Fig上评估MLCH性能,证明收缩约束项的有效性,并证明MLCH在大规模图像检索任务中的优越性. 展开更多
关键词 多标记 收缩项 哈希方法 人脸属性
下载PDF
Low latency systolic multipliers for finite field GF(2m) based on irreducible polynomials
2
作者 谢佳峰 贺建军 桂卫华 《Journal of Central South University》 SCIE EI CAS 2012年第5期1283-1289,共7页
Systolic implementation of multiplication over GF(2m) is usually very efficient in area-time complexity,but its latency is usually very large.Thus,two low latency systolic multipliers over GF(2m) based on general irre... Systolic implementation of multiplication over GF(2m) is usually very efficient in area-time complexity,but its latency is usually very large.Thus,two low latency systolic multipliers over GF(2m) based on general irreducible polynomials and irreducible pentanomials are presented.First,a signal flow graph(SFG) is used to represent the algorithm for multiplication over GF(2m).Then,the two low latency systolic structures for multiplications over GF(2m) based on general irreducible polynomials and pentanomials are presented from the SFG by suitable cut-set retiming,respectively.Analysis indicates that the proposed two low latency designs involve at least one-third less area-delay product when compared with the existing designs,To the authors' knowledge,the time-complexity of the structures is the lowest found in literature for systolic GF(2m) multipliers based on general irreducible polynomials and pentanomials.The proposed low latency designs are regular and modular,and therefore they are suitable for many time critical applications. 展开更多
关键词 finite field finite field multiplication systolic structure low latency POLYNOMIALS
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部