{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T00:55:16Z","timestamp":1771030516228,"version":"3.50.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031270765","type":"print"},{"value":"9783031270772","type":"electronic"}],"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\/978-3-031-27077-2_41","type":"book-chapter","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:03:10Z","timestamp":1679979790000},"page":"527-538","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["GIGO, Garbage In, Garbage Out: An Urban Garbage Classification Dataset"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0828-0281","authenticated-orcid":false,"given":"Maarten","family":"Sukel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1904-8736","authenticated-orcid":false,"given":"Stevan","family":"Rudinac","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4097-4136","authenticated-orcid":false,"given":"Marcel","family":"Worring","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,29]]},"reference":[{"key":"41_CR1","doi-asserted-by":"crossref","unstructured":"Albert, A., Kaur, J., Gonzalez, M.C.: Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1357\u20131366 (2017)","DOI":"10.1145\/3097983.3098070"},{"key":"41_CR2","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/j.neunet.2021.05.035","volume":"143","author":"J An","year":"2021","unstructured":"An, J., et al.: IGAGCN: information geometry and attention-based spatiotemporal graph convolutional networks for traffic flow prediction. Neural Netw. 143, 355\u2013367 (2021)","journal-title":"Neural Netw."},{"key":"41_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"41_CR4","doi-asserted-by":"crossref","unstructured":"Cai, G., Zhu, Y., Wu, Y., Jiang, X., Ye, J., Yang, D.: A multimodal transformer to fuse images and metadata for skin disease classification. The Visual Computer, pp. 1\u201313 (2022)","DOI":"10.1007\/s00371-022-02492-4"},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"41_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Moya, M.G., Phan, T.T., Gatica-Perez, D.: Zurich like new: analyzing open urban multimodal data. In: Proceedings of the 1st International Workshop on Multimedia Computing for Urban Data, pp. 1\u20138 (2021)","DOI":"10.1145\/3475721.3484310"},{"issue":"2","key":"41_CR8","doi-asserted-by":"publisher","first-page":"46","DOI":"10.3169\/mta.7.46","volume":"7","author":"C Gurrin","year":"2019","unstructured":"Gurrin, C., et al.: [invited papers] Comparing approaches to interactive lifelog search at the lifelog search challenge (LSC2018). ITE Trans. Media Technol. Appl. 7(2), 46\u201359 (2019)","journal-title":"ITE Trans. Media Technol. Appl."},{"key":"41_CR9","unstructured":"Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 1025\u20131035 (2017)"},{"key":"41_CR10","doi-asserted-by":"publisher","unstructured":"Harman, D.: Overview of the first TREC conference. In: Proceedings of the 16th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 36\u201347. SIGIR 1993, Association for Computing Machinery, New York, NY, USA (1993). https:\/\/doi.org\/10.1145\/160688.160692. https:\/\/doi.org\/10.1145\/160688.160692","DOI":"10.1145\/160688.160692 10.1145\/160688.160692"},{"key":"41_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"},{"issue":"7","key":"41_CR12","doi-asserted-by":"publisher","first-page":"5966","DOI":"10.1109\/TGRS.2020.3015157","volume":"59","author":"D Hong","year":"2021","unstructured":"Hong, D., Gao, L., Yao, J., Zhang, B., Plaza, A., Chanussot, J.: Graph convolutional networks for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 59(7), 5966\u20135978 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13). Sydney, Australia (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"41_CR14","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25 (2012)"},{"key":"41_CR15","doi-asserted-by":"publisher","unstructured":"Larson, M., et al.: Automatic tagging and geotagging in video collections and communities. In: Proceedings of the 1st ACM International Conference on Multimedia Retrieval. ICMR 2011, Association for Computing Machinery, New York, NY, USA (2011). https:\/\/doi.org\/10.1145\/1991996.1992047. https:\/\/doi.org\/10.1145\/1991996.1992047","DOI":"10.1145\/1991996.1992047 10.1145\/1991996.1992047"},{"key":"41_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"41_CR18","doi-asserted-by":"crossref","unstructured":"Loko\u010d, J., et al.: Is the reign of interactive search eternal? findings from the video browser showdown 2020. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 17(3), 1\u201326 (2021)","DOI":"10.1145\/3445031"},{"key":"41_CR19","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"41_CR20","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3D residual networks. In: proceedings of the IEEE International Conference on Computer Vision, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"41_CR22","doi-asserted-by":"publisher","unstructured":"Smeaton, A.F., Over, P., Kraaij, W.: Evaluation campaigns and TRECVid. In: Proceedings of the 8th ACM International Workshop on Multimedia Information Retrieval, pp. 321\u2013330. MIR 2006, Association for Computing Machinery, New York, NY, USA (2006). https:\/\/doi.org\/10.1145\/1178677.1178722. https:\/\/doi.org\/10.1145\/1178677.1178722","DOI":"10.1145\/1178677.1178722 10.1145\/1178677.1178722"},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"Sukel, M., Rudinac, S., Worring, M.: Multimodal classification of urban micro-events. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1455\u20131463 (2019)","DOI":"10.1145\/3343031.3350967"},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Sukel, M., Rudinac, S., Worring, M.: Urban object detection kit: a system for collection and analysis of street-level imagery. In: Proceedings of the 2020 International Conference on Multimedia Retrieval, pp. 509\u2013516 (2020)","DOI":"10.1145\/3372278.3390708"},{"key":"41_CR25","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":"41_CR26","unstructured":"Tan, M., Le, Q.: EfficientNetV2: smaller models and faster training. In: International Conference on Machine Learning, pp. 10096\u201310106. PMLR (2021)"},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Teichmann, M., Weber, M., Zoellner, M., Cipolla, R., Urtasun, R.: MultiNet: real-time joint semantic reasoning for autonomous driving. In: 2018 IEEE Intelligent Vehicles Symposium (IV), pp. 1013\u20131020. IEEE (2018)","DOI":"10.1109\/IVS.2018.8500504"},{"key":"41_CR28","doi-asserted-by":"crossref","unstructured":"Tobler, W.R.: A computer movie simulating urban growth in the detroit region. Econ. Geograp. 46, 234\u2013240 (1970). http:\/\/www.jstor.org\/stable\/143141","DOI":"10.2307\/143141"},{"key":"41_CR29","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Tech. Rep. CNS-TR-2011-001, California Institute of Technology (2011)"},{"key":"41_CR30","unstructured":"Xu, K., Li, C., Tian, Y., Sonobe, T., Kawarabayashi, K.i., Jegelka, S.: Representation learning on graphs with jumping knowledge networks. In: International Conference on Machine Learning, pp. 5453\u20135462. PMLR (2018)"},{"key":"41_CR31","unstructured":"Xu, P., Zhu, X., Clifton, D.A.: Multimodal learning with transformers: a survey. arXiv preprint arXiv:2206.06488 (2022)"},{"key":"41_CR32","doi-asserted-by":"crossref","unstructured":"Yu, B., Yin, H., Zhu, Z.: Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. arXiv preprint arXiv:1709.04875 (2017)","DOI":"10.24963\/ijcai.2018\/505"},{"key":"41_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hao, Y., Ngo, C.W.: Token shift transformer for video classification. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 917\u2013925 (2021)","DOI":"10.1145\/3474085.3475272"},{"issue":"9","key":"41_CR34","doi-asserted-by":"publisher","first-page":"3848","DOI":"10.1109\/TITS.2019.2935152","volume":"21","author":"L Zhao","year":"2019","unstructured":"Zhao, L., et al.: T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transp. Syst. 21(9), 3848\u20133858 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27077-2_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T04:35:01Z","timestamp":1729139701000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27077-2_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031270765","9783031270772"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27077-2_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"29 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bergen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","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":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","order":10,"name":"conference_id","label":"Conference ID","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":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"267","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":"86","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":"32% - 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":"3","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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}