{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:42:11Z","timestamp":1784738531356,"version":"3.55.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031250712","type":"print"},{"value":"9783031250729","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\/978-3-031-25072-9_41","type":"book-chapter","created":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T08:40:04Z","timestamp":1676623204000},"page":"608-623","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Cross-Modality Attention and\u00a0Multimodal Fusion Transformer for\u00a0Pedestrian Detection"],"prefix":"10.1007","author":[{"given":"Wei-Yu","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ljubomir","family":"Jovanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wilfried","family":"Philips","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,18]]},"reference":[{"key":"41_CR1","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"41_CR2","unstructured":"Choi, H., Kim, S., Park, K., Sohn, K.: Multi-spectral pedestrian detection based on accumulated object proposal with fully convolutional networks. In: International Conference on Pattern Recognition (ICPR) (2016)"},{"key":"41_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"41_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-030-58548-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"V Gabeur","year":"2020","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 214\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_13"},{"issue":"6","key":"41_CR5","doi-asserted-by":"publisher","first-page":"820","DOI":"10.3390\/s16060820","volume":"16","author":"A Gonz\u00e1lez","year":"2016","unstructured":"Gonz\u00e1lez, A., et al.: Pedestrian detection at day\/night time with visible and fir cameras: a comparison. Sensors 16(6), 820 (2016)","journal-title":"Sensors"},{"key":"41_CR6","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.inffus.2018.11.017","volume":"50","author":"D Guan","year":"2019","unstructured":"Guan, D., Cao, Y., Yang, J., Cao, Y., Yang, M.Y.: Fusion of multispectral data through illumination-aware deep neural networks for pedestrian detection. Inf. Fusion 50, 148\u2013157 (2019)","journal-title":"Inf. Fusion"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Hwang, S., Park, J., Kim, N., Choi, Y., Kweon, I.S.: Multispectral pedestrian detection: benchmark dataset and baselines. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Iashin, V., Rahtu, E.: Multi-modal dense video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2020)","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"41_CR9","unstructured":"Jingjing Liu, Shaoting Zhang, S.W., Metaxas, D.: Multispectral deep neural networks for pedestrian detection. In: Proceedings of the British Machine Vision Conference (BMVC) (2016)"},{"issue":"4","key":"41_CR10","doi-asserted-by":"publisher","first-page":"7846","DOI":"10.1109\/LRA.2021.3099870","volume":"6","author":"J Kim","year":"2021","unstructured":"Kim, J., Kim, H., Kim, T., Kim, N., Choi, Y.: MLPD: multi-label pedestrian detector in multispectral domain. IEEE Robot. Autom. Lett. 6(4), 7846\u20137853 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"Konig, D., Adam, M., Jarvers, C., Layher, G., Neumann, H., Teutsch, M.: Fully convolutional region proposal networks for multispectral person detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2017)","DOI":"10.1109\/CVPRW.2017.36"},{"key":"41_CR12","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)"},{"key":"41_CR13","unstructured":"Li, C., Song, D., Tong, R., Tang, M.: Multispectral pedestrian detection via simultaneous detection and segmentation. In: Proceedings of the British Machine Vision Conference (BMVC) (2018)"},{"key":"41_CR14","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.patcog.2018.08.005","volume":"85","author":"C Li","year":"2019","unstructured":"Li, C., Song, D., Tong, R., Tang, M.: Illumination-aware faster R-CNN for robust multispectral pedestrian detection. Pattern Recognit. 85, 161\u2013171 (2019)","journal-title":"Pattern Recognit."},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Li, G., Zhu, L., Liu, P., Yang, Y.: Entangled transformer for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00902"},{"key":"41_CR16","doi-asserted-by":"publisher","first-page":"2476","DOI":"10.1109\/TASLP.2021.3065823","volume":"29","author":"Z Li","year":"2021","unstructured":"Li, Z., Li, Z., Zhang, J., Feng, Y., Zhou, J.: Bridging text and video: a universal multimodal transformer for audio-visual scene-aware dialog. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 2476\u20132483 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"41_CR17","unstructured":"Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)"},{"key":"41_CR18","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems (2019)"},{"key":"41_CR19","unstructured":"Nagrani, A., Yang, S., Arnab, A., Jansen, A., Schmid, C., Sun, C.: Attention bottlenecks for multimodal fusion. In: Advances in Neural Information Processing Systems (2021)"},{"key":"41_CR20","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.patcog.2018.03.007","volume":"80","author":"K Park","year":"2018","unstructured":"Park, K., Kim, S., Sohn, K.: Unified multi-spectral pedestrian detection based on probabilistic fusion networks. Pattern Recognit. 80, 143\u2013155 (2018)","journal-title":"Pattern Recognit."},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Prakash, A., Chitta, K., Geiger, A.: Multi-modal fusion transformer for end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"41_CR22","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 (2015)"},{"key":"41_CR23","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"41_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"41_CR26","doi-asserted-by":"crossref","unstructured":"Wang, W., Chen, C., Ding, M., Yu, H., Zha, S., Li, J.: TransBTS: multimodal brain tumor segmentation using transformer. In: International Conference on Medical Image Computing and Computer-Assisted Intervention (2021)","DOI":"10.1007\/978-3-030-87193-2_11"},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Yang, M., Li, C., Liu, L., Tang, J.: Attribute-based progressive fusion network for RGBT tracking (2022)","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"41_CR28","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Ricci, E., Wang, X., Sebe, N.: Learning cross-modal deep representations for robust pedestrian detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.451"},{"key":"41_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, H., Fromont, E., Lef\u00e8vre, S., Avignon, B.: Guided attentive feature fusion for multispectral pedestrian detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2021)","DOI":"10.1109\/WACV48630.2021.00012"},{"key":"41_CR30","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.inffus.2018.09.015","volume":"50","author":"L Zhang","year":"2019","unstructured":"Zhang, L., et al.: Cross-modality interactive attention network for multispectral pedestrian detection. Inf. Fusion 50, 20\u201329 (2019)","journal-title":"Inf. Fusion"},{"key":"41_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhu, X., Chen, X., Yang, X., Lei, Z., Liu, Z.: Weakly aligned cross-modal learning for multispectral pedestrian detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00523"},{"key":"41_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1007\/978-3-030-58523-5_46","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Zhou","year":"2020","unstructured":"Zhou, K., Chen, L., Cao, X.: Improving multispectral pedestrian detection by addressing modality imbalance problems. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 787\u2013803. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_46"}],"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\/978-3-031-25072-9_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:47:43Z","timestamp":1710258463000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25072-9_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250712","9783031250729"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25072-9_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":"18 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)"}}]}}