期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

一种基于弱标签的三维模型语义自动标注方法 被引量：3

3D Model Semantic Automatic Annotation Based on Weak Label
原文传递
导出
摘要 随着三维应用的普及,三维模型大量产生并广泛传播。由于三维模型广泛应用于计算机辅助设计、三维游戏、电影特效制作等诸多领域,已经形成了大量的三维模型数据库。三维模型语义标注的目的是给出描述其语义的标注词,是三维模型管理和基于文本的三维检索的关键技术。针对互联网大量存在的弱标签三维模型现状,提出一种基于弱标签的三维模型语义标注方法LPMLL,首先,采用半监督学习方法进行标签传播,得到标注词置信度,达到提升训练集的目的。然后,采用一种基于最大后验概率准则的方法进行多标签学习,得到最终标注词。实验数据表明了该方法的有效性。 With the increasing popularity of 3D applications, a lot of 3D geometry models are being created The purpose of annotation for 3D model is that it can automatically list the best suitable labels to describe the 3D models; it is an important part of the text-based 3D model retrieval. A novel method LPMLLfor 3D models multiple semantic annotation was proposed based on weak label First, a graph-based method was proposed to expand the labeled data set. Then, a multi-label lazy learning approach was proposed based on its k nearest neighbors, and maximum a posteriori （MAP） principle was utilized to determine the label set for the unseen 3D model. Experimental evaluation of the method shows that the proposed method is effective in autotagging 3D models.
作者 田枫 沈旭昆 刘贤梅 周凯 杜睿山
机构地区 北京航空航天大学虚拟现实技术与系统国家重点实验室 东北石油大学计算机与信息技术学院
出处 《系统仿真学报》 CAS CSCD 北大核心 2012年第9期1873-1876,1881,共5页 Journal of System Simulation
基金 国家高技术研究发展计划(2009AA012103) 国家自然科学基金(60533070) 黑龙江省教育厅基金(12511011 12521055)
关键词 三维模型自动标注 语义标注 半监督学习 弱标签 3D model automatic annotation semantic annotation semi-supervised learning weak label
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献13

  • 1Shilane Philip, Min Patrick, Kazhdan Michael. The Princeton shape benchmark [C]// Proceedings of International Conference on Shape Modeling. Washington DC, USA: IEEE Computer Society, 2004: 167-178.
  • 2Pu J T, Liu Y, Xin G Y. 3D Model Retrieval Based on 2D Slice Similarity Measurements [C]// Proceedings of the second International Symposium on 3D Data Processing, Visualization, and Transmission. Washington DC USA: IEEE Computer Society, 2004: 95-101.
  • 3R Zhao, W I Grosky. Negotiating the semantic gap: from feature maps to semantic landscapes [J]. Pattern Recognition (S0031-3203), 2002, 35(3): 51-58.
  • 4Meng Z, Atta B. Semantic-associative visual content labeling and retrieval: A multimodal approach [J]. Signal Processing: Image Communication (S0923-5965), 2007, 22(6): 569-582.
  • 5G Leifman. Semantic-oriented 3d shape retrieval using relevance feedback [J]. The Visual Computer (S0178-2789), 2005, 21(8): 865-875.
  • 6Ryutarou Ohbuchi, Akihiro Yamamoto, Jun Kobayashi. Learning semantic categories for 3D Model Retrieval [C]// Proceedings of the international workshop on Workshop on multimedia information retrieval. New York, USA: ACM, 2007:31-40.
  • 7D Zhou, O Bousquet. Learning with local and global consistency [C]// Advances in Neural Information Processing Systemsl6, Seventeenth Annual Conference on Neural Information Processing Systems. MA, USA: MIT Press, 2003.321-328.
  • 8孔祥南,黎铭,姜远,周志华.一种针对弱标记的直推式多标记分类方法[J].计算机研究与发展,2010,47(8):1392-1399. 被引量：13
  • 9Zhangxiang Wang, Yiqun Hu, Liang-Tien Chia. Multi-Label Learning by Image-to-Class Distance for Scene Classification and Image Annotation [C]// ACM Conference on Image and Video Retrieval. USA: ACM, 2010.253-257.
  • 10Xiangyang Xue, Hangzai Luo, Jianping Fan. Structured Max-Margin Learning for Multi-Label Image Annotation [C]//ACM Conference on Image and Video Retrieval. USA: ACM, 2010.136-141.

二级参考文献16

  • 1Schapire R E,Singer Y.Boostexter:A boosting-based system for text categorization[J].Machine Learning,2000,39(2/3):135-168.
  • 2Elisseeff A,Weston J.A kernel method for multi-labelled classification[C] //Advances in Neural Information Processing Systems.Cambridge,MA:MIT Press,2002:681-687.
  • 3Zhang M -L,Zhou Z -H.Ml-kNN:A lazy learning approach to multi-label learning[J].Pattern Recognition,2007,40(7):2038-2048.
  • 4Zhang M -L,Zhou Z -H.Multi-label neural networks with applications to functional genomics and text categorization[J].IEEE Trans on Knowledge and Data Engineering,2006,18(10):1338-1351.
  • 5周志华,张敏灵,黄圣君,等.MIML:一种从歧义对象中学习的框架,0808.3231[R].南京:南京大学软件新技术国家重点实验室,2008.
  • 6Comite F D,Gilleron R,Tommasi M.Learning multi-label alternating decision tree from texts and data[C] //Proc of the 3rd Int Conf on Machine Learning and Data Mining in Pattern Recognition.Berlin:Springer,2003:35-49.
  • 7Gao S,Wu W,Lee C -H,et al.A MFoM learning approach to robust multiclass multi-label text categorization[C] //Proc of the 21st Int Conf on Machine Learning.New York:ACM,2004:329-336.
  • 8Kazawa H,Izumitani T,Taira H,et al.Maximal margin labeling for multi-topic text categorization[C] //Advances in Neural Information Processing Systems.Cambridge,MA:MIT Press,2005:649-656.
  • 9McCallum A.Multi-label text classification with a mixture model trained by EM[C] //Working Notes of the AAAI'99 Workshop on Text Learning.Menlo Park,CA:AAAI,1999:1-7.
  • 10Boutell M R,Luo J,Shen X,Brown C M.Learning multi-label scene classification[J].Pattern Recognition,2004,37(9):1757-1771.

共引文献12

同被引文献27

  • 1Symonova O, Dao M S, Ucelli G, et al. Ontology based shapeannotation and retrieval [C] //Proc of the ECAI, 2006.
  • 2Linxweiler J, Tolke J, Krafczyk M. Part-based annotation of virtual 3D shapes [C] // International Conference on IEEE, 2007 : 427-436.
  • 3Goldfeder C, Allen P. Autotagging to improve text search for 3D models [C] //Proceedings of the 8th ACM/IEEE-CS Joint Conference on Digital Libraries, 2008: 355-358.
  • 4Lu T, Huang S, Wu P, et al. Research on semantic annotation and retrival of 3D models based on user feedback [R]. China Zhejiang Province Ningbo CityNew Century Grand Hotel Ning- bo: Chinese Academy of Sciences Institute of Computing Tech- nology, 2010.
  • 5黄文.三维模型语义标注系统的设计与实现[D].西安:西北大学,2011.
  • 6王小凤,周蓬勃,耿国华,等.三维模型自动语义标注技术研究[OL].中国科技论文在线,http://www.paper.edu.cn/re-leasepaper/content/201202-653.
  • 7王新颖,吕天阳,王钲旋.基于语义相关性的三维模型分类及标注[0L].中国科技论文在线,http://www.pa-per.edu.cn/releasepaper/content/2009.
  • 8Attene M,Robbiano F,Spagnuolo M,et al.Characterization of 3D shape parts for semantic annotation[J].Computer-Aided Design,2009,41(10):756-763.
  • 9Kalogerakis E,Hertzmann A,Singh K.Learning 3D mesh segmentation and labeling[J].ACM Transactions on Graphics(TOG),2010,29(4):102.
  • 10Lu T,Huang S,Wu P,et al.Research on Semantic Annotation and Retrival of 3D Models Based on User Feedback[R].China Zhejiang province Ningbo City New Century Grand Hotel Ningbo:Chinese Academy of Sciences Institute of Computing Technology,2010.

引证文献3

二级引证文献1

系统仿真学报
2012年 第9期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部