{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T11:58:46Z","timestamp":1746187126661,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031258244"},{"type":"electronic","value":"9783031258251"}],"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\/978-3-031-25825-1_18","type":"book-chapter","created":{"date-parts":[[2023,2,3]],"date-time":"2023-02-03T19:02:52Z","timestamp":1675450972000},"page":"246-261","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["M3T: Multi-class Multi-instance Multi-view Object Tracking for Embodied AI Tasks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6662-4607","authenticated-orcid":false,"given":"Mariia","family":"Khan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6651-2880","authenticated-orcid":false,"given":"Jumana","family":"Abu-Khalaf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6306-3023","authenticated-orcid":false,"given":"David","family":"Suter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3861-1424","authenticated-orcid":false,"given":"Bodo","family":"Rosenhahn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,4]]},"reference":[{"key":"18_CR1","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"18_CR2","unstructured":"MOT15 results. https:\/\/motchallenge.net\/results\/MOT15\/. Accessed 20 Sept 2022"},{"key":"18_CR3","unstructured":"Kolve, E., et al.: AI2-THOR: an interactive 3D environment for visual AI. arXiv preprint arXiv:1712.05474 (2017)"},{"key":"18_CR4","unstructured":"Batra, D., et al.: Rearrangement: a challenge for embodied AI. arXiv preprint arXiv:2011.01975 (2020)"},{"key":"18_CR5","unstructured":"Hall, D., et al.: The robotic vision scene understanding challenge. arXiv preprint arXiv:2009.05246\u00a0(2020)"},{"key":"18_CR6","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.neucom.2019.11.023","volume":"381","author":"G Ciaparrone","year":"2020","unstructured":"Ciaparrone, G., et al.: Deep learning in video multi-object tracking: a survey. Neurocomputing 381, 61\u201388 (2020)","journal-title":"Neurocomputing"},{"key":"18_CR7","unstructured":"Leal-Taix\u00e9, L., et al.: MOT challenge 2015: towards a benchmark for multi-target tracking. arXiv preprint arXiv:1504.01942\u00a0(2015)"},{"key":"18_CR8","unstructured":"Redmon, J., Ali, F.: YOLOv3: an incremental improvement.\u00a0arXiv preprint arXiv:1804.02767\u00a0(2018)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"18_CR11","unstructured":"Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"18_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"18_CR13","unstructured":"Zhu, X., et al.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159\u00a0(2020)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Kotar, K., Mottaghi, R.: Interactron: embodied adaptive object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14860\u201314869 (2022)","DOI":"10.1109\/CVPR52688.2022.01444"},{"key":"18_CR15","unstructured":"Yang, J., et al.: Embodied visual recognition.\u00a0arXiv preprint arXiv:1904.04404\u00a0(2019)"},{"issue":"5","key":"18_CR16","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1109\/TCSVT.2014.2352552","volume":"25","author":"A Li","year":"2015","unstructured":"Li, A., Liu, L., Wang, K., Liu, S., Yan, S.: Clothing attributes assisted person reidentification. IEEE Trans. Circ. Syst. Video Technol. 25(5), 869\u2013878 (2015)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: Person re-identification by symmetry-driven accumulation of local features. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 2360\u20132367. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539926"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Zhao, J., et al.: Heterogeneous relational complement for vehicle re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 205\u2013214 (2021)","DOI":"10.1109\/ICCV48922.2021.00027"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Yu, J., et al.: Camera-tracklet-aware contrastive learning for unsupervised vehicle re-identification. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 905\u2013911. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812007"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Bansal, V., Foresti, G.L., Martinel, N.: Where did i see it? Object instance re-identification with attention. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 298\u2013306 (2021)","DOI":"10.1109\/ICCVW54120.2021.00038"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Bewley, A., et al.: Simple online and realtime tracking. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 3464\u20133468. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3645\u20133649. IEEE (2017)","DOI":"10.1109\/ICIP.2017.8296962"},{"issue":"16","key":"18_CR23","doi-asserted-by":"publisher","first-page":"5608","DOI":"10.3390\/s21165608","volume":"21","author":"X Zhu","year":"2021","unstructured":"Zhu, X., et al.: ViTT: vision transformer tracker. Sensors 21(16), 5608 (2021)","journal-title":"Sensors"},{"key":"18_CR24","unstructured":"Sun, P., et al.: TransTrack: multiple object tracking with transformer.\u00a0arXiv preprint arXiv:2012.15460\u00a0(2020)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., et al.: TrackFormer: multi-object tracking with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8844\u20138854 (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Zeng, F., et al.: MOTR: end-to-end multiple-object tracking with transformer. arXiv preprint arXiv:2105.03247\u00a0(2021)","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Savva, M., et al.: Habitat: a platform for embodied AI research.\u00a0In:\u00a0Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9339\u20139347 (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"issue":"2","key":"18_CR28","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/s11263-020-01375-2","volume":"129","author":"J Luiten","year":"2021","unstructured":"Luiten, J., et al.: HOTA: A higher order metric for evaluating multi-object tracking. Int. J. Comput. Vis. 129(2), 548\u2013578 (2021). https:\/\/doi.org\/10.1007\/s11263-020-01375-2","journal-title":"Int. J. Comput. Vis."},{"key":"18_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/246309","volume":"1","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the clear MOT metrics. EURASIP J. Image Video Process. 1, 1\u201310 (2008). https:\/\/doi.org\/10.1155\/2008\/246309","journal-title":"EURASIP J. Image Video Process."},{"key":"18_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-319-48881-3_2","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"E Ristani","year":"2016","unstructured":"Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for\u00a0multi-target, multi-camera tracking. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17\u201335. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_2"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Weihs, L., et al.: Visual room rearrangement.\u00a0In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5922\u20135931 (2021)","DOI":"10.1109\/CVPR46437.2021.00586"},{"key":"18_CR32","unstructured":"Deitke, M., et al.: ProcTHOR: large-scale embodied AI using procedural generation. arXiv preprint arXiv:2206.06994\u00a0(2022)"},{"key":"18_CR33","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., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Piotr Doll\u00e1r, C., Zitnick, L.: 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"}],"container-title":["Lecture Notes in Computer Science","Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25825-1_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,3]],"date-time":"2023-02-03T19:07:42Z","timestamp":1675451262000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25825-1_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031258244","9783031258251"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25825-1_18","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":"4 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IVCNZ","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Vision Computing New Zealand","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"37","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ivcnz2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ivcnz2022.aut.ac.nz\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"79","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":"14","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":"23","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":"18% - 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":"2.7","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":"3.1","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)"}}]}}