{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T10:49:20Z","timestamp":1744800560277,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695316"},{"type":"electronic","value":"9783030695323"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69532-3_41","type":"book-chapter","created":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T08:04:33Z","timestamp":1614326673000},"page":"683-699","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Modeling Cross-Modal Interaction in a Multi-detector, Multi-modal Tracking Framework"],"prefix":"10.1007","author":[{"given":"Yiqi","family":"Zhong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suya","family":"You","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulrich","family":"Neumann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,27]]},"reference":[{"key":"41_CR1","doi-asserted-by":"crossref","unstructured":"Yoo, J.H., Kim, Y., Kim, J.S., Choi, J.W.: 3D-CVF: generating joint camera and lidar features using cross-view spatial feature fusion for 3D object detection (2020)","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"41_CR2","doi-asserted-by":"crossref","unstructured":"Liang, M., Yang, B., Chen, Y., Hu, R., Urtasun, R.: Multi-task multi-sensor fusion for 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7345\u20137353 (2019)","DOI":"10.1109\/CVPR.2019.00752"},{"key":"41_CR3","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"41_CR4","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: PV-RCNN: point-voxel feature set abstraction for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10529\u201310538 (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Yilmaz, A., Javed, O., Shah, M.: Object tracking: a survey. ACM Comput. Surv. (CSUR) 38, 13-es (2006)","DOI":"10.1145\/1177352.1177355"},{"key":"41_CR6","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., et al.: MOTS: multi-object tracking and segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00813"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Chu, Q., Ouyang, W., Liu, B., Zhu, F., Yu, N.: DASOT: a unified framework integrating data association and single object tracking for online multi-object tracking. In: AAAI, pp. 10672\u201310679 (2020)","DOI":"10.1609\/aaai.v34i07.6694"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Xu, J., Cao, Y., Zhang, Z., Hu, H.: Spatial-temporal relation networks for multi-object tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3988\u20133998 (2019)","DOI":"10.1109\/ICCV.2019.00409"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Baser, E., Balasubramanian, V., Bhattacharyya, P., Czarnecki, K.: FANTrack: 3D multi-object tracking with feature association network. arxiv abs\/1905.02843 (2019)","DOI":"10.1109\/IVS.2019.8813779"},{"key":"41_CR10","unstructured":"Weng, X., Kitani, K.: A baseline for 3D multi-object tracking (2019)"},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhou, H., Sun, S., Wang, Z., Shi, J., Loy, C.C.: Robust multi-modality multi-object tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2365\u20132374 (2019)","DOI":"10.1109\/ICCV.2019.00245"},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Weng, X., Wang, Y., Man, Y., Kitani, K.: GNN3DMOT: graph neural network for 3D multi-object tracking with multi-feature learning (2020)","DOI":"10.1109\/CVPR42600.2020.00653"},{"key":"41_CR13","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Naval Res. Logist. Q. 2, 83\u201397 (1955)","journal-title":"Naval Res. Logist. Q."},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Ristic, B., Arulampalam, S., Gordon, N.: Beyond the Kalman Filter: Particle Filters for Tracking Applications, vol. 685. Artech House, Boston (2004)","DOI":"10.1155\/S1110865704405095"},{"key":"41_CR15","unstructured":"Zhang, L., Li, Y., Nevatia, R.: Global data association for multi-object tracking using network flows. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2008)"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Frossard, D., Urtasun, R.: End-to-end learning of multi-sensor 3D tracking by detection. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 635\u2013642. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8462884"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 941\u2013951 (2019)","DOI":"10.1109\/ICCV.2019.00103"},{"key":"41_CR18","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1109\/TIP.2018.2878956","volume":"28","author":"G Li","year":"2018","unstructured":"Li, G., Gan, Y., Wu, H., Xiao, N., Lin, L.: Cross-modal attentional context learning for RGB-D object detection. IEEE Trans. Image Process. 28, 1591\u20131601 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Chen, H., Li, Y.F., Su, D.: Attention-aware cross-modal cross-level fusion network for RGB-D salient object detection. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6821\u20136826. IEEE (2018)","DOI":"10.1109\/IROS.2018.8594373"},{"key":"41_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-030-01225-0_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K-H Lee","year":"2018","unstructured":"Lee, K.-H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 212\u2013228. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_13"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, W., Wang, L.: Instance-aware image and sentence matching with selective multimodal LSTM. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.767"},{"key":"41_CR22","doi-asserted-by":"crossref","unstructured":"Nam, H., Ha, J.W., Kim, J.: Dual attention networks for multimodal reasoning and matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 299\u2013307 (2017)","DOI":"10.1109\/CVPR.2017.232"},{"key":"41_CR23","doi-asserted-by":"crossref","unstructured":"Ye, L., Rochan, M., Liu, Z., Wang, Y.: Cross-modal self-attention network for referring image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10502\u201310511 (2019)","DOI":"10.1109\/CVPR.2019.01075"},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, Y.F., Wang, W.Y.: Watch, listen, and describe: globally and locally aligned cross-modal attentions for video captioning. arXiv preprint arXiv:1804.05448 (2018)","DOI":"10.18653\/v1\/N18-2125"},{"key":"41_CR25","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"41_CR26","doi-asserted-by":"crossref","unstructured":"Frossard, D., Urtasun, R.: End-to-end learning of multi-sensor 3D tracking by detection. In: ICRA. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8462884"},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Schulter, S., Vernaza, P., Choi, W., Chandraker, M.: Deep network flow for multi-object tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6951\u20136960 (2017)","DOI":"10.1109\/CVPR.2017.292"},{"key":"41_CR28","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":"41_CR29","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3D object detection from RGB-D data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"41_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need (2017)"},{"key":"41_CR31","unstructured":"Guan, Q., Huang, Y., Zhong, Z., Zheng, Z., Zheng, L., Yang, Y.: Diagnose like a radiologist: attention guided convolutional neural network for thorax disease classification (2018)"},{"key":"41_CR32","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"41_CR33","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, C., Nevatia, R.: Learning to associate: hybridboosted multi-target tracker for crowded scene. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2953\u20132960. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206735"},{"key":"41_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/246309","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the CLEAR MOT metrics. EURASIP J. Image Video Process. 2008, 1\u201310 (2008)","journal-title":"EURASIP J. Image Video Process."},{"key":"41_CR35","doi-asserted-by":"crossref","unstructured":"Ren, J., et al.: Accurate single stage detector using recurrent rolling convolution. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.87"},{"key":"41_CR36","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"41_CR37","unstructured":"Gunduz, G., Acarman, T.: Efficient multi-object tracking by strong associations on temporal window. IEEE Trans. Intell. Veh. 4(3), 447\u2013455 (2019)"},{"key":"41_CR38","doi-asserted-by":"crossref","unstructured":"Osep, A., Mehner, W., Mathias, M., Leibe, B.: Combined image- and world-space tracking in traffic scenes. In: ICRA (2017)","DOI":"10.1109\/ICRA.2017.7989230"},{"key":"41_CR39","doi-asserted-by":"crossref","unstructured":"Yoon, J.H., Lee, C.R., Yang, M.H., Yoon, K.J.: Online multi-object tracking via structural constraint event aggregation. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.155"},{"key":"41_CR40","doi-asserted-by":"crossref","unstructured":"Simon, M., et al.: Complexer-YOLO: real-time 3D object detection and tracking on semantic point clouds. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00158"},{"key":"41_CR41","doi-asserted-by":"crossref","unstructured":"Chu, P., Ling, H.: FAMNet: joint learning of feature, affinity and multi-dimensional assignment for online multiple object tracking. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00627"},{"key":"41_CR42","unstructured":"Wang, S., Fowlkes, C.: Learning optimal parameters for multi-target tracking with contextual interactions. Int. J. Comput. Vis. 122(3), 484\u2013501 (2016)"},{"key":"41_CR43","doi-asserted-by":"crossref","unstructured":"Burnett, K., Samavi, S., Waslander, S., Barfoot, T., Schoellig, A.: aUToTrack: a lightweight object detection and tracking system for the SAE autodrive challenge. In: 2019 16th Conference on Computer and Robot Vision (CRV) (2019)","DOI":"10.1109\/CRV.2019.00036"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69532-3_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T09:10:46Z","timestamp":1614330646000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69532-3_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695316","9783030695323"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69532-3_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"27 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","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":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"33% - 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":"3","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)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}