{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T21:08:51Z","timestamp":1742936931127,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031490101"},{"type":"electronic","value":"9783031490118"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-49011-8_44","type":"book-chapter","created":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T16:03:27Z","timestamp":1702569807000},"page":"561-573","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vision Transformers Applied to Indoor Room Classification"],"prefix":"10.1007","author":[{"given":"Bruno","family":"Veiga","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8248-080X","authenticated-orcid":false,"given":"Tiago","family":"Pinto","sequence":"additional","affiliation":[]},{"given":"R\u00faben","family":"Teixeira","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5143-1711","authenticated-orcid":false,"given":"Carlos","family":"Ramos","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,15]]},"reference":[{"key":"44_CR1","unstructured":"Ahmed, E., Moustafa, M.: House price estimation from visual and textual features (2016). arXiv:1609.08399"},{"key":"44_CR2","doi-asserted-by":"publisher","unstructured":"Ali, N., Zafar, B.: 15-Scene Image Dataset (2018). https:\/\/doi.org\/10.6084\/m9.figshare.7007177.v1, https:\/\/figshare.com\/articles\/dataset\/15-Scene_Image_Dataset\/7007177","DOI":"10.6084\/m9.figshare.7007177.v1"},{"key":"44_CR3","doi-asserted-by":"publisher","unstructured":"Boiman, O., Shechtman, E., Irani, M.: In defense of nearest-neighbor based image classification. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138 (2008). https:\/\/doi.org\/10.1109\/CVPR.2008.4587598","DOI":"10.1109\/CVPR.2008.4587598"},{"key":"44_CR4","doi-asserted-by":"publisher","unstructured":"Bosch, A., Zisserman, A., Munoz, X.: Image classification using random forests and ferns. In: 2007 IEEE 11th International Conference on Computer Vision, pp. 1\u20138 (2007). https:\/\/doi.org\/10.1109\/ICCV.2007.4409066","DOI":"10.1109\/ICCV.2007.4409066"},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Chhikara, P., Goyal, A., Sharma, C.: Re- tagger: A light-weight real-estate image classifier. In: Amini, M.R., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds.) Machine Learning and Knowledge Discovery in Databases, pp. 627\u2013630. Springer Nature Switzerland, Cham (2023)","DOI":"10.1007\/978-3-031-26422-1_44"},{"key":"44_CR6","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"44_CR7","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"Espinace, P., Kollar, T., Soto, A., Roy, N.: Indoor scene recognition through object detection. In: 2010 IEEE International Conference on Robotics and Automation, pp. 1406\u20131413. IEEE (2010)","DOI":"10.1109\/ROBOT.2010.5509682"},{"key":"44_CR9","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. In: Computer Vision and Pattern Recognition Workshop (2004)"},{"key":"44_CR10","doi-asserted-by":"publisher","unstructured":"Hayat, M., Khan, S.H., Bennamoun, M., An, S.: A spatial layout and scale invariant feature representation for indoor scene classification. IEEE Trans. Image Process. 25(10), 4829\u20134841 (2016). https:\/\/doi.org\/10.1109\/TIP.2016.2599292","DOI":"10.1109\/TIP.2016.2599292"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"44_CR12","doi-asserted-by":"crossref","unstructured":"Koch, D., Despotovic, M., Leiber, S., Sakeena, M., Doeller, M., Zeppelzauer, M.: Real estate image analysis: A literature review. J. R. Estate Lit. 27, 269\u2013300 (2019). https:\/\/doi.org\/10.22300\/0927-7544.27.2.269","DOI":"10.22300\/0927-7544.27.2.269"},{"key":"44_CR13","doi-asserted-by":"publisher","unstructured":"Li, J., Huang, S., He, R., Qian, K.: Image classification based on fuzzy support vector machine. In: 2008 International Symposium on Computational Intelligence and Design, vol. 1, pp. 68\u201371 (2008). https:\/\/doi.org\/10.1109\/ISCID.2008.51","DOI":"10.1109\/ISCID.2008.51"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s (2022). ArXiv:abs\/2201.03545, https:\/\/arxiv.org\/abs\/2201.03545","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"44_CR15","doi-asserted-by":"publisher","unstructured":"Lu, L., Toyama, K., Hager, G.: A two level approach for scene recognition. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol. 1, pp. 688\u2013695 (2005). https:\/\/doi.org\/10.1109\/CVPR.2005.51","DOI":"10.1109\/CVPR.2005.51"},{"key":"44_CR16","doi-asserted-by":"crossref","unstructured":"Mar\u00e9e, R., Geurts, P., Piater, J., Wehenkel, L.: Biomedical image classification with random subwindows and decision trees. In: International Workshop on Computer Vision for Biomedical Image Applications, pp. 220\u2013229. Springer, Berlin (2005)","DOI":"10.1007\/11569541_23"},{"key":"44_CR17","unstructured":"Mazurov, M.: House rooms & streets image dataset (2022). https:\/\/www.kaggle.com\/datasets\/mikhailma\/house-rooms-streets-image-dataset. Accessed 12 Dec 2022"},{"key":"44_CR18","unstructured":"Mokhairi, M., Engku Fadzli Hasan, S.A., Nur Shazwani, K.: Comparison of image classification techniques using caltech 101 dataset. J. Theor. Appl. Inf. Technol. 71(1), 79\u201386 (2015)"},{"key":"44_CR19","doi-asserted-by":"crossref","unstructured":"Nascimento, G., Laranjeira, C., Braz, V., Lacerda, A., Nascimento, E.R.: A robust indoor scene recognition method based on sparse representation. In: Mendoza, M., Velast\u00edn, S. (eds.) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, pp. 408\u2013415. Springer International Publishing, Cham (2018)","DOI":"10.1007\/978-3-319-75193-1_49"},{"issue":"3","key":"44_CR20","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A Oliva","year":"2001","unstructured":"Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. Int. J. Comput. Vision 42(3), 145\u2013175 (2001)","journal-title":"Int. J. Comput. Vision"},{"key":"44_CR21","unstructured":"Papers with code: Image classification on imagenet (2022). https:\/\/paperswithcode.com\/sota\/image-classification-on-imagenet. Accessed 12 Dec 2022"},{"key":"44_CR22","doi-asserted-by":"publisher","unstructured":"Quattoni, A., Torralba, A.: Recognizing indoor scenes. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 413\u2013420 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206537","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"44_CR23","unstructured":"Roberts, L.G.: Machine perception of three-dimensional solids. Ph.D. thesis, Massachusetts Institute of Technology (1963)"},{"issue":"1","key":"44_CR24","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","volume":"77","author":"BC Russell","year":"2008","unstructured":"Russell, B.C., Torralba, A., Murphy, K.P., Freeman, W.T.: Labelme: a database and web-based tool for image annotation. Int. J. Comput. Vision 77(1), 157\u2013173 (2008)","journal-title":"Int. J. Comput. Vision"},{"issue":"1","key":"44_CR25","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1023\/A:1007963824710","volume":"23","author":"SM Smith","year":"1997","unstructured":"Smith, S.M., Brady, J.M.: Susan-a new approach to low level image processing. Int. J. Comput. Vision 23(1), 45\u201378 (1997)","journal-title":"Int. J. Comput. Vision"},{"key":"44_CR26","unstructured":"Sullivan, E.: Facial Recognition Technology (2021). https:\/\/leg.mt.gov\/content\/Committees\/Interim\/2021-2022\/EconomicAffairs\/Meetings\/September2021\/facial-recognition-technology.pdf"},{"key":"44_CR27","doi-asserted-by":"crossref","unstructured":"Szummer, M., Picard, R.W.: Indoor-outdoor image classification. In: Proceedings 1998 IEEE International Workshop on Content-Based Access of Image and Video Database, pp. 42\u201351. IEEE (1998)","DOI":"10.1109\/CAIVD.1998.646032"},{"key":"44_CR28","unstructured":"Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"44_CR29","doi-asserted-by":"publisher","unstructured":"Vailaya, A., Jain, A., Zhang, H.J.: On image classification: City images vs. landscapes. Pattern Recognit. 31(12), 1921\u20131935 (1998). https:\/\/doi.org\/10.1016\/S0031-3203(98)00079-X, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S003132039800079X","DOI":"10.1016\/S0031-3203(98)00079-X"},{"key":"44_CR30","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"44_CR31","doi-asserted-by":"publisher","unstructured":"Wang, W., Dong, S., Zou, K., LI, W.S.: Room classification in floor plan recognition. In: 2020 4th International Conference on Advances in Image Processing, pp. 48\u201354. ICAIP 2020, Association for Computing Machinery, New York, NY, USA (2021). https:\/\/doi.org\/10.1145\/3441250.3441265","DOI":"10.1145\/3441250.3441265"},{"key":"44_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.104039","volume":"134","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Sacks, R., Yeung, T.: Exploring graph neural networks for semantic enrichment: Room type classification. Autom. Constr. 134, 104039 (2022)","journal-title":"Autom. Constr."},{"issue":"1","key":"44_CR33","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s11263-014-0748-y","volume":"119","author":"J Xiao","year":"2016","unstructured":"Xiao, J., Ehinger, K.A., Hays, J., Torralba, A., Oliva, A.: Sun database: Exploring a large collection of scene categories. Int. J. Comput. Vision 119(1), 3\u201322 (2016)","journal-title":"Int. J. Comput. Vision"},{"key":"44_CR34","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: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3485\u20133492. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"44_CR35","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: Coca: Contrastive captioners are image-text foundation models (2022). arXiv:2205.01917"},{"key":"44_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: A 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2017)","DOI":"10.1167\/17.10.296"}],"container-title":["Lecture Notes in Computer Science","Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-49011-8_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T01:19:23Z","timestamp":1730855963000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-49011-8_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031490101","9783031490118"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-49011-8_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"15 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EPIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"EPIA Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Faial Island","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"epia2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/epia2023.inesctec.pt\/","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 (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"163","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"85","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"52% - 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 (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}