{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T17:06:51Z","timestamp":1745428011207},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2020,3,2]],"date-time":"2020-03-02T00:00:00Z","timestamp":1583107200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,3,2]],"date-time":"2020-03-02T00:00:00Z","timestamp":1583107200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1007\/s10489-019-01625-y","type":"journal-article","created":{"date-parts":[[2020,3,2]],"date-time":"2020-03-02T13:03:08Z","timestamp":1583154188000},"page":"2208-2221","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["FRWCAE: joint faster-RCNN and Wasserstein convolutional auto-encoder for instance retrieval"],"prefix":"10.1007","volume":"50","author":[{"given":"Yi-yang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da-jiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia-xing","family":"Shang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bao-hua","family":"Qiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,2]]},"reference":[{"issue":"2","key":"1625_CR1","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110","journal-title":"Int J Comput Vis"},{"key":"1625_CR2","doi-asserted-by":"crossref","unstructured":"Sivic, Zisserman (2003) Video google: a text retrieval approach to object matching in videos. In: 9th IEEE international conference on computer vision (ICCV 2003), 14-17 October 2003, Nice, France, vol 2. IEEE, pp 1470\u20131477","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"1625_CR3","doi-asserted-by":"crossref","unstructured":"Philbin J, Chum O, Isard M, Sivic J, Zisserman A (2007) Object retrieval with large vocabularies and fast spatial matching. In: 2007 IEEE computer society conference on computer vision and pattern recognition (CVPR 2007), 18-23 June 2007, Minneapolis, Minnesota, USA. IEEE, pp 1\u20138","DOI":"10.1109\/CVPR.2007.383172"},{"key":"1625_CR4","doi-asserted-by":"crossref","unstructured":"Jegou H, Douze M, Schmid C (2008) Hamming embedding and weak geometric consistency for large scale image search. In: Computer vision - ECCV 2008, 10th European conference on computer vision, Marseille, France, October 12-18, 2008, Proceedings, Part I, vol 5302. Springer, pp 304\u2013317","DOI":"10.1007\/978-3-540-88682-2_24"},{"key":"1625_CR5","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016. IEEE, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"1625_CR6","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick RB, Sun J (2017) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"1625_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10489-015-0739-x","volume":"45","author":"Z Wang","year":"2016","unstructured":"Wang Z, Wu X (2016) Salient object detection using biogeography-based optimization to combine features. Appl Intell 45(1):1\u201317","journal-title":"Appl Intell"},{"issue":"4","key":"1625_CR8","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1007\/s10489-015-0679-5","volume":"43","author":"X Han","year":"2015","unstructured":"Han X, Xiong X, Duan F (2015) A new method for image segmentation based on BP neural network and gravitational search algorithm enhanced by cat chaotic mapping. Appl Intell 43(4):855\u2013873","journal-title":"Appl Intell"},{"issue":"2","key":"1625_CR9","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1007\/s10489-016-0819-6","volume":"46","author":"R Arya","year":"2017","unstructured":"Arya R, Singh N, Agrawal RK (2017) A novel combination of second-order statistical features and segmentation using multi-layer superpixels for salient object detection. Appl Intell 46(2):254\u2013271","journal-title":"Appl Intell"},{"key":"1625_CR10","doi-asserted-by":"crossref","unstructured":"Razavian AS, Azizpour H, Sullivan J, Carlsson S (2014) CNN features off-the-shelf: an astounding baseline for recognition. In: IEEE conference on computer vision and pattern recognition, CVPR Workshops 2014, Columbus, OH, USA, June 23-28, 2014. IEEE, pp 512\u2013519","DOI":"10.1109\/CVPRW.2014.131"},{"key":"1625_CR11","doi-asserted-by":"crossref","unstructured":"Babenko A, Slesarev A, Chigorin A, Lempitsky VS (2014) Neural codes for image retrieval. In: Computer vision - ECCV 2014 - 13th European conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I, vol 8689. Springer, pp 584\u2013599","DOI":"10.1007\/978-3-319-10590-1_38"},{"key":"1625_CR12","doi-asserted-by":"crossref","unstructured":"Gordo A, Almazan J, Revaud J, Larlus D (2016) Deep image retrieval: Learning global representations for image search. In: Computer vision - ECCV 2016 - 14th European conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VI, vol 9910, pp 241\u2013257","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"1625_CR13","unstructured":"Babenko A, Lempitsky VS (2015) Aggregating local deep convolutional features for image retrieval. In: 2015 IEEE international conference on computer vision (ICCV). IEEE, pp 1269\u20131277"},{"key":"1625_CR14","doi-asserted-by":"crossref","unstructured":"Kalantidis Y, Mellina C, Osindero S (2016) Cross-dimensional weighting for aggregated deep convolutional features. In: Computer vision - ECCV 2016 workshops - Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part I, vol 9913, pp 685\u2013701","DOI":"10.1007\/978-3-319-46604-0_48"},{"key":"1625_CR15","unstructured":"Tolias G, Sicre R, J\u00e9gou H (2016) Particular object retrieval with integral max-pooling of CNN activations. In: 4th international conference on learning representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings"},{"key":"1625_CR16","doi-asserted-by":"crossref","unstructured":"Zagoruyko S, Komodakis N (2015) Learning to compare image patches via convolutional neural networks. In: IEEE conference on computer vision and pattern recognition, CVPR 2015, Boston, MA, USA, June 7-12, 2015. IEEE, pp 4353\u20134361","DOI":"10.1109\/CVPR.2015.7299064"},{"key":"1625_CR17","unstructured":"Yingying Z, Jiong W, Lingxi X, Liang Z (2018) Attention-based pyramid aggregation network for visual place recognition. In: 2018 ACM multimedia conference on multimedia conference, MM 2018, Seoul, Republic of Korea, October 22-26, 2018. ACM, pp 99\u2013107"},{"key":"1625_CR18","doi-asserted-by":"crossref","unstructured":"Chen Z, Lin J, Chandrasekhar V, Duan L-Y (2018) Gated square-root pooling for image instance retrieval. In: 2018 IEEE International Conference on Image Processing, ICIP 2018, Athens, Greece, October 7-10, 2018, pp 1982\u20131986","DOI":"10.1109\/ICIP.2018.8451486"},{"key":"1625_CR19","doi-asserted-by":"crossref","unstructured":"Datar M, Immorlica N, Indyk P, Mirrokni VS (2004) Locality-sensitive hashing scheme based on p-stable distributions. In: Proceedings of the 20th ACM symposium on computational geometry, Brooklyn, New York, USA, June 8-11, 2004. ACM Press, pp 253\u2013262","DOI":"10.1145\/997817.997857"},{"key":"1625_CR20","unstructured":"Norouzi M, Blei DM (2011) Minimal loss hashing for compact binary codes. In: Proceedings of the 28th international conference on machine learning, ICML 2011, Bellevue, Washington, USA, June 28 - July 2, 2011. Omnipress, pp 353\u2013360"},{"key":"1625_CR21","unstructured":"Liu W, Wang J, Ji R, Jiang Y-G, Chang S-F (2012) Supervised hashing with kernels. In: 2012 IEEE conference on computer vision and pattern recognition, Providence, RI, USA, June 16-21, 2012. IEEE Computer Society, pp 2074\u20132081"},{"issue":"1","key":"1625_CR22","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H J\u00e9gou","year":"2011","unstructured":"J\u00e9gou H, Douze M, Schmid C (2011) Product quantization for nearest neighbor search. IEEE Trans Pattern Anal Mach Intell 33(1):117\u2013128","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1625_CR23","unstructured":"Zhang T, Du C, Wang J (2014) Composite quantization for approximate nearest neighbor search. In: Proceedings of the 31th international conference on machine learning, ICML 2014, Beijing, China, 21-26 June 2014. JMLR.org, pp 838\u2013846"},{"issue":"11","key":"1625_CR24","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1080\/14786440109462720","volume":"2","author":"K Pearson","year":"1901","unstructured":"Pearson K (1901) Liii. on lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science 2(11):559\u2013572","journal-title":"The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science"},{"issue":"6","key":"1625_CR25","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1037\/h0071325","volume":"24","author":"H Hotelling","year":"1932","unstructured":"Hotelling H (1932) Analysis of a complex of statistical variables into principal components. J Educ Psychol 24(6):417\u2013441","journal-title":"J Educ Psychol"},{"key":"1625_CR26","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten L, Hinton GE (2008) Visualizing data using t-sne. J Mach Learn Res 9:2579\u20132605","journal-title":"J Mach Learn Res"},{"issue":"5786","key":"1625_CR27","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov R (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504\u2013507","journal-title":"Science"},{"key":"1625_CR28","unstructured":"Krizhevsky A, Hinton GE (2011) Using very deep autoencoders for content-based image retrieval. In: ESANN 2011, 19th European symposium on artificial neural networks, Bruges, Belgium, April 27-29, 2011, Proceedings"},{"key":"1625_CR29","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.neucom.2015.08.104","volume":"184","author":"Y Wang","year":"2016","unstructured":"Wang Y, Yao H, Zhao S (2016) Auto-encoder based dimensionality reduction. Neurocomputing 184:232\u2013242","journal-title":"Neurocomputing"},{"issue":"3","key":"1625_CR30","doi-asserted-by":"publisher","first-page":"1068","DOI":"10.1109\/JSTARS.2016.2621011","volume":"10","author":"E Li","year":"2017","unstructured":"Li E, Du P, Samat A, Meng Y, Che M (2017) Mid-level feature representation via sparse autoencoder for remotely sensed scene classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 10(3):1068\u20131081","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"issue":"7","key":"1625_CR31","first-page":"3289","volume":"29","author":"W Luo","year":"2017","unstructured":"Luo W, Li J, Yang J, Xu W, Zhang J (2017) Convolutional sparse autoencoders for image classification. IEEE Trans Neural Netw Learning Sys 29(7):3289\u20133294","journal-title":"IEEE Trans Neural Netw Learning Sys"},{"key":"1625_CR32","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.patrec.2017.07.016","volume":"105","author":"M Ribeiro","year":"2018","unstructured":"Ribeiro M, Lazzaretti AE, Lopes HS (2018) A study of deep convolutional auto-encoders for anomaly detection in videos. Pattern Recogn Lett 105:13\u201322","journal-title":"Pattern Recogn Lett"},{"key":"1625_CR33","doi-asserted-by":"crossref","unstructured":"Zhou C, Paffenroth RC (2017) Anomaly detection with robust deep autoencoders. In: Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, Halifax, NS, Canada, August 13 - 17, 2017. ACM Press, pp 665\u2013674","DOI":"10.1145\/3097983.3098052"},{"key":"1625_CR34","unstructured":"Kingma DP, Welling M (2014) Auto-encoding variational bayes. In: 2nd international conference on learning representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings"},{"key":"1625_CR35","unstructured":"Mescheder LM, Nowozin S, Geiger A (2017) Adversarial variational bayes: unifying variational autoencoders and generative adversarial networks. In: Proceedings of the 34th international conference on machine learning, ICML 2017, Sydney, NSW, Australia, vol 70. PMLR, pp 2391\u20132400"},{"key":"1625_CR36","doi-asserted-by":"crossref","unstructured":"Masci J, Meier U, Ciresan DC, Schmidhuber J (2011) Stacked convolutional auto-encoders for hierarchical feature extraction. In: Artificial neural networks and machine learning - ICANN 2011 - 21st International Conference on Artificial Neural Networks, Espoo, Finland, vol 6791. Springer, pp 52\u201359","DOI":"10.1007\/978-3-642-21735-7_7"},{"key":"1625_CR37","unstructured":"Arjovsky M, Chintala S, Bottou L (2017) Wasserstein gan. CoRR, arXiv:1701.07875"},{"key":"1625_CR38","doi-asserted-by":"crossref","unstructured":"Villani C (2003) Topics in optimal transportation. Ams Graduate Studies in Mathematics: 370","DOI":"10.1090\/gsm\/058"},{"key":"1625_CR39","unstructured":"Frogner C, Zhang C, Mobahi H, Araya-Polo M, Poggio TA (2015) Learning with a wasserstein loss. In: Advances in neural information processing systems 28: annual conference on neural information processing systems 2015, December 7-12, 2015, Montreal, Quebec, Canada, pp 2053\u20132061"},{"key":"1625_CR40","doi-asserted-by":"crossref","unstructured":"Gong Y, Wang L, Guo R, Lazebnik S (2014) Multi-scale orderless pooling of deep convolutional activation features. In: Computer vision - ECCV 2014 - 13th European conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VII, pp 392\u2013407","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"1625_CR41","unstructured":"Yandex AB, Lempitsky V (2015) Aggregating local deep features for image retrieval. In: 2015 IEEE international conference on computer vision, ICCV 2015, Santiago, Chile, December 7-13, 2015, pp 1269\u20131277"},{"issue":"66-71","key":"1625_CR42","first-page":"13","volume":"10","author":"L Van Der Maaten","year":"2007","unstructured":"Van Der Maaten L, Postma E, Van den Herik J (2007) Dimensionality reduction: a comparative review. J Mach Learn Res - JMLR 10(66-71):13","journal-title":"J Mach Learn Res - JMLR"},{"key":"1625_CR43","doi-asserted-by":"crossref","unstructured":"J\u00e9gou H, Chum O (2012) Negative evidences and co-occurences in image retrieval: the benefit of PCA and whitening. In: Computer vision - ECCV 2012 - 12th European conference on computer vision, Florence, Italy, October 7-13, 2012, Proceedings, Part II. Springer, Berlin, pp 774\u2013787","DOI":"10.1007\/978-3-642-33709-3_55"},{"issue":"4","key":"1625_CR44","doi-asserted-by":"publisher","first-page":"45","DOI":"10.4018\/IJACI.2017100104","volume":"8","author":"MA Belarbi","year":"2017","unstructured":"Belarbi MA, Mahmoudi S, Belalem G (2017) PCA as dimensionality reduction for large-scale image retrieval systems. Int J Ambient Comput Intell (IJACI) 8(4):45\u201358","journal-title":"Int J Ambient Comput Intell (IJACI)"},{"issue":"7553","key":"1625_CR45","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"issue":"1","key":"1625_CR46","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/s10489-016-0880-1","volume":"47","author":"H Ghodrati","year":"2017","unstructured":"Ghodrati H, Hamza AB (2017) Nonrigid 3d shape retrieval using deep auto-encoders. Appl Intell 47 (1):44\u201361","journal-title":"Appl Intell"},{"issue":"1","key":"1625_CR47","doi-asserted-by":"publisher","first-page":"436","DOI":"10.2991\/ijcis.2018.125905686","volume":"12","author":"FJ Pulgar","year":"2018","unstructured":"Pulgar FJ, Charte F, Rivera AJ, del Jes\u00fas MJ (2018) Aeknn: An autoencoder knn-based classifier with built-in dimensionality reduction. Int J Comput Intell Sys 12(1):436\u2013452","journal-title":"Int J Comput Intell Sys"},{"key":"1625_CR48","unstructured":"Tolstikhin I, Bousquet O, Gelly S, Schoelkopf B (2017) Wasserstein auto-encoders. In: 6th international conference on learning representations, ICLR 2018, Vancouver, BC, Canada. OpenReview.net"},{"key":"1625_CR49","doi-asserted-by":"crossref","unstructured":"Salvador A, Giro-I-Nieto X, Marques F, Satoh S (2016) Faster r-CNN features for instance search. In: 2016 IEEE conference on computer vision and pattern recognition workshops, CVPR workshops 2016, Las Vegas, NV, USA, June 26 - July 1, 2016. IEEE Computer Society, pp 394\u2013401","DOI":"10.1109\/CVPRW.2016.56"},{"key":"1625_CR50","unstructured":"Bousquet O, Gelly S, Tolstikhin I, Simon-Gabriel C-J, Schoelkopf B (2017) From optimal transport to generative modeling: the VEGAN cookbook. CoRR, arXiv:1705.07642"},{"key":"1625_CR51","doi-asserted-by":"crossref","unstructured":"Philbin J, Chum O, Isard M, Sivic J, Zisserman A (2008) Lost in quantization: Improving particular object retrieval in large scale image databases. In: 2008 IEEE computer society conference on computer vision and pattern recognition (CVPR 2008), 24-26 June 2008, Anchorage, Alaska, USA. IEEE Computer Society , pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587635"},{"key":"1625_CR52","doi-asserted-by":"crossref","unstructured":"Philbin J, Chum O, Isard M, Sivic J, Zisserman A (2007) Object retrieval with large vocabularies and fast spatial matching. In: 2007 IEEE computer society conference on computer vision and pattern recognition (CVPR 2007), 18-23 June 2007, Minneapolis, Minnesota, USA. IEEE Computer Society, pp 1\u20138","DOI":"10.1109\/CVPR.2007.383172"},{"key":"1625_CR53","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: 3rd international conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings"},{"key":"1625_CR54","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd international conference on machine learning, ICML 2015, Lille, France, 6-11 July 2015. JMLR.org, pp 448\u2013456"},{"key":"1625_CR55","unstructured":"Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: 3rd international conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-019-01625-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10489-019-01625-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-019-01625-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T01:32:04Z","timestamp":1614648724000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10489-019-01625-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,2]]},"references-count":55,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2020,7]]}},"alternative-id":["1625"],"URL":"https:\/\/doi.org\/10.1007\/s10489-019-01625-y","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,2]]},"assertion":[{"value":"6 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 December 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}