{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:13:51Z","timestamp":1774419231365,"version":"3.50.1"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031250842","type":"print"},{"value":"9783031250859","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\/978-3-031-25085-9_27","type":"book-chapter","created":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T09:12:42Z","timestamp":1676106762000},"page":"478-494","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Learning Dual-Fused Modality-Aware Representations for\u00a0RGBD Tracking"],"prefix":"10.1007","author":[{"given":"Shang","family":"Gao","sequence":"first","affiliation":[]},{"given":"Jinyu","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Li","sequence":"additional","affiliation":[]},{"given":"Feng","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Ale\u0161","family":"Leonardis","sequence":"additional","affiliation":[]},{"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,12]]},"reference":[{"key":"27_CR1","unstructured":"An, N., Zhao, X.G., Hou, Z.G.: Online rgb-d tracking via detection-learning-segmentation. In: 2016 23rd International Conference on Pattern Recognition, pp. 1231\u20131236. IEEE (2016)"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L.V., Timofte, R.: Learning discriminative model prediction for tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6182\u20136191 (2019)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Camplani, M., et al.: Real-time rgb-d tracking with depth scaling kernelised correlation filters and occlusion handling. In: BMVC, vol. 4, p. 5 (2015)","DOI":"10.5244\/C.29.145"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Cao, Z., Huang, Z., Pan, L., Zhang, S., Liu, Z., Fu, C.: Tctrack: Temporal contexts for aerial tracking. arXiv preprint arXiv:2203.01885 (2022)","DOI":"10.1109\/CVPR52688.2022.01438"},{"key":"27_CR5","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":"27_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8126\u20138135 (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"27_CR7","unstructured":"Chen, Y.W., Tsai, Y.H., Yang, M.H.: End-to-end multi-modal video temporal grounding. In: Advances in Neural Information Processing Systems 34 (2021)"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: Atom: Accurate tracking by overlap maximization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4660\u20134669 (2019)","DOI":"10.1109\/CVPR.2019.00479"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Gool, L.V., Timofte, R.: Probabilistic regression for visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7183\u20137192 (2020)","DOI":"10.1109\/CVPR42600.2020.00721"},{"issue":"5","key":"27_CR10","first-page":"1","volume":"16","author":"S Hannuna","year":"2016","unstructured":"Hannuna, S., et al.: Ds-kcf: a real-time tracker for rgb-d data. J. Real-Time Image Proc. 16(5), 1\u201320 (2016)","journal-title":"J. Real-Time Image Proc."},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Hu, J., Lu, J., Tan, Y.P.: Sharable and individual multi-view metric learning. IEEE Trans. Pattern Anal. Mach. Intell. 1 (2017)","DOI":"10.1109\/TPAMI.2017.2749576"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Kart, U., K\u00e4m\u00e4r\u00e4inen, J.K., Matas, J.: How to make an rgbd tracker? In: ECCVW (2018)","DOI":"10.1007\/978-3-030-11009-3_8"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Kart, U., Luke\u017ei\u010d, A., Kristan, M., K\u00e4m\u00e4r\u00e4inen, J.K., Matas, J.: Object tracking by reconstruction with view-specific discriminative correlation filters. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00143"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Kim, J., Ma, M., Pham, T., Kim, K., Yoo, C.D.: Modality shifting attention network for multi-modal video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10106\u201310115 (2020)","DOI":"10.1109\/CVPR42600.2020.01012"},{"key":"27_CR15","unstructured":"Lin, L., Fan, H., Xu, Y., Ling, H.: Swintrack: A simple and strong baseline for transformer tracking. arXiv preprint arXiv:2112.00995 (2021)"},{"issue":"3","key":"27_CR16","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TMM.2018.2863604","volume":"21","author":"Y Liu","year":"2018","unstructured":"Liu, Y., Jing, X.Y., Nie, J., Gao, H., Liu, J., Jiang, G.P.: Context-aware three-dimensional mean-shift with occlusion handling for robust object tracking in rgb-d videos. IEEE Trans. Multimedia 21(3), 664\u2013677 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Lukezic, A., et al.: Cdtb: A color and depth visual object tracking dataset and benchmark. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10013\u201310022 (2019)","DOI":"10.1109\/ICCV.2019.01011"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Luo, W., Yang, B., Urtasun, R.: Fast and furious: Real time end-to-end 3d detection, tracking and motion forecasting with a single convolutional net. In: Proceedings of the IEEE Conference On Computer Vision and Pattern Recognition, pp. 3569\u20133577 (2018)","DOI":"10.1109\/CVPR.2018.00376"},{"key":"27_CR19","unstructured":"Machida, E., Cao, M., Murao, T., Hashimoto, H.: Human motion tracking of mobile robot with kinect 3d sensor. In: 2012 Proceedings of SICE Annual Conference (SICE), pp. 2207\u20132211. IEEE (2012)"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Mayer, C., Danelljan, M., Paudel, D.P., Van Gool, L.: Learning target candidate association to keep track of what not to track. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13444\u201313454 (2021)","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"27_CR21","doi-asserted-by":"publisher","unstructured":"Meshgi, K., ichi Maeda, S., Oba, S., Skibbe, H., zhe Li, Y., Ishii, S.: An occlusion-aware particle filter tracker to handle complex and persistent occlusions. Comput. Vision Image Understand. 150, 81\u201394 (2016). https:\/\/doi.org\/10.1016\/j.cviu.2016.05.011, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1077314216300649","DOI":"10.1016\/j.cviu.2016.05.011"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Pan, B., et al.: Spatio-temporal graph for video captioning with knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10870\u201310879 (2020)","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Qi, H., Feng, C., Cao, Z., Zhao, F., Xiao, Y.: P2b: Point-to-box network for 3d object tracking in point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6329\u20136338 (2020)","DOI":"10.1109\/CVPR42600.2020.00636"},{"key":"27_CR24","unstructured":"Qian, Y., Yan, S., Luke\u017ei\u010d, A., Kristan, M., K\u00e4m\u00e4r\u00e4inen, J.K., Matas, J.: DAL: A deep depth-aware long-term tracker. In: International Conference on Pattern Recognition (2020)"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Song, S., Xiao, J.: Tracking revisited using rgbd camera: Unified benchmark and baselines. In: Proceedings of the IEEE International Conference On Computer Vision, pp. 233\u2013240 (2013)","DOI":"10.1109\/ICCV.2013.36"},{"key":"27_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhou, W., Wang, J., Li, H.: Transformer meets tracker: Exploiting temporal context for robust visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1571\u20131580 (2021)","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Q., Fang, J., Yuan, Y.: Multi-cue based tracking (2014)","DOI":"10.1016\/j.neucom.2013.10.021"},{"issue":"8","key":"27_CR29","doi-asserted-by":"crossref","first-page":"2485","DOI":"10.1109\/TCYB.2017.2740952","volume":"48","author":"J Xiao","year":"2017","unstructured":"Xiao, J., Stolkin, R., Gao, Y., Leonardis, A.: Robust fusion of color and depth data for rgb-d target tracking using adaptive range-invariant depth models and spatio-temporal consistency constraints. IEEE Trans. Cybern. 48(8), 2485\u20132499 (2017)","journal-title":"IEEE Trans. Cybern."},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10448\u201310457 (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Yan, S., Yang, J., K\u00e4pyl\u00e4, J., Zheng, F., Leonardis, A., K\u00e4m\u00e4r\u00e4inen, J.K.: Depthtrack: Unveiling the power of rgbd tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10725\u201310733 (2021)","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"27_CR32","unstructured":"Yang, J., et al.: Rgbd object tracking: An in-depth review. arXiv preprint arXiv:2203.14134 (2022)"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Yu, B., et al.: High-performance discriminative tracking with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9856\u20139865 (2021)","DOI":"10.1109\/ICCV48922.2021.00971"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Zhao, P., Liu, Q., Wang, W., Guo, Q.: Tsdm: Tracking by siamrpn++ with a depth-refiner and a mask-generator. In: 2020 25th International Conference on Pattern Recognition, pp. 670\u2013676. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413315"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Zheng, C., Yan, X., Gao, J., Zhao, W., Zhang, W., Li, Z., Cui, S.: Box-aware feature enhancement for single object tracking on point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13199\u201313208 (2021)","DOI":"10.1109\/ICCV48922.2021.01295"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, T., Fu, H., Chen, G., Zhou, Y., Fan, D.P., Shao, L.: Specificity-preserving rgb-d saliency detection. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00464"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25085-9_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:08:06Z","timestamp":1728864486000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25085-9_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250842","9783031250859"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25085-9_27","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":"12 February 2023","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","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 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}