{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T10:51:08Z","timestamp":1761648668714,"version":"3.37.3"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208868"},{"type":"electronic","value":"9783030208875"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-20887-5_16","type":"book-chapter","created":{"date-parts":[[2019,5,27]],"date-time":"2019-05-27T12:03:59Z","timestamp":1558958639000},"page":"249-265","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["An Unsupervised Deep Learning Framework via Integrated Optimization of Representation Learning and GMM-Based Modeling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2629-1198","authenticated-orcid":false,"given":"Jinghua","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7576-3999","authenticated-orcid":false,"given":"Jianmin","family":"Jiang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,5,28]]},"reference":[{"key":"16_CR1","doi-asserted-by":"publisher","DOI":"10.1201\/b15410","volume-title":"Data Clustering: Algorithms and Applications","author":"CC Aggarwal","year":"2013","unstructured":"Aggarwal, C.C., Reddy, C.K.: Data Clustering: Algorithms and Applications, 1st edn. Chapman & Hall\/CRC, Boca Raton (2013)","edition":"1"},{"key":"16_CR2","series-title":"Information Science and Statistics","volume-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning. Information Science and Statistics. Springer, New York (2006)"},{"issue":"8","key":"16_CR3","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1109\/TPAMI.2012.230","volume":"35","author":"J Bruna","year":"2013","unstructured":"Bruna, J., Mallat, S.: Invariant scattering convolution networks. TPAMI 35(8), 1872\u20131886 (2013)","journal-title":"TPAMI"},{"issue":"12","key":"16_CR4","first-page":"1624","volume":"17","author":"D Cai","year":"2005","unstructured":"Cai, D., He, X., Han, J.: Document clustering using locality preserving indexing. TKDE 17(12), 1624\u20131637 (2005)","journal-title":"TKDE"},{"issue":"1","key":"16_CR5","first-page":"1","volume":"3","author":"T Cali\u00e5Ski","year":"1974","unstructured":"Cali\u00e5Ski, T., Harabasz, J.: A dendrite method for cluster analysis. Commun. Stat. 3(1), 1\u201327 (1974)","journal-title":"Commun. Stat."},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Cai, D.: Large scale spectral clustering with landmark-based representation. In: AAAI, pp. 313\u2013318 (2011)","DOI":"10.1609\/aaai.v25i1.7900"},{"key":"16_CR7","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning 15, 215\u2013223 (2011)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Deng, L., Chen, J.: Sequence classification using the high-level features extracted from deep neural networks. In: ICASSP, pp. 6844\u20136848 (2014)","DOI":"10.1109\/ICASSP.2014.6854926"},{"issue":"1","key":"16_CR9","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/TPAMI.2008.277","volume":"32","author":"C Ding","year":"2010","unstructured":"Ding, C., Li, T., Jordan, M.I.: Convex and semi-nonnegative matrix factorizations. TPAMI 32(1), 45\u201355 (2010)","journal-title":"TPAMI"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Dizaji, K.G., Herandi, A., Huang, H.: Deep clustering via joint convolutional autoencoder embedding and relative entropy minimization. In: ICCV, pp. 5747\u20135756 (2017)","DOI":"10.1109\/ICCV.2017.612"},{"issue":"4","key":"16_CR11","doi-asserted-by":"publisher","first-page":"101:1","DOI":"10.1145\/2185520.2185597","volume":"31","author":"C Doersch","year":"2012","unstructured":"Doersch, C., Singh, S., Gupta, A., Sivic, J., Efros, A.A.: What makes paris look like paris? ACM Trans. Graph. 31(4), 101:1\u2013101:9 (2012)","journal-title":"ACM Trans. Graph."},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"5","key":"16_CR13","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.1109\/TASL.2010.2082532","volume":"19","author":"G Heigold","year":"2011","unstructured":"Heigold, G., Ney, H., Lehnen, P., Gass, T., Schluter, R.: Equivalence of generative and log-linear models. IEEE Trans. Audio Speech Lang. Process. 19(5), 1138\u20131148 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"16_CR14","unstructured":"Heigold, G.: A log-linear discriminative modeling framework for speech recognition. Ph.D. dissertation, Rwth Aachen (2010)"},{"issue":"5786","key":"16_CR15","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"G Hinton","year":"2006","unstructured":"Hinton, G., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006)","journal-title":"Science"},{"key":"16_CR16","unstructured":"Law, M.T., Urtasun, R., Zemel, R.S.: Deep spectral clustering learning. In: ICML, vol. 70, pp. 1985\u20131994 (2017)"},{"issue":"11","key":"16_CR17","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"16_CR18","first-page":"361","volume":"5","author":"DD Lewis","year":"2004","unstructured":"Lewis, D.D., Yang, Y., Rose, T.G., Li, F.: RCV1: a new benchmark collection for text categorization research. J. Mach. Learn. Res. 5, 361\u2013397 (2004)","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"16_CR19","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S Lloyd","year":"1982","unstructured":"Lloyd, S.: Least squares quantization in PCM. IEEE Trans. Inf. Theory 28(2), 129\u2013137 (1982)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"16_CR20","unstructured":"Maaten, L.: Learning a parametric embedding by preserving local structure. In: Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics, pp. 384\u2013391 (2009)"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Nakayama, H., Harada, T., Kuniyoshi, Y.: Global Gaussian approach for scene categorization using information geometry, pp. 2336\u20132343 (2010)","DOI":"10.1109\/CVPR.2010.5539921"},{"key":"16_CR22","unstructured":"Nene, S.A., Nayar, S.K., Murase, H.: Columbia university image library (coil-100) (1996)"},{"key":"16_CR23","unstructured":"Nene, S.A., Nayar, S.K., Murase, H.: Columbia university image library (coil-20) (1996)"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: CVPR, pp. 1520\u20131528 (2015)","DOI":"10.1109\/ICCV.2015.178"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Paulik, M.: Lattice-based training of bottleneck feature extraction neural networks. In: INTERSPEECH (2013)","DOI":"10.21437\/Interspeech.2013-44"},{"key":"16_CR26","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Kingsbury, B., Ramabhadran, B.: Auto-encoder bottleneck features using deep belief networks. In: ICASSP, pp. 4153\u20134156 (2012)","DOI":"10.1109\/ICASSP.2012.6288833"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: CVPR, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"16_CR29","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.cviu.2015.01.005","volume":"134","author":"G Serra","year":"2015","unstructured":"Serra, G., Grana, C., Manfredi, M., Cucchiara, R.: Gold: Gaussians of local descriptors for image representation. Comput. Vis. Image Underst. 134, 22\u201332 (2015)","journal-title":"Comput. Vis. Image Underst."},{"key":"16_CR30","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR 15, 1929\u20131958 (2014)","journal-title":"JMLR"},{"key":"16_CR31","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1109\/TNNLS.2012.2183645","volume":"23","author":"A Stuhlsatz","year":"2012","unstructured":"Stuhlsatz, A., Lippel, J., Zielke, T.: Feature extraction with deep neural networks by a generalized discriminant analysis. IEEE Trans. Neural Netw. Learn. Syst. 23, 596\u2013608 (2012)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"16_CR32","unstructured":"Trigeorgis, G., Bousmalis, K., Zafeiriou, S., Schuller, B.W.: A deep semi-NMF model for learning hidden representations. In: ICML, pp. II-1692\u2013II-1700 (2014)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"T\u00fcske, Z., Tahir, M.A., Schl\u00fcter, R., Ney, H.: Integrating Gaussian mixtures into deep neural networks: softmax layer with hidden variables. In: ICASSP, pp. 4285\u20134289 (2015)","DOI":"10.1109\/ICASSP.2015.7178779"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Variani, E., Mcdermott, E., Heigold, G.: A Gaussian mixture model layer jointly optimized with discriminative features within a deep neural network architecture. In: ICASSP, pp. 4270\u20134274 (2015)","DOI":"10.1109\/ICASSP.2015.7178776"},{"key":"16_CR35","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. JMLR 11, 3371\u20133408 (2010)","journal-title":"JMLR"},{"issue":"1","key":"16_CR36","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/TCSVT.2016.2586853","volume":"28","author":"J Wang","year":"2018","unstructured":"Wang, J., Wang, G.: Hierarchical spatial sum-product networks for action recognition in still images. IEEE Trans. Circuits Syst. Video Technol. 28(1), 90\u2013100 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"16_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1007\/978-3-319-46454-1_40","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Wang","year":"2016","unstructured":"Wang, J., Wang, Z., Tao, D., See, S., Wang, G.: Learning common and specific features for RGB-D semantic segmentation with deconvolutional networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 664\u2013679. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_40"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Q., Li, P., Zhang, L.: G $$^2$$ DeNet: global gaussian distribution embedding network and its application to visual recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.689"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Q., Li, P., Zuo, W., Zhang, L.: RAID-G: robust estimation of approximate infinite dimensional Gaussian with application to material recognition. In: CVPR, pp. 4433\u20134441 (2016)","DOI":"10.1109\/CVPR.2016.480"},{"key":"16_CR40","unstructured":"Xie, J., Girshick, R., Farhadi, A.: Unsupervised deep embedding for clustering analysis. In: ICML, pp. 478\u2013487"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Xu, W., Liu, X., Gong, Y.: Document clustering based on non-negative matrix factorization. In: Proceedings of the ACM SIGIR 2003, pp. 267\u2013273 (2003)","DOI":"10.1145\/860484.860485"},{"key":"16_CR42","first-page":"3861","volume":"70","author":"B Yang","year":"2017","unstructured":"Yang, B., Fu, X., Sidiropoulos, N.D., Hong, M.: Towards k-means-friendly spaces: simultaneous deep learning and clustering. ICML 70, 3861\u20133870 (2017)","journal-title":"ICML"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Yang, J., Parikh, D., Batra, D.: Joint unsupervised learning of deep representations and image clusters. In: CVPR, pp. 5147\u20135156 (2016)","DOI":"10.1109\/CVPR.2016.556"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"You, C., Robinson, D.P., Vidal, R.: Scalable sparse subspace clustering by orthogonal matching pursuit. In: CVPR, pp. 3918\u20133927, June 2016","DOI":"10.1109\/CVPR.2016.425"},{"key":"16_CR45","first-page":"1601","volume":"17","author":"L Zelnik-Manor","year":"2004","unstructured":"Zelnik-Manor, L.: Self-tuning spectral clustering. NIPS 17, 1601\u20131608 (2004)","journal-title":"NIPS"},{"key":"16_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1007\/978-3-642-33718-5_31","volume-title":"Computer Vision \u2013 ECCV 2012","author":"W Zhang","year":"2012","unstructured":"Zhang, W., Wang, X., Zhao, D., Tang, X.: Graph degree linkage: agglomerative clustering on a directed graph. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 428\u2013441. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33718-5_31"},{"issue":"11","key":"16_CR47","doi-asserted-by":"publisher","first-page":"3056","DOI":"10.1016\/j.patcog.2013.04.013","volume":"46","author":"W Zhang","year":"2013","unstructured":"Zhang, W., Zhao, D., Wang, X.: Agglomerative clustering via maximum incremental path integral. Pattern Recognit. 46(11), 3056\u20133065 (2013)","journal-title":"Pattern Recognit."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20887-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,18]],"date-time":"2022-09-18T18:03:39Z","timestamp":1663524219000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20887-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208868","9783030208875"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20887-5_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"28 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}