{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T00:04:35Z","timestamp":1774051475553,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,3,23]],"date-time":"2024-03-23T00:00:00Z","timestamp":1711152000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,23]],"date-time":"2024-03-23T00:00:00Z","timestamp":1711152000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Project of Major Scientific and Technological Achievements Engineering in Hefei","award":["2021CG003"],"award-info":[{"award-number":["2021CG003"]}]},{"name":"Anhui Provincial Development and Reform Commission 2021 New Energy Vehicle Industry Innovation Development Project","award":["wfgcyh2021439"],"award-info":[{"award-number":["wfgcyh2021439"]}]},{"name":"2022 Major Science and Technology Projects of Anhui Province","award":["202203a 05020008"],"award-info":[{"award-number":["202203a 05020008"]}]},{"name":"Joint research project of the Yangtze River Delta community of sci-tech innovation","award":["2022CSJGG1501"],"award-info":[{"award-number":["2022CSJGG1501"]}]},{"name":"Jining City Industrial Innovation Major Technology \"Global Unveiling\" Project","award":["2022JBZP002"],"award-info":[{"award-number":["2022JBZP002"]}]},{"name":"Projects for Transformation and Industrialization of Scientific and China Speech Valley innovation and development Project","award":["2108-340161-04-01-727575"],"award-info":[{"award-number":["2108-340161-04-01-727575"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s00138-024-01509-3","type":"journal-article","created":{"date-parts":[[2024,3,23]],"date-time":"2024-03-23T17:01:30Z","timestamp":1711213290000},"update-policy":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["AFMCT: adaptive fusion module based on cross-modal transformer block for 3D object detection"],"prefix":"10.1007","volume":"35","author":[{"given":"Bingli","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Yixin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chengbiao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Junzhao","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Zehao","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Jin","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Yangyang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xinyu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chenglei","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yanhui","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,23]]},"reference":[{"key":"1509_CR1","unstructured":"Huang, K., Shi, B., Li, X., Li, X., Huang, S., Li, Y.: Multi-modal sensor fusion for auto driving perception: a survey. arXiv preprint arXiv:2202.02703 (2022)"},{"key":"1509_CR2","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"},{"key":"1509_CR3","doi-asserted-by":"crossref","unstructured":"Mao, J., Xue, Y., Niu, M., Bai, H., Feng, J., Liang, X., Xu, H., Xu, C.: Voxel transformer for 3d object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 3164\u20133173 (2021)","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"1509_CR4","doi-asserted-by":"publisher","first-page":"704","DOI":"10.3390\/s20030704","volume":"20","author":"H Kuang","year":"2020","unstructured":"Kuang, H., Wang, B., An, J., Zhang, M., Zhang, Z.: Voxel-FPN: Multi-scale voxel feature aggregation for 3D object detection from LIDAR point clouds. Sensors 20, 704 (2020)","journal-title":"Sensors"},{"key":"1509_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel r-cnn: Towards high performance voxel-based 3d object detection. In: Proceedings of the AAAI conference on artificial intelligence. pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"1509_CR6","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\/CVF conference on computer vision and pattern recognition. pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"1509_CR7","doi-asserted-by":"crossref","unstructured":"Wang, Y., Fathi, A., Kundu, A., Ross, D.A., Pantofaru, C., Funkhouser, T., Solomon, J.: Pillar-based object detection for autonomous driving. In: Computer vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, Proceedings, Springer, Part XXII 16. pp. 18\u201334 August 23\u201328 (2020)","DOI":"10.1007\/978-3-030-58542-6_2"},{"key":"1509_CR8","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":"1509_CR9","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Adv Neural Inf Process Syst. 30, (2017)"},{"key":"1509_CR10","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: Pointrcnn: 3d object proposal generation and detection from point cloud. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 770\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"1509_CR11","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., Li, H.: 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":"1509_CR12","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s11263-022-01710-9","volume":"131","author":"S Shi","year":"2023","unstructured":"Shi, S., Jiang, L., Deng, J., Wang, Z., Guo, C., Shi, J., Wang, X., Li, H.: PV-RCNN++: Point-voxel feature set abstraction with local vector representation for 3D object detection. Int. J. Comput. Vis. 131, 531\u2013551 (2023)","journal-title":"Int. J. Comput. Vis."},{"key":"1509_CR13","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: Second sparsely embedded convolutional detection. Sensors (2018). https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.3390\/s18103337","journal-title":"Sensors"},{"key":"1509_CR14","unstructured":"Yin, T., Zhou, X., Kr\u00e4henb\u00fchl, P.: Center-based 3D Object Detection and Tracking. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp. 11784-11793."},{"key":"1509_CR15","doi-asserted-by":"crossref","unstructured":"Pang, S., Morris, D., Radha, H.: CLOCs: Camera-LiDAR object candidates fusion for 3D object detection. In: 2020 IEEE\/RSJ International conference on intelligent robots and systems (IROS). pp. 10386\u201310393 (2020)","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"1509_CR16","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3d object detection network for autonomous driving. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. pp. 1907\u20131915 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"1509_CR17","doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.L.: Joint 3d proposal generation and object detection from view aggregation. In: 2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS). pp. 1\u20138 (2018)","DOI":"10.1109\/IROS.2018.8594049"},{"key":"1509_CR18","doi-asserted-by":"crossref","unstructured":"Vora, S., Lang, A.H., Helou, B., Beijbom, O.: Pointpainting: Sequential fusion for 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 4604\u20134612 (2020)","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"1509_CR19","doi-asserted-by":"crossref","unstructured":"Wang, C., Ma, C., Zhu, M., Yang, X.: Pointaugmenting: Cross-modal augmentation for 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 11794\u201311803 (2021)","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"1509_CR20","doi-asserted-by":"crossref","unstructured":"Huang, T., Liu, Z., Chen, X., Bai, X.: Epnet: Enhancing point features with image semantics for 3d object detection. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, Proceedings, Springer Part XV 16. pp. 35\u201352 August (2020)","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"1509_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Huang, T., Li, B., Chen, X., Wang, X., Bai, X.: EPNet++: Cascade bi-directional fusion for multi-modal 3D object detection. IEEE Trans Pattern Anal Mach Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3228806"},{"key":"1509_CR22","doi-asserted-by":"crossref","unstructured":"Yoo, J.H., Kim, Y., Kim, J., Choi, J.W.: 3d-cvf: Generating joint camera and lidar features using cross-view spatial feature fusion for 3d object detection. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, Proceedings, Springer, Part XXVII 16. pp. 720\u2013736. August (2020)","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"1509_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Shen, Y., Li, H., Zhao, X., Yang, M., Tan, W., Pu, S., Mao, H.: Maff-net: Filter false positive for 3d vehicle detection with multi-modal adaptive feature fusion. In: 2022 IEEE 25th International conference on intelligent transportation systems (ITSC). pp. 369\u2013376 (2022)","DOI":"10.1109\/ITSC55140.2022.9922104"},{"key":"1509_CR24","unstructured":"Wang, G., Tian, B., Zhang, Y., Chen, L., Cao, D., Wu, J.: Multi-view adaptive fusion network for 3D object detection. arXiv preprint arXiv:2011.00652 (2020)"},{"key":"1509_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, J., Huang, D.: Cat-det: Contrastively augmented transformer for multi-modal 3d object detection. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition. pp. 908\u2013917 (2022)","DOI":"10.1109\/CVPR52688.2022.00098"},{"key":"1509_CR26","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F., Zhou, B., Zhao, H.: Autoalign: Pixel-instance feature aggregation for multi-modal 3d object detection. arXiv preprint arXiv:2201.06493 (2022)","DOI":"10.24963\/ijcai.2022\/116"},{"key":"1509_CR27","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":"1509_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Yu, A.W., Meng, T., Caine, B., Ngiam, J., Peng, D., Shen, J., Lu, Y., Zhou, D., Le, Q. V: Deepfusion: Lidar-camera deep fusion for multi-modal 3d object detection. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition. pp. 17182\u201317191 (2022)","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"1509_CR29","unstructured":"Yang, H., Shi, C., Chen, Y., Wang, L.: Boosting 3D object detection via object-focused image fusion. arXiv preprint arXiv:2207.10589. (2022)"},{"key":"1509_CR30","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv Neural Inf Process Syst. 30, (2017)"},{"key":"1509_CR31","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"1509_CR32","unstructured":"OpenPCDet Development Team. (2020). OpenPCDet: An open-source toolbox for 3D object detection from point clouds."},{"key":"1509_CR33","unstructured":"Kim, Y., Park, K., Kim, M., Kum, D., & Choi, J. W. (2022). 3D Dual-Fusion: dual-domain dual-query camera-LiDAR fusion for 3D object detection. https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/http\/arxiv.org\/abs\/2211.13529"},{"key":"1509_CR34","doi-asserted-by":"crossref","unstructured":"Tsai, Y.-H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.-P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the conference. Association for computational linguistics. Meeting. NIH Public Access pp. 6558 (2019)","DOI":"10.18653\/v1\/P19-1656"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01509-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/link.springer.com\/article\/10.1007\/s00138-024-01509-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01509-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T04:18:13Z","timestamp":1715660293000},"score":1,"resource":{"primary":{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/link.springer.com\/10.1007\/s00138-024-01509-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,23]]},"references-count":34,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["1509"],"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.1007\/s00138-024-01509-3","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,23]]},"assertion":[{"value":"26 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, and there is no professional or other personal interest of any nature or kind in any product, service and\/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled, \u201cAFMCT: Adaptive Fusion Module based on Cross-modal Transformer block for 3D Object Detection\u201d.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"40"}}