一种运动数据检索的相关反馈算法  

A Relevance Feedback Algorithm for Motion Data Retrieval

作　　者：陈松乐[1,2] 孙正兴[1] 张岩[1] 李骞[1] 

机构地区：[1]南京大学计算机软件新技术国家重点实验室,江苏南京210046 [2]南京邮电大学宽带无线通信与传感网教育部重点实验室,江苏南京210003

出　　处：《电子学报》2016年第4期868-872,共5页Acta Electronica Sinica

基　　金：国家高科技发展计划(No.2007AA01Z334);国家自然科学基金(No.61272219;No.61100110;No.61321491);教育部新世纪优秀人才资助计划(No.NCET-04-0460);江苏省科技计划(No.BE2010072;No.BE2011058;No.BY2012190;No.BY2013072-04);计算机软件新技术国家重点实验室创新基金重点项目(No.ZZKT2013A12)

摘　　要：本文提出了一种基于Rank Boost的运动数据检索相关反馈算法.该算法具有以下二个方面的特点:首先,以KNN-DTW作为Rank Boost集成学习的弱排序器,在适应变长多变量时间序列(Variable-Length Multivariate Time Series,VLMTS)数据的同时,利用Rank Boost的集成性与高效性解决相关反馈实时性要求与VLMTS数据计算复杂度高的矛盾;其次,以本文提出的最小化排序经验损失和泛化损失风险作为Rank Boost集成学习目标,有效地克服了相关反馈小样本学习环境下的过拟合问题.在CMU动作库上的实验结果验证了该方法的有效性.A relevance feedback algorithm based on RankBoost for content-based motion data retrieval （CBMR） is presented and has two characteristics. First, KNN-DTW is employed as the weak ranker for RankBoost ensemble learning. While adapting to variable-length multivariate time series （ VLMTS ） data, by taking the advantage of the ensemble and effi- ciency of RankBoost,it can resolve the conflict between the real-time requirement of relevance feedback and the high com- putational complexity of VLMTS data. Second, minimizing ranking experience loss and generalization loss risk proposed in this paper are used as the learning objective for RankBoost ensemble learning, which can effectively solve the over-fitting problem caused by small-sample training in relevance feedback. Experimental results on CMU action library verify the effec- tiveness of the proposed algorithm.

关 键 词：运动捕获数据 相关反馈 RankBoost 排序损失 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]