{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T16:44:26Z","timestamp":1781541866028,"version":"3.54.5"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030983574","type":"print"},{"value":"9783030983581","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-98358-1_28","type":"book-chapter","created":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T12:06:56Z","timestamp":1647259616000},"page":"352-363","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-scale Cross-Modal Transformer Network for RGB-D Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9028-5884","authenticated-orcid":false,"given":"Zhibin","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1005-9252","authenticated-orcid":false,"given":"Pengwei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2131-3044","authenticated-orcid":false,"given":"Guijin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,3,15]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Blum, M., Springenberg, J.T., W\u00fclfing, J., Riedmiller, M.: A learned feature descriptor for object recognition in RGB-D data. In: 2012 IEEE International Conference on Robotics and Automation, pp. 1298\u20131303. IEEE (2012)","DOI":"10.1109\/ICRA.2012.6225188"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Bo, L., Lai, K., Ren, X., Fox, D.: Object recognition with hierarchical kernel descriptors. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1729\u20131736 (2011)","DOI":"10.1109\/CVPR.2011.5995719"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Bo, L., Ren, X., Fox, D.: Depth kernel descriptors for object recognition. In: 2011 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 821\u2013826. IEEE (2011)","DOI":"10.1109\/IROS.2011.6095119"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. arXiv preprint arXiv:2005.12872 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"28_CR6","unstructured":"Chen, K., et al.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"28_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Eitel, A., Springenberg, J.T., Spinello, L., Riedmiller, M., Burgard, W.: Multimodal deep learning for robust RGB-D object recognition. In: 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 681\u2013687. IEEE (2015)","DOI":"10.1109\/IROS.2015.7353446"},{"issue":"1","key":"28_CR10","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"28_CR11","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":"28_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"10","key":"28_CR13","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","volume":"28","author":"K Greff","year":"2016","unstructured":"Greff, K., Srivastava, R.K., Koutn\u00edk, J., Steunebrink, B.R., Schmidhuber, J.: LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28(10), 2222\u20132232 (2016)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"28_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-319-10584-0_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"S Gupta","year":"2014","unstructured":"Gupta, S., Girshick, R., Arbel\u00e1ez, P., Malik, J.: Learning rich features from RGB-D images for object detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 345\u2013360. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_23"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Gupta, S., Hoffman, J., Malik, J.: Cross modal distillation for supervision transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2827\u20132836 (2016)","DOI":"10.1109\/CVPR.2016.309"},{"key":"28_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-319-54181-5_14","volume-title":"Computer Vision \u2013 ACCV 2016","author":"C Hazirbas","year":"2017","unstructured":"Hazirbas, C., Ma, L., Domokos, C., Cremers, D.: FuseNet: incorporating depth into semantic segmentation via fusion-based CNN architecture. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10111, pp. 213\u2013228. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54181-5_14"},{"issue":"4","key":"28_CR17","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(4), 1591\u20131601 (2018)","journal-title":"IEEE Trans. Image Process."},{"issue":"5","key":"28_CR18","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1109\/TMM.2016.2642789","volume":"19","author":"J Li","year":"2016","unstructured":"Li, J., et al.: Attentive contexts for object detection. IEEE Trans. Multimedia 19(5), 944\u2013954 (2016)","journal-title":"IEEE Trans. Multimedia"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. In: NeurIPS (2020)","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"28_CR20","unstructured":"Liu, Z., et al.: ConvTransformer: a convolutional transformer network for video frame synthesis. arXiv preprint arXiv:2011.10185 (2020)"},{"key":"28_CR21","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"28_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"28_CR23","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Sparse R-CNN: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14454\u201314463 (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"28_CR26","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. arXiv preprint arXiv:2012.12877 (2020)"},{"key":"28_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"28_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/978-3-030-58548-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Wang","year":"2020","unstructured":"Wang, J., et al.: Side-aware boundary localization for more precise object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 403\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_24"},{"key":"28_CR29","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1016\/j.patcog.2017.07.026","volume":"72","author":"X Xu","year":"2017","unstructured":"Xu, X., Li, Y., Wu, G., Luo, J.: Multi-modal deep feature learning for RGB-D object detection. Pattern Recogn. 72, 300\u2013313 (2017)","journal-title":"Pattern Recogn."},{"key":"28_CR30","unstructured":"Yang, Z., Dai, Z., Salakhutdinov, R., Cohen, W.W.: Breaking the softmax bottleneck: a high-rank RNN language model. arXiv preprint arXiv:1711.03953 (2017)"},{"key":"28_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/978-3-030-58604-1_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Zhang","year":"2020","unstructured":"Zhang, D., Zhang, H., Tang, J., Wang, M., Hua, X., Sun, Q.: Feature pyramid transformer. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 323\u2013339. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_20"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, H., Chang, H., Ma, B., Wang, N., Chen, X.: Dynamic R-CNN: towards high quality object detection via dynamic training. arXiv preprint arXiv:2004.06002 (2020)","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"28_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759\u20139768 (2020)","DOI":"10.1109\/CVPR42600.2020.00978"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-98358-1_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T10:12:46Z","timestamp":1708337566000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-98358-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030983574","9783030983581"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-98358-1_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 March 2022","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":"Phu Quoc","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"6 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2022","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":"212","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":"84","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":"40% - 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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}