{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:58:02Z","timestamp":1742943482839,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819984343"},{"type":"electronic","value":"9789819984350"}],"license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8435-0_23","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"287-298","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cascaded Bilinear Mapping Collaborative Hybrid Attention Modality Fusion Model"],"prefix":"10.1007","author":[{"given":"Jiayu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuizhi","family":"Mei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Bai, X., et al.: Transfusion: robust lidar-camera fusion for 3D object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1090\u20131099 (2022)","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhang, T., Wang, Y., Wang, Y., Zhao, H.: FUTR3D: a unified sensor fusion framework for 3D detection. arXiv preprint arXiv:2203.10642 (2022)","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F.: Autoalignv2: deformable feature aggregation for dynamic multi-modal 3D object detection. arXiv preprint arXiv:2207.10316 (2022)","DOI":"10.1007\/978-3-031-20074-8_36"},{"key":"23_CR6","unstructured":"Cortes, C., Lawarence, N., Lee, D., Sugiyama, M., Garnett, R.: Advances in neural information processing systems 28. In: Proceedings of the 29th Annual Conference on Neural Information Processing Systems (2015)"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: CMT: convolutional neural networks meet vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12175\u201312185 (2022)","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Jiao, Y., Jie, Z., Chen, S., Chen, J., Ma, L., Jiang, Y.G.: Msmdfusion: fusing lidar and camera at multiple scales with multi-depth seeds for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21643\u201321652 (2023)","DOI":"10.1109\/CVPR52729.2023.02073"},{"key":"23_CR9","unstructured":"Kim, Y., Park, K., Kim, M., Kum, D., Choi, J.W.: 3D dual-fusion: dual-domain dual-query camera-lidar fusion for 3D object detection. arXiv preprint arXiv:2211.13529 (2022)"},{"key":"23_CR10","unstructured":"Li, H., et al.: Delving into the devils of bird\u2019s-eye-view perception: a review, evaluation and recipe. arXiv preprint arXiv:2209.05324 (2022)"},{"key":"23_CR11","unstructured":"Li, J., et al.: Next-ViT: next generation vision transformer for efficient deployment in realistic industrial scenarios. arXiv preprint arXiv:2207.05501 (2022)"},{"key":"23_CR12","unstructured":"Li, Y., Chen, Y., Qi, X., Li, Z., Sun, J., Jia, J.: Unifying voxel-based representation with transformer for 3D object detection. arXiv preprint arXiv:2206.00630 (2022)"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Voxel field fusion for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1120\u20131129 (2022)","DOI":"10.1109\/CVPR52688.2022.00119"},{"key":"23_CR14","unstructured":"Liang, T., et al.: Bevfusion: a simple and robust lidar-camera fusion framework. arXiv preprint arXiv:2205.13790 (2022)"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Bevfusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. arXiv preprint arXiv:2205.13542 (2022)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"23_CR17","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Nabati, R., Qi, H.: Centerfusion: center-based radar and camera fusion for 3D object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1527\u20131536 (2021)","DOI":"10.1109\/WACV48630.2021.00157"},{"key":"23_CR19","unstructured":"Park, N., Kim, S.: How do vision transformers work? arXiv preprint arXiv:2202.06709 (2022)"},{"key":"23_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"23_CR21","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: DETR3D: 3D object detection from multi-view images via 3D-to-2D queries. In: Conference on Robot Learning, pp. 180\u2013191. PMLR (2022)"},{"key":"23_CR22","unstructured":"Yan, J., et al.: Cross modal transformer via coordinates encoding for 3D object dectection. arXiv preprint arXiv:2301.01283 (2023)"},{"key":"23_CR23","unstructured":"Yin, T., Zhou, X., Kr\u00e4henb\u00fchl, P.: Multimodal virtual point 3D detection (2021)"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Fan, J., Tao, D.: Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1821\u20131830 (2017)","DOI":"10.1109\/ICCV.2017.202"},{"issue":"12","key":"23_CR25","doi-asserted-by":"publisher","first-page":"5947","DOI":"10.1109\/TNNLS.2018.2817340","volume":"29","author":"Z Yu","year":"2018","unstructured":"Yu, Z., Yu, J., Xiang, C., Fan, J., Tao, D.: Beyond bilinear: generalized multimodal factorized high-order pooling for visual question answering. IEEE Trans. Neural Netw. Learn. Syst. 29(12), 5947\u20135959 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"23_CR26","unstructured":"Zhang, Y., Zhang, Q., Hou, J., Yuan, Y., Xing, G.: Bidirectional propagation for cross-modal 3D object detection. arXiv preprint arXiv:2301.09077 (2023)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8435-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:12:50Z","timestamp":1703319170000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8435-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984343","9789819984350"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8435-0_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,24]]},"assertion":[{"value":"24 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","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":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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)"}}]}}