{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:46:44Z","timestamp":1773773204309,"version":"3.50.1"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012519","type":"print"},{"value":"9783030012526","type":"electronic"}],"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\/978-3-030-01252-6_28","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T09:48:05Z","timestamp":1538732885000},"page":"471-488","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Hierarchy of Alternating Specialists for Scene Recognition"],"prefix":"10.1007","author":[{"given":"Hyo Jin","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan-Michael","family":"Frahm","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"28_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/978-3-319-10584-0_22","volume-title":"Computer Vision \u2013 ECCV 2014","author":"P Agrawal","year":"2014","unstructured":"Agrawal, P., Girshick, R., Malik, J.: Analyzing the performance of multilayer neural networks for object recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 329\u2013344. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_22"},{"key":"28_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1007\/978-3-319-46478-7_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K Ahmed","year":"2016","unstructured":"Ahmed, K., Baig, M.H., Torresani, L.: Network of experts for large-scale image categorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 516\u2013532. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_32"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Ahmed, K., Torresani, L.: Branchconnect: Large-scale visual recognition with learned branch connections. In: WACV (2018)","DOI":"10.1109\/WACV.2018.00141"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Aljundi, R., Chakravarty, P., Tuytelaars, T.: Expert gate: Lifelong learning with a network of experts. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.753"},{"key":"28_CR5","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"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.354"},{"key":"28_CR7","unstructured":"Bishop, C.M., Svenskn, M.: Bayesian hierarchical mixtures of experts. In: Uncertainty in Artificial Intelligence (2002)"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Chen, W., Chen, X., Zhang, J., Huang, K.: Beyond triplet loss: a deep quadruplet network for person re-identification. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.145"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, G., Zhou, P., Han, J.: RIFD-CNN: Rotation-invariant and fisher discriminative convolutional neural networks for object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.315"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, X., Lu, J., Feng, J., Yuan, B., Zhou, J.: Scene recognition with objectness. Pattern Recogn. (2018)","DOI":"10.1016\/j.patcog.2017.09.025"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Deng, J., Berg, A.C., Fei-Fei, L.: Hierarchical semantic indexing for large scale image retrieval. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995516"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: Large-scale object classification using label relation graphs. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10590-1_4"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Dixit, M., Chen, S., Gao, D., Rasiwasia, N., Vasconcelos, N.: Scene classification with semantic fisher vectors. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298916"},{"key":"28_CR14","unstructured":"Dixit, M.D., Vasconcelos, N.: Object based scene representations using fisher scores of local subspace projections. In: NIPS (2016)"},{"key":"28_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-319-46475-6_6","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Goo","year":"2016","unstructured":"Goo, W., Kim, J., Kim, G., Hwang, S.J.: Taxonomy-regularized semantic deep convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 86\u2013101. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_6"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Gross, S., Ranzato, M., Szlam, A.: Hard mixtures of experts for large scale weakly supervised vision. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.540"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Guo, S., Huang, W., Wang, L., Qiao, Y.: Locally supervised deep hybrid model for scene recognition. TIP (2017)","DOI":"10.1109\/TIP.2016.2629443"},{"key":"28_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/978-3-642-19318-7_15","volume-title":"Computer Vision \u2013 ACCV 2010","author":"Y Guo","year":"2011","unstructured":"Guo, Y., Zhao, G., Pietik\u00e4inen, M., Xu, Z.: Descriptor learning based on fisher separation criterion for texture classification. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6494, pp. 185\u2013198. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-19318-7_15"},{"key":"28_CR19","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":"28_CR20","doi-asserted-by":"crossref","unstructured":"Herranz, L., Jiang, S., Li, X.: Scene recognition with CNNs: objects, scales and dataset bias. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.68"},{"key":"28_CR21","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. Arxiv preprint arXiv:1503.02531 (2015)"},{"key":"28_CR22","unstructured":"Hwang, S.J., Sigal, L.: A unified semantic embedding: Relating taxonomies and attributes. In: NIPS (2014)"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Jordan, M.I., Jacobs, R.A.: Hierarchical mixtures of experts and the EM algorithm. Neural Comput. (1994)","DOI":"10.1007\/978-1-4471-2097-1_113"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Juneja, M., Vedaldi, A., Jawahar, C., Zisserman, A.: Blocks that shout: distinctive parts for scene classification. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.124"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Khan, S.H., Hayat, M., Porikli, F.: Scene categorization with spectral features. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.601"},{"key":"28_CR26","unstructured":"Kim, J., Park, Y., Kim, G., Hwang, S.J.: SplitNet: learning to semantically split deep networks for parameter reduction and model parallelization. In: ICML (2017)"},{"key":"28_CR27","unstructured":"Krizhevsky, A.: One weird trick for parallelizing convolutional neural networks. arXiv preprint arXiv:1404.5997 (2014)"},{"key":"28_CR28","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)"},{"key":"28_CR29","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"28_CR30","unstructured":"Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Li, F., Neverova, N., Wolf, C., Taylor, G.: Modout: learning multi-modal architectures by stochastic regularization. In: FG (2017)","DOI":"10.1109\/FG.2017.59"},{"key":"28_CR32","unstructured":"Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"28_CR34","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Object recognition from local scale-invariant features. In: ICCV (1999)","DOI":"10.1109\/ICCV.1999.790410"},{"key":"28_CR35","unstructured":"Mousavian, A., Kosecka, J.: Deep convolutional features for image based retrieval and scene categorization. arXiv preprint arXiv:1509.06033 (2015)"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Murdock, C., Li, Z., Zhou, H., Duerig, T.: Blockout: dynamic model selection for hierarchical deep networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.283"},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Murthy, V.N., Singh, V., Chen, T., Manmatha, R., Comaniciu, D.: Deep decision network for multi-class image classification. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.246"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. IJCV (2001)","DOI":"10.1023\/A:1011139631724"},{"key":"28_CR39","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G.: PyTorch: tensors and dynamic neural networks in python with strong GPU acceleration (2017). http:\/\/pytorch.org\/"},{"key":"28_CR40","unstructured":"Qian, Q., Jin, R., Zhu, S., Lin, Y.: Fine-grained visual categorization via multi-stage metric learning. In: CVPR (2015)"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"28_CR42","unstructured":"Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. In: NIPS (2017)"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Das, A., Vedantam, R., Cogswell, M., Parikh, D., Batra, D.: Grad-CAM: why did you say that? Visual explanations from deep networks via gradient-based localization. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"28_CR44","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"28_CR45","doi-asserted-by":"crossref","unstructured":"Somanath, G., Kambhamettu, C.: Abstraction and generalization of 3D structure for recognition in large intra-class variation. In: ACCV (2010)","DOI":"10.1007\/978-3-642-19318-7_38"},{"key":"28_CR46","unstructured":"Srivastava, N., Salakhutdinov, R.R.: Discriminative transfer learning with tree-based priors. In: NIPS (2013)"},{"key":"28_CR47","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"28_CR48","unstructured":"Tu, Z.: Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering. In: CVPR (2005)"},{"key":"28_CR49","unstructured":"Urban, G., et al.: Do deep convolutional nets really need to be deep and convolutional? arXiv preprint arXiv:1603.05691 (2016)"},{"key":"28_CR50","unstructured":"Wang, J., Liu, Z., Wu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras. In: CVPR (2012)"},{"key":"28_CR51","doi-asserted-by":"crossref","unstructured":"Wang, L., Guo, S., Huang, W., Xiong, Y., Qiao, Y.: Knowledge guided disambiguation for large-scale scene classification with multi-resolution CNNs. TIP (2017)","DOI":"10.1109\/TIP.2017.2675339"},{"key":"28_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, L., Wang, Y., Zhang, B., Qiao, Y.: Weakly supervised patchnets: describing and aggregating local patches for scene recognition. TIP (2017)","DOI":"10.1109\/TIP.2017.2666739"},{"key":"28_CR53","unstructured":"Warde-Farley, D., Rabinovich, A., Anguelov, D.: Self-informed neural network structure learning. arXiv preprint arXiv:1412.6563 (2014)"},{"key":"28_CR54","doi-asserted-by":"crossref","unstructured":"Wu, R., Wang, B., Wang, W., Yu, Y.: Harvesting discriminative meta objects with deep CNN features for scene classification. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.152"},{"key":"28_CR55","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"28_CR56","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Wu, J., Yuan, J.: mCENTRIST: a multi-channel feature generation mechanism for scene categorization. TIP (2014)","DOI":"10.1109\/TIP.2013.2295756"},{"key":"28_CR57","doi-asserted-by":"crossref","unstructured":"Yan, Z., et al.: HD-CNN: hierarchical deep convolutional neural networks for large scale visual recognition. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"28_CR58","unstructured":"Zhao, B., Li, F., Xing, E.P.: Large-scale category structure aware image categorization. In: NIPS (2011)"},{"key":"28_CR59","doi-asserted-by":"crossref","unstructured":"Zheng, W.S., Gong, S., Xiang, T.: Person re-identification by probabilistic relative distance comparison. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995598"},{"key":"28_CR60","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Object detectors emerge in deep scene CNNs. In: ICLR (2014)"},{"key":"28_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"28_CR62","doi-asserted-by":"crossref","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: A 10 million image database for scene recognition. PAMI (2017)","DOI":"10.1167\/17.10.296"},{"key":"28_CR63","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: NIPS (2014)"}],"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\/978-3-030-01252-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T15:48:22Z","timestamp":1773762502000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01252-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012519","9783030012526"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01252-6_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 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"}]}}