图像重排序技术的研究进展
|
摘要
近年来,数字多媒体图像出现了爆炸式的增长,人们在互联网搜索过程中遇到的问题也越来越多,提高图像的搜索效率极具挑战性。图像搜索是图像领域的研究热点,目前已有多种搜索技术在各商业领域得到应用,但搜索的结果并不能完全满足用户的需求,"语义鸿沟"的存在使得搜索结果仍存在一定的噪声。图像重排序为解决此问题提供了很好的帮助,在初始搜索的基础上进行重排序可使搜索结果更加准确和丰富。文中着重介绍图像重排序技术的研究进展,对已有研究方法进行总结和分析,比较各自的优缺点以及近年来突破的主要关键技术;关注最新的研究进展,总结了目前图像重排序的典型数据集以及针对特定领域研究建立的数据集,并对图像重排序领域未来的发展进行了展望。
In recent years,with the rapid development of Internet technology and the popularity of multimedia terminals electronic products,improving the efficiency of image search is a challenge in the media retrieval.The research of image search is a hot issue in the field of image.At present,many current commercial image search techniques have been applied,but the search results cannot meet the needs of users because of the existence of"semantic gap".The search results still have some noise.Image search reordering is helpful to solve this problem.Based on the initial search,results can be more accurate and more abundant after reranking.In this paper,the research progress of image search reranking technology was introduced,and the current research methods were summarized and analyzed.The advantages and disadvantages of these methods and the key technologies in recent years were compared.The latest research progress and the future development of image search reranking and the future development were also given.
In recent years,with the rapid development of Internet technology and the popularity of multimedia terminals electronic products,improving the efficiency of image search is a challenge in the media retrieval.The research of image search is a hot issue in the field of image.At present,many current commercial image search techniques have been applied,but the search results cannot meet the needs of users because of the existence of"semantic gap".The search results still have some noise.Image search reordering is helpful to solve this problem.Based on the initial search,results can be more accurate and more abundant after reranking.In this paper,the research progress of image search reranking technology was introduced,and the current research methods were summarized and analyzed.The advantages and disadvantages of these methods and the key technologies in recent years were compared.The latest research progress and the future development of image search reranking and the future development were also given.
引文
[1]DENG L Q,HAO X N,XIA M,et al.Image Annotation by Similarity Content-based Image Retrieval[J].Computer Science2014,41(11A):119-122.(in Chinese)邓莉琼,郝向宁,夏鸣,等.基于内容检索的图像自动标注方法研究[J].计算机科学,2014,41(11A):119-122.
[2]SMEULDERS A W M,WORRING M,SANTINI S,et al.Content-based image retrieval at the end of the early years[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2000,22(12):1349-1380.
[3]ZHU J L,YANG X P,PENG L Q.Research on Effect of Adding Internal Semantic Relationship into Text Categorization[J].Computer Science,2016,43(9):82-86.(in Chinese)朱建林,杨小平,彭鲸桥.融入内部语义关系对文本分类的影响研究[J].计算机科学,2016,43(9):82-86.
[4]WANG Y H,CHEN X R.Improved Text Clustering Algorithm Based on Kolmogorov Complexity[J].Computer Science,2016,43(5):243-246.(in Chinese)王有华,陈笑蓉.基于Kolmogorov复杂性的文本聚类算法改进[J].计算机科学,2016,43(5):243-246.
[5]ZHANG J,LI D Y,WANG S G,et al.Multi-label Text Classification Based on Robust Fuzzy Rough Set Model[J].Computer Science,2015,2(7):270-275.(in Chinese)张晶,李德玉,王素格,等.基于稳健模糊粗糙集模型的多标记文本分类[J].计算机科学,2015,42(7):270-275.
[6]LEE K S,PARK Y C,CHOI K S.Re-ranking model based on document clusters[J].Information Processing&Management,2001,37(1):1-14.
[7]CAO Z,QIN T,LIU T Y,et al.Learning to rank:from pairwise approach to listwise approach[C]∥Machine Learning,Proceedings of the Twenty-Fourth International Conference.2007:129-136.
[8]ZLOOF M M.Query-by-Example:A data base language[J].Ibm Systems Journal,1977,16(4):324-343.
[9]ZLOOF M M.Query-by-example:the invocation and definition of tables and forms[C]∥International Conference on Very Large Data Bases,Framingham,Massachusetts,USA.1975:1-24.
[10]BOGERS T,BOSCH V A.Authoritative re-ranking in fusing authorship-based subcollection search results[C]∥BelgianDutch Information Retrieval Workshop,Dir.2006:49-55.
[11]YAMAMOTO T,NAKAMURA S,TANAKA K.Rerank-byExample:Efficient Browsing of Web Search Results[M]∥Database and Expert Systems Applications.Springer Berlin Heidelberg,2007:801-810.
[12]ROHINI U,VARMA V.A Novel Approach for Re-Ranking of Search Results Using Collaborative Filtering[C]∥Computing:Using Collaborative Filtering.International Conferenceon Computing:Theory and Applications.2007:491-496.
[13]YANG J G,FREDERKING Y,ROBERT E,et al.Translingual Information Retrieval:A Comparative Evaluation[C]∥Proceedings of the 15th International Joint Conference on Artificial Intelligence.1997:708-715.
[14]YAN R,HAUPTMANN A,JIN R.Multimedia search with pseudo-relevance feedback[J].Lecture Notes in Computer Science,2003,2728:238-247.
[15]YAN R,HAUPRMANN A.Query expansion using probabilistic local feedback with application to multimedia retrieval[C]∥Sixteenth ACM Conference on Information and Knowledge Management(CIKM 2007).Lisbon,Portugal,November,2007:361-370.
[16]HSU W H,KENNEDY L S,CHANG S F.Video search reranking via information bottleneck principle[C]∥ACM International Conference on Multimedia.Santa Barbara,CA,USA,2006:35-44.
[17]BEN-HAIM N,BABENKO B,BELONGIE S.Improving Webbased Image Search via Content Based Clustering[C]∥Conference on Computer Vision and Pattern Recognition Workshop.IEEE Computer Society,2006:106.
[18]BEN-HAIM N,BABENKO B,BELONGIE S.Improving Webbased Image Search via Content Based Clustering[C]∥Conference on Computer Vision and Pattern Recognition Workshop.IEEE Computer Society,2006:106.
[19]PARK G,BAEK Y,LEE H K.Re-ranking algorithm using postretrieval clustering for content-based image retrieval[J].Information Processing&Management,2005,41(2):177-194.
[20]VAN LEUKEN R H,GARCIA L,et al.Visual diversification of image search results[C]∥International Conference on World Wide Web(WWW 2009).Madrid,Spain,2009:341-350.
[21]FERGUS R,PERONA P,ZISSERMAN A.A Visual Category Filter for Google Images[M]∥Computer Vision-ECCV 2004.Springer Berlin Heidelberg,2004:242-256.
[22]BRIN S,PAGE L.The anatomy of a large-scale hypertextual Web search engine[J].Computer Networks&Isdn Systems,1998,30(1-7):107-117.
[23]HSU W H.Video search reranking through random walk over document-level context graph[C]∥International Conference on Multimedia 2007.Augsburg,Germany,2007:971-980.
[24]BALUJA S,SETH R,SIVAKUMAR D,et al.Video suggestion and discovery for youtube:taking random walks through the view graph[C]∥Proceedings of the 17th International Conference on World Wide Web.ACM,2015:895-904.
[25]JING Y,BALUJA S.VisualRank:applying PageRank to largescale image search[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2008,30(11):1877-1890.
[26]TIAN X,YANG L,WANG J,et al.Bayesian video search reranking[C]∥International Conference on Multimedia 2008.Vancouver,British Columbia,Canada,2008:131-140.
[27]HOU H M,XU X S,WANG G,et al.Joint-Rerank:a novel method for image search reranking[J].Multimedia Tools&Applications,2012,74(4):1423-1442.
[28]LU J,ZHOU J,WANG J,et al.Image search results refinement via outlier detection using deep contexts[C]∥IEEE Conference on Computer Vision&Pattern Recognition.2012:3029-3036.
[29]GAO S,CHENG X,WANG H,et al.Concept model-based unsupervised web image re-ranking[C]∥IEEE International Conference on Image Processing.IEEE Press,2009:793-796.
[30]KENNEDY L S,CHANG S F.A reranking approach for context-based concept fusion in video indexing and retrieval[C]∥ACM International Conference on Image and Video Retrieval,Civr 2007.2007:333-340.
[31]NATSEV A,HAUBOLD A,JELENA,et al.Semantic conceptbased query expansion and re-ranking for multimedia retrieval[C]∥Proceedings of the 15th International Conference on Multimedia.ACM,2007:991-1000.
[32]LIU Y,MEI T,HUA X S,et al.Learning to video search rerank via pseudo preference feedback[C]∥IEEE International Conference on Multimedia and Expo.2008:297-300.
[33]YAO T,MEI T,NGO C W.Co-reranking by mutual reinforcement for image search[C]∥ACM International Conference on Image and Video Retrieval(Civr 2010).Xi’an,China,2010:34-41.
[34]YAN R,HAUPTMANN A G.Co-retrieval:A Boosted Reranking Approach for Video Retrieval[J].IEEE Proceedings of Vision Image and Signal Processing,2004,19(5):888-895.
[35]LIU Y,MEI T,HUA X S.Crowd Reranking:Exploring Multiple Search Engines for Visual Search Reranking[C]∥International ACM SIGIR Conference on Research and Development in Information Retrieval(SIGIR 2009).Boston,MA,USA,2009:500-507.
[36]KENNEDY L S,CHANG S F.A reranking approach for context-based concept fusion in video indexing and retrieval[C]∥ACM International Conference on Image and Video Retrieval,Civr 2007.Amsterdam,the Netherlands,2007:333-340.
[37]XU X L,ZHANG L B,LIU X D,et al.Image Retrieval Relevance Feedback Algorithm Based onarticle Swarm Optimization[J].Acta Electronica Sinica,2010,38(8):1935-1940.
[38]DENG C,JI R,TAO D,et al.Weakly Supervised Multi-Graph Learning for Robust Image Reranking[J].IEEE Transactions on Multimedia,2014,16(3):785-795.
(1)http://www-nlpir.nist.gov/projects/trecvid
[2]SMEULDERS A W M,WORRING M,SANTINI S,et al.Content-based image retrieval at the end of the early years[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2000,22(12):1349-1380.
[3]ZHU J L,YANG X P,PENG L Q.Research on Effect of Adding Internal Semantic Relationship into Text Categorization[J].Computer Science,2016,43(9):82-86.(in Chinese)朱建林,杨小平,彭鲸桥.融入内部语义关系对文本分类的影响研究[J].计算机科学,2016,43(9):82-86.
[4]WANG Y H,CHEN X R.Improved Text Clustering Algorithm Based on Kolmogorov Complexity[J].Computer Science,2016,43(5):243-246.(in Chinese)王有华,陈笑蓉.基于Kolmogorov复杂性的文本聚类算法改进[J].计算机科学,2016,43(5):243-246.
[5]ZHANG J,LI D Y,WANG S G,et al.Multi-label Text Classification Based on Robust Fuzzy Rough Set Model[J].Computer Science,2015,2(7):270-275.(in Chinese)张晶,李德玉,王素格,等.基于稳健模糊粗糙集模型的多标记文本分类[J].计算机科学,2015,42(7):270-275.
[6]LEE K S,PARK Y C,CHOI K S.Re-ranking model based on document clusters[J].Information Processing&Management,2001,37(1):1-14.
[7]CAO Z,QIN T,LIU T Y,et al.Learning to rank:from pairwise approach to listwise approach[C]∥Machine Learning,Proceedings of the Twenty-Fourth International Conference.2007:129-136.
[8]ZLOOF M M.Query-by-Example:A data base language[J].Ibm Systems Journal,1977,16(4):324-343.
[9]ZLOOF M M.Query-by-example:the invocation and definition of tables and forms[C]∥International Conference on Very Large Data Bases,Framingham,Massachusetts,USA.1975:1-24.
[10]BOGERS T,BOSCH V A.Authoritative re-ranking in fusing authorship-based subcollection search results[C]∥BelgianDutch Information Retrieval Workshop,Dir.2006:49-55.
[11]YAMAMOTO T,NAKAMURA S,TANAKA K.Rerank-byExample:Efficient Browsing of Web Search Results[M]∥Database and Expert Systems Applications.Springer Berlin Heidelberg,2007:801-810.
[12]ROHINI U,VARMA V.A Novel Approach for Re-Ranking of Search Results Using Collaborative Filtering[C]∥Computing:Using Collaborative Filtering.International Conferenceon Computing:Theory and Applications.2007:491-496.
[13]YANG J G,FREDERKING Y,ROBERT E,et al.Translingual Information Retrieval:A Comparative Evaluation[C]∥Proceedings of the 15th International Joint Conference on Artificial Intelligence.1997:708-715.
[14]YAN R,HAUPTMANN A,JIN R.Multimedia search with pseudo-relevance feedback[J].Lecture Notes in Computer Science,2003,2728:238-247.
[15]YAN R,HAUPRMANN A.Query expansion using probabilistic local feedback with application to multimedia retrieval[C]∥Sixteenth ACM Conference on Information and Knowledge Management(CIKM 2007).Lisbon,Portugal,November,2007:361-370.
[16]HSU W H,KENNEDY L S,CHANG S F.Video search reranking via information bottleneck principle[C]∥ACM International Conference on Multimedia.Santa Barbara,CA,USA,2006:35-44.
[17]BEN-HAIM N,BABENKO B,BELONGIE S.Improving Webbased Image Search via Content Based Clustering[C]∥Conference on Computer Vision and Pattern Recognition Workshop.IEEE Computer Society,2006:106.
[18]BEN-HAIM N,BABENKO B,BELONGIE S.Improving Webbased Image Search via Content Based Clustering[C]∥Conference on Computer Vision and Pattern Recognition Workshop.IEEE Computer Society,2006:106.
[19]PARK G,BAEK Y,LEE H K.Re-ranking algorithm using postretrieval clustering for content-based image retrieval[J].Information Processing&Management,2005,41(2):177-194.
[20]VAN LEUKEN R H,GARCIA L,et al.Visual diversification of image search results[C]∥International Conference on World Wide Web(WWW 2009).Madrid,Spain,2009:341-350.
[21]FERGUS R,PERONA P,ZISSERMAN A.A Visual Category Filter for Google Images[M]∥Computer Vision-ECCV 2004.Springer Berlin Heidelberg,2004:242-256.
[22]BRIN S,PAGE L.The anatomy of a large-scale hypertextual Web search engine[J].Computer Networks&Isdn Systems,1998,30(1-7):107-117.
[23]HSU W H.Video search reranking through random walk over document-level context graph[C]∥International Conference on Multimedia 2007.Augsburg,Germany,2007:971-980.
[24]BALUJA S,SETH R,SIVAKUMAR D,et al.Video suggestion and discovery for youtube:taking random walks through the view graph[C]∥Proceedings of the 17th International Conference on World Wide Web.ACM,2015:895-904.
[25]JING Y,BALUJA S.VisualRank:applying PageRank to largescale image search[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2008,30(11):1877-1890.
[26]TIAN X,YANG L,WANG J,et al.Bayesian video search reranking[C]∥International Conference on Multimedia 2008.Vancouver,British Columbia,Canada,2008:131-140.
[27]HOU H M,XU X S,WANG G,et al.Joint-Rerank:a novel method for image search reranking[J].Multimedia Tools&Applications,2012,74(4):1423-1442.
[28]LU J,ZHOU J,WANG J,et al.Image search results refinement via outlier detection using deep contexts[C]∥IEEE Conference on Computer Vision&Pattern Recognition.2012:3029-3036.
[29]GAO S,CHENG X,WANG H,et al.Concept model-based unsupervised web image re-ranking[C]∥IEEE International Conference on Image Processing.IEEE Press,2009:793-796.
[30]KENNEDY L S,CHANG S F.A reranking approach for context-based concept fusion in video indexing and retrieval[C]∥ACM International Conference on Image and Video Retrieval,Civr 2007.2007:333-340.
[31]NATSEV A,HAUBOLD A,JELENA,et al.Semantic conceptbased query expansion and re-ranking for multimedia retrieval[C]∥Proceedings of the 15th International Conference on Multimedia.ACM,2007:991-1000.
[32]LIU Y,MEI T,HUA X S,et al.Learning to video search rerank via pseudo preference feedback[C]∥IEEE International Conference on Multimedia and Expo.2008:297-300.
[33]YAO T,MEI T,NGO C W.Co-reranking by mutual reinforcement for image search[C]∥ACM International Conference on Image and Video Retrieval(Civr 2010).Xi’an,China,2010:34-41.
[34]YAN R,HAUPTMANN A G.Co-retrieval:A Boosted Reranking Approach for Video Retrieval[J].IEEE Proceedings of Vision Image and Signal Processing,2004,19(5):888-895.
[35]LIU Y,MEI T,HUA X S.Crowd Reranking:Exploring Multiple Search Engines for Visual Search Reranking[C]∥International ACM SIGIR Conference on Research and Development in Information Retrieval(SIGIR 2009).Boston,MA,USA,2009:500-507.
[36]KENNEDY L S,CHANG S F.A reranking approach for context-based concept fusion in video indexing and retrieval[C]∥ACM International Conference on Image and Video Retrieval,Civr 2007.Amsterdam,the Netherlands,2007:333-340.
[37]XU X L,ZHANG L B,LIU X D,et al.Image Retrieval Relevance Feedback Algorithm Based onarticle Swarm Optimization[J].Acta Electronica Sinica,2010,38(8):1935-1940.
[38]DENG C,JI R,TAO D,et al.Weakly Supervised Multi-Graph Learning for Robust Image Reranking[J].IEEE Transactions on Multimedia,2014,16(3):785-795.
(1)http://www-nlpir.nist.gov/projects/trecvid