{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T15:12:21Z","timestamp":1768230741908,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557394","type":"print"},{"value":"9789819557400","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5740-0_8","type":"book-chapter","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:23:39Z","timestamp":1768220619000},"page":"108-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HDFN: Hierarchical Deformable Fusion with\u00a0Dual-Latency Adaptation for\u00a0Vehicle-Infrastructure Cooperative 3D Detection"],"prefix":"10.1007","author":[{"given":"Guorui","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wuyang","family":"Luan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jincheng","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Chen, X., et\u00a0al.: Futr3d: a unified sensor fusion framework for 3d detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 172\u2013181 (2023)","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Xu, R., et\u00a0al.: V2x-vit: vehicle-to-everything cooperative perception with vision transformer. In: European Conference on Computer Vision, pp. 107\u2013124. Springer (2022)","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Xiang, C., et\u00a0al.: Multi-sensor fusion and cooperative perception for autonomous driving: a review. In: IEEE Intelligent Transportation Systems Magazine 15.5, pp. 36\u201358 (2023)","DOI":"10.1109\/MITS.2023.3283864"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Wei, Y., et\u00a0al.: Spatial-temporal transformer for 3d point cloud sequences. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1171\u20131180 (2022)","DOI":"10.1109\/WACV51458.2022.00073"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Shi, S., et\u00a0al.: 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":"8_CR6","unstructured":"Park, J., et\u00a0al.: Time will tell: new outlooks and a baseline for temporal multi-view 3d object detection. In: arXiv preprint arXiv:2210.02443 (2022)"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Yu, H., et\u00a0al.: V2x-seq: a large-scale sequential dataset for vehicleinfrastructure cooperative perception and forecasting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5486\u20135495 (2023)","DOI":"10.1109\/CVPR52729.2023.00531"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Yu, H., et\u00a0al.: Dair-v2x: a large-scale dataset for vehicle-infrastructure cooperative 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21361\u2013 21370 (2022)","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: A lidar semantic segmentation framework for the cooperative vehicle-infrastructure system. In: IEEE 98th Vehicular Technology Conference (VTC2023-Fall). IEEE. 2023, pp. 1\u20135 (2023)","DOI":"10.1109\/VTC2023-Fall60731.2023.10333790"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Ming Liang et\u00a0al. Deep continuous fusion for multi-sensor 3d object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 641\u2013656 (2018)","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Liang, M., et\u00a0al.: Multi-task multi-sensor fusion for 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7345\u20137353 (2019)","DOI":"10.1109\/CVPR.2019.00752"},{"key":"8_CR12","unstructured":"Haibao, Yu., et\u00a0al.: Flow-based feature fusion for vehicle-infrastructure cooperative 3d object detection. Adv. Neural. Inf. Process. Syst. 36, 34493\u201334503 (2023)"},{"key":"8_CR13","unstructured":"Li, Y., et\u00a0al.: 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)"},{"key":"8_CR14","first-page":"29541","volume":"34","author":"Y Li","year":"2021","unstructured":"Li, Y., et al.: Learning distilled collaboration graph for multi-agent perception. Adv. Neural. Inf. Process. Syst. 34, 29541\u201329552 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR15","doi-asserted-by":"publisher","unstructured":"Wang, T.-H., Manivasagam, S., Liang, M., Yang, B., Zeng, W., Urtasun, R.: V2VNet: vehicle-to-Vehicle Communication for Joint Perception and Prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 605\u2013621. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_36","DOI":"10.1007\/978-3-030-58536-5_36"},{"key":"8_CR16","unstructured":"Xu, R., et\u00a0al.: CoBEVT: cooperative bird\u2019s eye view semantic segmentation with sparse transformers. In: arXiv preprint arXiv:2207.02202 (2022)"},{"issue":"1\u20133","key":"8_CR17","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","volume":"17","author":"BKP Horn","year":"1981","unstructured":"Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artif. Intell. 17(1\u20133), 185\u2013203 (1981)","journal-title":"Artif. Intell."},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Zhu, X., et\u00a0al.: Flow-guided feature aggregation for video object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 408\u2013417 (2017)","DOI":"10.1109\/ICCV.2017.52"},{"key":"8_CR19","unstructured":"Li, J., et\u00a0al.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning. PMLR, pp. 19730\u201319742 (2023)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Lei, Z., et\u00a0al.: Latency-aware collaborative perception. In: European Conference on Computer Vision, pp. 316\u2013332. Springer (2022)","DOI":"10.1007\/978-3-031-19824-3_19"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Lin, M., et\u00a0al.: Flowmamba: learning point cloud scene flow with global motion propagation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39. 5, pp. 5271\u20135279 (2025)","DOI":"10.1609\/aaai.v39i5.32560"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"He, C., et\u00a0al.: Msf: motion-guided sequential fusion for efficient 3d object detection from point cloud sequences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5196\u20135205 (2023)","DOI":"10.1109\/CVPR52729.2023.00503"},{"issue":"10","key":"8_CR23","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)","journal-title":"Sensors"},{"key":"8_CR24","unstructured":"Zhu, X., et\u00a0al.: Deformable detr: deformable transformers for end-toend object detection. In: arXiv preprint arXiv:2010.04159 (2020)"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"He, K., et\u00a0al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Jacob, B., et\u00a0al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2704\u20132713 (2018)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"8_CR28","unstructured":"Lin, T.-Y., et\u00a0al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u2013 2988 (2017)"},{"key":"8_CR29","unstructured":"Chen, Z., et\u00a0al.: Gradnorm: gradient normalization for adaptive loss balancing in deep multitask networks. In: International Conference on Machine Learning. PMLR, pp. 794\u2013803 (2018)"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Lang, A.H., et\u00a0al.: 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":"8_CR31","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE. 2012, pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Geiger, A., et\u00a0al.: Vision meets robotics: the kitti dataset. In: Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","DOI":"10.1177\/0278364913491297"}],"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\/978-981-95-5740-0_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T12:24:08Z","timestamp":1768220648000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5740-0_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557394","9789819557400"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5740-0_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 January 2026","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":"Shanghai","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}