{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T10:03:03Z","timestamp":1780999383915,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":50,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698684","type":"print"},{"value":"9789819698691","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-9869-1_21","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T13:43:45Z","timestamp":1753364625000},"page":"242-253","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BiSyncFusion: Dual-Stream Bidirectional Synchronization for BEV Multimodal Fusion"],"prefix":"10.1007","author":[{"given":"Long","family":"You","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunlei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Vora, S., Lang, A.H., Hello, B., et al.: Pointpainting: sequential fusion for 3D object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Chae, Y., Kim, H., Yoon, K.: Towards robust 3D object detection with LiDAR and 4D radar fusion in various weather conditions. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01436"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Wang, L., Zhang, X., Song, Z., et al.: Multi-modal 3D object detection in autonomous driving: a survey and taxonomy. IEEE Trans. Intell. Transp. Syst., 3781\u20133798 (2023)","DOI":"10.1109\/TIV.2023.3264658"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., et al.: Frustum PointNets for 3D object detection from RGB-D data. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Huang, Z., Lv, C., Xing, Y., et al.: Multi-modal sensor fusion-based deep neural network for end-to-end autonomous driving with scene understanding. IEEE Sens. J., 11781\u201311790 (2021)","DOI":"10.1109\/JSEN.2020.3003121"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Bijelic, M., Gruber, T., Mannan, F., et al.: Seeing through fog without seeing fog: deep multimodal sensor fusion in unseen adverse weather. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01170"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Stiller, C., et al.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res., 1231\u20131237 (2013)","DOI":"10.1177\/0278364913491297"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Li, H., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: CVPR (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Liu, Z., Tang, H., Amini, A., et al.: BEVFusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: ICRA (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Chitta, K., Prakash, A., Jaeger, B., et al.: TransFuser: imitation with transformer-based sensor fusion for autonomous driving. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Liu, M., Niu, J.: BEV-Net: a bird\u2019s eye view object detection network for LiDAR point cloud. In: IROS (2021)","DOI":"10.1109\/IROS51168.2021.9636810"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., Ge, Z., Yu, G., et al.: BEVDepth: acquisition of reliable depth for multi-view 3D object detection. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Wang, J., Kong, X., Nishikawa, H., et al.: Dynamic point-pixel feature alignment for multimodal 3D object detection. IEEE Internet Things J. (2024)","DOI":"10.1109\/JIOT.2023.3329884"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Berens, F., Koschinski, Y., Badami, M.K., et al.: Adaptive training for robust object detection in autonomous driving environments. IEEE Trans. Intell. Transp. Syst., 1\u201315 (2024)","DOI":"10.1109\/TIV.2024.3439001"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Zhen, L., Hu, P., Peng, X., et al.: Deep multimodal transfer learning for cross-modal retrieval. IEEE Trans. Neural Netw. Learn. Syst. (2022)","DOI":"10.1109\/TNNLS.2020.3029181"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Han, Y., Zhang, H., Li, H., et al.: Collaborative perception in autonomous driving: methods, datasets, and challenges. IEEE Intell. Transp. Syst. Mag., 131\u2013151 (2023)","DOI":"10.1109\/MITS.2023.3298534"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Alaba, S.Y., Ball, J.E.: Transformer-based optimized multimodal fusion for 3D object detection in autonomous driving. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3385439"},{"key":"21_CR18","doi-asserted-by":"publisher","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 194\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"21_CR19","unstructured":"Huang, J., Huang, G., Zhu, Z., et al.: BEVDet: high-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint (2021)"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Yu, A.W., Meng, T., et al.: DeepFusion: LiDAR-camera deep fusion for multi-modal 3D object detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Xu, S., Zhou, D., Fang, J., et al.: FusionPainting: multimodal fusion with adaptive attention for 3D object detection. In: ITSC (2021)","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Wang, S., Caesar, H., Nan, L., et al.: UniBEV: multi-modal 3D object detection with uniform BEV encoders for robustness against missing sensor modalities. In: IEEE IV (2024)","DOI":"10.1109\/IV55156.2024.10588783"},{"key":"21_CR23","unstructured":"Zhang, Y., Shi, G., Xiong, K., et al.: BEVWorld: a multimodal world model for autonomous driving via unified BEV latent space. arXiv preprint (2024)"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Su, H., Gao, H., Wang, X., et al.: Object detection in adverse weather for autonomous vehicles based on sensor fusion and incremental learning. IEEE Trans. Instrum. Meas., 1\u201310 (2024)","DOI":"10.1109\/TIM.2024.3472860"},{"key":"21_CR25","unstructured":"Li, Y., Huang, B., Chen, Z., et al.: Fast-BEV: a fast and strong bird\u2019s-eye view perception baseline. arXiv preprint (2023)"},{"key":"21_CR26","unstructured":"Yang, B., Bender, G., Le, Q.V., et al.: CondConv: conditionally parameterized convolutions for efficient inference (2019)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Fan, M., Lai, S., Huang, J., et al.: Rethinking BiSeNet for real-time semantic segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Xiong, Z., Yao, Z., Liu, X., et al.: Efficient multispectral object detection with attentive feature aggregation leveraging zero-shot implicit illumination guidance. Inf. Fus. (2025)","DOI":"10.1016\/j.inffus.2025.102939"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Cui, Y., et al.: Deep modular co-attention networks for visual question answering. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00644"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Li, F., Zheng, J., Zhang, Y.F., et al.: AMDFNet: adaptive multi-level deformable fusion network for RGB-D saliency detection. Neurocomputing (2021)","DOI":"10.1016\/j.neucom.2021.08.116"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Uzair, M., Dong, J., Shi, R., et al.: Channelwise and spatially guided multimodal feature fusion network for 3D object detection in autonomous vehicles. IEEE Trans. Geosci. Remote Sens., 1\u201315 (2024)","DOI":"10.1109\/TGRS.2024.3476072"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Jiang, C., Ding, Y., Zeng, Y., et al.: Multi-modal deep cross-fusion network for autonomous driving. In: CAC (2023)","DOI":"10.1109\/CAC59555.2023.10451691"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Sidheekh, S., Tenali, P., Mathur, S., et al.: On the robustness and reliability of late multi-modal fusion using probabilistic circuits. In: FUSION (2024)","DOI":"10.23919\/FUSION59988.2024.10706372"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Wei, K., Dai, J., Hong, D., et al.: MGFNet: an MLP-dominated gated fusion network for semantic segmentation of high-resolution multi-modal remote sensing images. Int. J. Appl. Earth Obs. Geoinf., 104241 (2024)","DOI":"10.1016\/j.jag.2024.104241"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Neverova, N., Wolf, C., Taylor, G., et al.: ModDrop: adaptive multi-modal gesture recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2016)","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Wan, X., Chen, F., Gao, W., et al.: Efficient spectral-spatial fusion with multiscale and adaptive attention for hyperspectral image classification. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 1196\u20131211 (2025)","DOI":"10.1109\/JSTARS.2024.3492351"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Bai, X., Hu, Z., Tai, C.-L., et al.: TransFusion: robust LiDAR-camera fusion for 3D object detection with transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"21_CR39","unstructured":"Yang, Z., Chen, J., Miao, Z., et al.: DeepInteraction: 3D object detection via modality interaction. In: NeurIPS (2022)"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Tulsiani, S.: SparseFusion: distilling view-conditioned diffusion for 3D reconstruction. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01211"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, W., Lv, Y., Lei, J., et al.: Embedded control gate fusion and attention residual learning for RGB\u2013thermal urban scene parsing. IEEE Trans. Intell. Transp. Syst. 4794\u20134803 (2023)","DOI":"10.1109\/TITS.2023.3242651"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"21_CR44","doi-asserted-by":"crossref","unstructured":"Yan, Y., Mao, Y., Li, B.: SECOND: sparsely embedded convolutional detection. Sensors (2018)","DOI":"10.3390\/s18103337"},{"key":"21_CR45","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Kr\u00e4henb\u00fchl, P.: Center-based 3D object detection and tracking. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"21_CR46","unstructured":"Yin, T., Zhou, X., Kr\u00e4henb\u00fchl, P.: Multimodal virtual point 3D detection. In: NeurIPS (2021)"},{"key":"21_CR47","doi-asserted-by":"crossref","unstructured":"Xu, Z., Zhang, Y., Xie, E., et al.: DriveGPT4: interpretable end-to-end autonomous driving via large language model. IEEE Robot. Autom. Lett. (2024)","DOI":"10.1109\/LRA.2024.3440097"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Rong, Y., Wei, X., Lin, T., et al.: DynStaTF: an efficient feature fusion strategy for LiDAR 3D object detection. In: CVPR (2023)","DOI":"10.1109\/CVPRW59228.2023.00326"},{"key":"21_CR49","doi-asserted-by":"crossref","unstructured":"Xu, X., Dong, S., Xu, T., et al.: FusionRCNN: LiDAR-camera fusion for two-stage 3D object detection. Remote Sens. (2023)","DOI":"10.3390\/rs15071839"},{"key":"21_CR50","doi-asserted-by":"crossref","unstructured":"Huang, J., Ye, Y., Liang, Z., et al.: Detecting as labeling: rethinking LiDAR-camera fusion in 3D object detection. arXiv preprint (2023)","DOI":"10.1007\/978-3-031-72670-5_25"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9869-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T09:54:28Z","timestamp":1780998868000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9869-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698684","9789819698691"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9869-1_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}