{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T10:33:15Z","timestamp":1744281195822,"version":"3.40.3"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030012182"},{"type":"electronic","value":"9783030012199"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01219-9_38","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T14:23:51Z","timestamp":1538835831000},"page":"639-656","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Second-Order Democratic Aggregation"],"prefix":"10.1007","author":[{"given":"Tsung-Yu","family":"Lin","sequence":"first","affiliation":[]},{"given":"Subhransu","family":"Maji","sequence":"additional","affiliation":[]},{"given":"Piotr","family":"Koniusz","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"38_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.572"},{"issue":"2","key":"38_CR2","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1002\/mrm.20965","volume":"56","author":"V Arsigny","year":"2006","unstructured":"Arsigny, V., Fillard, P., Pennec, X., Ayache, N.: Log-euclidean metrics for fast and simple calculus on diffusion tensors. Magn. Reson. Med. 56(2), 411\u2013421 (2006)","journal-title":"Magn. Reson. Med."},{"key":"38_CR3","volume-title":"Positive Definite Matrices","author":"R Bhatia","year":"2007","unstructured":"Bhatia, R.: Positive Definite Matrices. Princeton University Press, Princeton (2007)"},{"issue":"4","key":"38_CR4","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1080\/00029890.2000.12005203","volume":"107","author":"R Bhatia","year":"2000","unstructured":"Bhatia, R., Davis, C.: A better bound on the variance. Am. Math. Mon. 107(4), 353\u2013357 (2000)","journal-title":"Am. Math. Mon."},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Boughorbel, S., Tarel, J.P., Boujemaa, N.: Generalized histogram intersection kernel for image recognition. In: ICIP (2005)","DOI":"10.1109\/ICIP.2005.1530353"},{"key":"38_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1007\/978-3-642-33786-4_32","volume-title":"Computer Vision \u2013 ECCV 2012","author":"J Carreira","year":"2012","unstructured":"Carreira, J., Caseiro, R., Batista, J., Sminchisescu, C.: Semantic segmentation with second-order pooling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012 Part VII. LNCS, vol. 7578, pp. 430\u2013443. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33786-4_32"},{"issue":"9","key":"38_CR7","doi-asserted-by":"publisher","first-page":"2161","DOI":"10.1109\/TPAMI.2012.259","volume":"35","author":"A Cherian","year":"2013","unstructured":"Cherian, A., Sra, S., Banerjee, A., Papanikolopoulos, N.: Jensen-Bregman LogDet divergence with application to efficient similarity search for covariance matrices. TPAMI 35(9), 2161\u20132174 (2013)","journal-title":"TPAMI"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Vedaldi, A.: Deep filter banks for texture recognition and segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299007"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Dai, X., Yue-Hei Ng, J., Davis, L.S.: FASON: first and second order information fusion network for texture recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.646"},{"issue":"3","key":"38_CR11","doi-asserted-by":"publisher","first-page":"1102","DOI":"10.1214\/09-AOAS249","volume":"3","author":"IL Dryden","year":"2009","unstructured":"Dryden, I.L., Koloydenko, A., Zhou, D.: Non-euclidean statistics for covariance matrices, with applications to diffusion tensor imaging. Ann. Appl. Stat. 3(3), 1102\u20131123 (2009)","journal-title":"Ann. Appl. Stat."},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"Gao, Y., Beijbom, O., Zhang, N., Darrell, T.: Compact bilinear pooling. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.41"},{"key":"38_CR13","unstructured":"Genevay, A., Peyr\u00e9, G., Cuturi, M.: Learning generative models with sinkhorn divergences (2017). arXiv preprint arXiv:1706.00292"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Gong, Y., Wang, L., Guo, R., Lazebnik, S.: Multi-scale orderless pooling of deep convolutional activation features. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10584-0_26"},{"issue":"6","key":"38_CR15","doi-asserted-by":"publisher","first-page":"2479","DOI":"10.1109\/TIP.2013.2252622","volume":"22","author":"K Guo","year":"2013","unstructured":"Guo, K., Ishwar, P., Konrad, J.: Action recognition from video using feature covariance matrices. Trans. Image Procss. 22(6), 2479\u20132494 (2013)","journal-title":"Trans. Image Procss."},{"key":"38_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Z., Gool, L.V.: A Riemannian network for SPD matrix learning. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.10866"},{"key":"38_CR18","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Vantzos, O., Sminchisescu, C.: Matrix Backpropagation for deep networks with structured layers. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.339"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C.: On the burstiness of visual elements. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206609"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact image representation. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Zisserman, A.: Triangulation embedding and democratic aggregation for image search. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.417"},{"key":"38_CR22","doi-asserted-by":"crossref","unstructured":"Khan, S.H., Hayat, M., Porikli, F.: Scene categorization with spectral features. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.601"},{"issue":"1","key":"38_CR23","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1137\/060659624","volume":"30","author":"PA Knight","year":"2008","unstructured":"Knight, P.A.: The Sinkhorn-Knopp algorithm: convergence and applications. SIAM J. Matrix Anal. Appl. 30(1), 261\u2013275 (2008)","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"38_CR24","unstructured":"Koniusz, P., Yan, F., Gosselin, P., Mikolajczyk, K.: Higher-order occurrence pooling on mid- and low-level features: visual concept detection. Technical report, HAL Id: hal-00922524 (2013)"},{"issue":"2","key":"38_CR25","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1109\/TPAMI.2016.2545667","volume":"39","author":"P Koniusz","year":"2017","unstructured":"Koniusz, P., Yan, F., Gosselin, P., Mikolajczyk, K.: Higher-order occurrence pooling for bags-of-words: visual concept detection. PAMI 39(2), 313\u2013326 (2017)","journal-title":"PAMI"},{"key":"38_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-319-46493-0_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Koniusz","year":"2016","unstructured":"Koniusz, P., Cherian, A., Porikli, F.: Tensor representations via kernel linearization for action recognition from 3D skeletons. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016 Part IV. LNCS, vol. 9908, pp. 37\u201353. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_3"},{"key":"38_CR27","doi-asserted-by":"crossref","unstructured":"Koniusz, P., Tas, Y., Zhang, H., Harandi, M., Porikli, F., Zhang, R.: Museum exhibit identification challenge for the supervised domain adaptation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01270-0_48"},{"key":"38_CR28","doi-asserted-by":"crossref","unstructured":"Koniusz, P., Zhang, H., Porikli, F.: A deeper look at power normalizations. In: CVPR, pp. 5774\u20135783 (2018)","DOI":"10.1109\/CVPR.2018.00605"},{"key":"38_CR29","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Workshop on 3D Representation and Recognition (3DRR) (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"38_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/978-3-642-33712-3_34","volume-title":"Computer Vision \u2013 ECCV 2012","author":"P Li","year":"2012","unstructured":"Li, P., Wang, Q.: Local log-euclidean covariance matrix (L2ECM) for image representation and its applications. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012 Part III. LNCS, vol. 7574, pp. 469\u2013482. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33712-3_34"},{"key":"38_CR31","doi-asserted-by":"crossref","unstructured":"Li, P., Xie, J., Wang, Q., Zuo, W.: Is second-order information helpful for large-scale visual recognition? In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.228"},{"issue":"6","key":"38_CR32","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1109\/TPAMI.2017.2723400","volume":"40","author":"TY Lin","year":"2018","unstructured":"Lin, T.Y., RoyChowdhury, A., Maji, S.: Bilinear convolutional neural networks for fine-grained visual recognition. IEEE TPAMI 40(6), 1309\u20131322 (2018)","journal-title":"IEEE TPAMI"},{"key":"38_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maji, S.: Improved bilinear pooling with CNNs. In: BMVC (2017)","DOI":"10.5244\/C.31.117"},{"key":"38_CR34","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.170"},{"key":"38_CR35","unstructured":"Maji, S., Kannala, J., Rahtu, E., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft (2013)"},{"key":"38_CR36","unstructured":"Mena, G., Belanger, D., Linderman, S., Snoek, J.: Learning latent permutations with Gumbel-Sinkhorn networks (2018). arXiv preprint arXiv:1802.08665"},{"issue":"9","key":"38_CR37","doi-asserted-by":"publisher","first-page":"1797","DOI":"10.1109\/TPAMI.2016.2615621","volume":"39","author":"N Murray","year":"2017","unstructured":"Murray, N., J\u00e9gou, H., Perronnin, F., Zisserman, A.: Interferences in match Kernels. IEEE TPAMI 39(9), 1797\u20131810 (2017)","journal-title":"IEEE TPAMI"},{"key":"38_CR38","doi-asserted-by":"crossref","unstructured":"Negrel, R., Picard, D., Gosselin, P.H.: Compact tensor based image representation for similarity search. In: ICIP (2012)","DOI":"10.1109\/ICIP.2012.6467387"},{"issue":"1","key":"38_CR39","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s11263-005-3222-z","volume":"66","author":"X Pennec","year":"2006","unstructured":"Pennec, X., Fillard, P., Ayache, N.: A Riemannian framework for tensor computing. IJCV 66(1), 41\u201366 (2006)","journal-title":"IJCV"},{"key":"38_CR40","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Dance, C.: Fisher kernels on visual vocabularies for image categorization. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383266"},{"key":"38_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-15561-1_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"F Perronnin","year":"2010","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010 Part IV. LNCS, vol. 6314, pp. 143\u2013156. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_11"},{"key":"38_CR42","doi-asserted-by":"crossref","unstructured":"Pham, N., Pagh, R.: Fast and scalable polynomial kernels via explicit feature maps. In: KDD (2013)","DOI":"10.1145\/2487575.2487591"},{"key":"38_CR43","first-page":"129","volume":"9","author":"T Popoviciu","year":"1935","unstructured":"Popoviciu, T.: Sur les \u00e9quations alg\u00e9briques ayant toutes leurs racines r\u00e9elles. Mathematica 9, 129\u2013145 (1935)","journal-title":"Mathematica"},{"key":"38_CR44","unstructured":"Porikli, F., Tuzel, O.: Covariance tracker. In: CVPR (2006)"},{"key":"38_CR45","doi-asserted-by":"crossref","unstructured":"Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"38_CR46","doi-asserted-by":"crossref","unstructured":"Romero, A., Ter\u00e1n, M.Y., Gouiff\u00e8s, M., Lacassagne, L.: Enhanced local binary covariance matrices for texture analysis and object tracking. In: MIRAGE (2013)","DOI":"10.1145\/2466715.2466733"},{"issue":"3","key":"38_CR47","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/s11263-013-0636-x","volume":"105","author":"J S\u00e1nchez","year":"2013","unstructured":"S\u00e1nchez, J., Perronnin, F., Mensink, T., Verbeek, J.: Image classification with the fisher vector: theory and practice. IJCV 105(3), 222\u2013245 (2013)","journal-title":"IJCV"},{"issue":"8","key":"38_CR48","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1167\/9.8.784","volume":"9","author":"L Sharan","year":"2009","unstructured":"Sharan, L., Rosenholtz, R., Adelson, E.: Material perceprion: what can you see in a brief glance? J. Vis. 9(8), 784 (2009)","journal-title":"J. Vis."},{"key":"38_CR49","doi-asserted-by":"crossref","unstructured":"Shih, Y.F., Yeh, Y.M., Lin, Y.Y., Weng, M.F., Lu, Y.C., Chuang, Y.Y.: Deep co-occurrence feature learning for visual object recognition. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.772"},{"key":"38_CR50","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"38_CR51","doi-asserted-by":"crossref","unstructured":"Song, Y., Zhang, F., Li, Q., Huang, H., O\u2019Donnell, L.J., Cai, W.: Locally-transferred fisher vectors for texture classification. In: ICCV, October 2017","DOI":"10.1109\/ICCV.2017.526"},{"key":"38_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1007\/11744047_45","volume-title":"Computer Vision \u2013 ECCV 2006","author":"O Tuzel","year":"2006","unstructured":"Tuzel, O., Porikli, F., Meer, P.: Region covariance: a fast descriptor for detection and classification. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006 Part II. LNCS, vol. 3952, pp. 589\u2013600. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744047_45"},{"issue":"10","key":"38_CR53","doi-asserted-by":"publisher","first-page":"1713","DOI":"10.1109\/TPAMI.2008.75","volume":"30","author":"O Tuzel","year":"2008","unstructured":"Tuzel, O., Porikli, F., Meer, P.: Pedestrian detection via classification on riemannian manifolds. IEEE TPAMI 30(10), 1713\u20131727 (2008)","journal-title":"IEEE TPAMI"},{"key":"38_CR54","unstructured":"Wang, L., Guo, S., Huang, W., Qiao, Y.: Places205-VGGnet models for scene recognition. CoRR abs\/1508.01667 (2015)"},{"key":"38_CR55","unstructured":"Wang, Z., Vemuri, B.C.: An affine invariant tensor dissimilarity measure and its applications to tensor-valued image segmentation. In: CVPR (2004)"},{"key":"38_CR56","unstructured":"Welinder, P., et al.: Caltech-UCSD Birds 200. Technical report. CNS-TR-2010-001. California Institute of Technology (2010)"},{"key":"38_CR57","doi-asserted-by":"crossref","unstructured":"Yandex, A.B., Lempitsky, V.: Aggregating local deep features for image retrieval. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.150"},{"key":"38_CR58","unstructured":"Yu, K., Salzmann, M.: Second-order convolutional neural networks. abs\/1703.06817 (2017)"},{"key":"38_CR59","doi-asserted-by":"crossref","unstructured":"Yu, K., Salzmann, M.: Statistically-motivated second-order pooling. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01234-2_37"},{"key":"38_CR60","unstructured":"Zhang, Y., Ozay, M., Liu, X., Okatani, T.: Integrating deep features for material recognition. In: ICPR (2016)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01219-9_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T01:18:08Z","timestamp":1665019088000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01219-9_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012182","9783030012199"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01219-9_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}