{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:32:30Z","timestamp":1778344350445,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729485","type":"print"},{"value":"9783031729492","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-72949-2_10","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:22:17Z","timestamp":1730301737000},"page":"162-178","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Hetecooper: Feature Collaboration Graph for\u00a0Heterogeneous Collaborative Perception"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3935-6796","authenticated-orcid":false,"given":"Congzhang","family":"Shao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1912-8536","authenticated-orcid":false,"given":"Guiyang","family":"Luo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2552-333X","authenticated-orcid":false,"given":"Quan","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Yifu","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yilin","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Kexin","family":"Gong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-9533","authenticated-orcid":false,"given":"Jinglin","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"10_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"10_CR2","unstructured":"Baldi, P.: Autoencoders, unsupervised learning, and deep architectures. In: Proceedings of ICML Workshop on Unsupervised and Transfer Learning, pp. 37\u201349. JMLR Workshop and Conference Proceedings (2012)"},{"key":"10_CR3","unstructured":"Chen, D., O\u2019Bray, L., Borgwardt, K.M.: Structure-aware transformer for graph representation learning. In: International Conference on Machine Learning (2022). https:\/\/api.semanticscholar.org\/CorpusID:246634635"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Q., Ma, X., Tang, S., Guo, J., Yang, Q., Fu, S.: F-cooper: feature based cooperative perception for autonomous vehicle edge computing system using 3d point clouds. In: Proceedings of the 4th ACM\/IEEE Symposium on Edge Computing, pp. 88\u2013100 (2019)","DOI":"10.1145\/3318216.3363300"},{"key":"10_CR5","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., L\u00f3pez, A.M., Koltun, V.: Carla: an open urban driving simulator. In: Conference on Robot Learning (2017). https:\/\/api.semanticscholar.org\/CorpusID:5550767"},{"key":"10_CR6","unstructured":"Dwivedi, V.P., Bresson, X.: A generalization of transformer networks to graphs. arXiv preprint arXiv:2012.09699 (2020)"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: 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":"10_CR8","unstructured":"Hu, Y., Fang, S., Lei, Z., Zhong, Y., Chen, S.: Where2comm: communication-efficient collaborative perception via spatial confidence maps. In: Advances in Neural Information Processing Systems, vol. 35, pp. 4874\u20134886 (2022)"},{"key":"10_CR9","unstructured":"Kreuzer, D., Beaini, D., Hamilton, W., L\u00e9tourneau, V., Tossou, P.: Rethinking graph transformers with spectral attention. In: Advances in Neural Information Processing Systems, vol. 34, pp. 21618\u201321629 (2021)"},{"key":"10_CR10","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":"10_CR11","doi-asserted-by":"crossref","unstructured":"Lei, Z., Ren, S., Hu, Y., Zhang, W., Chen, S.: Latency-aware collaborative perception. In: European Conference on Computer Vision (2022). https:\/\/api.semanticscholar.org\/CorpusID:250627145","DOI":"10.1007\/978-3-031-19824-3_19"},{"key":"10_CR12","unstructured":"Li, Y., Ren, S., Wu, P., Chen, S., Feng, C., Zhang, W.: Learning distilled collaboration graph for multi-agent perception. In: Advances in Neural Information Processing Systems, vol. 34, pp. 29541\u201329552 (2021)"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Y.C., Tian, J., Glaser, N., Kira, Z.: When2com: multi-agent perception via communication graph grouping. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4106\u20134115 (2020)","DOI":"10.1109\/CVPR42600.2020.00416"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Y.C., Tian, J., Ma, C.Y., Glaser, N., Kuo, C.W., Kira, Z.: Who2com: collaborative perception via learnable handshake communication. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 6876\u20136883. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197364"},{"key":"10_CR15","unstructured":"Lu, Y., Hu, Y., Zhong, Y., Wang, D., Chen, S., Wang, Y.: An extensible framework for open heterogeneous collaborative perception. arXiv preprint arXiv:2401.13964 (2024)"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Luo, G., et al.: Edgecooper: network-aware cooperative lidar perception for enhanced vehicular awareness. IEEE J. Sel. Areas Commun. (2023)","DOI":"10.1109\/JSAC.2023.3322764"},{"issue":"1","key":"10_CR17","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1109\/JSAC.2023.3322764","volume":"42","author":"G Luo","year":"2024","unstructured":"Luo, G., et al.: Edgecooper: network-aware cooperative lidar perception for enhanced vehicular awareness. IEEE J. Sel. Areas Commun. 42(1), 207\u2013222 (2024). https:\/\/doi.org\/10.1109\/JSAC.2023.3322764","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Luo, G., Zhang, H., Yuan, Q., Li, J.: Complementarity-enhanced and redundancy-minimized collaboration network for multi-agent perception. In: Proceedings of the 30th ACM International Conference on Multimedia (2022). https:\/\/api.semanticscholar.org\/CorpusID:252782950","DOI":"10.1145\/3503161.3548197"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Luo, G., Zhang, H., Yuan, Q., Li, J.: Complementarity-enhanced and redundancy-minimized collaboration network for multi-agent perception. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 3578\u20133586 (2022)","DOI":"10.1145\/3503161.3548197"},{"key":"10_CR20","unstructured":"Mialon, G., Chen, D., Selosse, M., Mairal, J.: Graphit: encoding graph structure in transformers. arXiv preprint arXiv:2106.05667 (2021)"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Qiu, H., Huang, P., Asavisanu, N., Liu, X., Psounis, K., Govindan, R.: Autocast: scalable infrastructure-less cooperative perception for distributed collaborative driving. arXiv preprint arXiv:2112.14947 (2021)","DOI":"10.1145\/3498361.3538925"},{"key":"10_CR22","unstructured":"Ramp\u00e1\u0161ek, L., Galkin, M., Dwivedi, V.P., Luu, A.T., Wolf, G., Beaini, D.: Recipe for a general, powerful, scalable graph transformer. In: Advances in Neural Information Processing Systems, vol. 35, pp. 14501\u201314515 (2022)"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Rauch, A., Klanner, F., Rasshofer, R., Dietmayer, K.: Car2x-based perception in a high-level fusion architecture for cooperative perception systems. In: 2012 IEEE Intelligent Vehicles Symposium, pp. 270\u2013275. IEEE (2012)","DOI":"10.1109\/IVS.2012.6232130"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Rawashdeh, Z.Y., Wang, Z.: Collaborative automated driving: a machine learning-based method to enhance the accuracy of shared information. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 3961\u20133966 (2018). https:\/\/api.semanticscholar.org\/CorpusID:54460348","DOI":"10.1109\/ITSC.2018.8569832"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Rockl, M., Strang, T., Kranz, M.: V2V communications in automotive multi-sensor multi-target tracking. In: 2008 IEEE 68th Vehicular Technology Conference, pp.\u00a01\u20135. IEEE (2008)","DOI":"10.1109\/VETECF.2008.440"},{"key":"10_CR26","unstructured":"Rong, Y., et al.: Self-supervised graph transformer on large-scale molecular data. arXiv: Biomolecules (2020). https:\/\/api.semanticscholar.org\/CorpusID:226191736"},{"key":"10_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: UMC: a unified bandwidth-efficient and multi-resolution based collaborative perception framework. arXiv preprint arXiv:2303.12400 (2023)","DOI":"10.1109\/ICCV51070.2023.00752"},{"key":"10_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/978-3-030-58536-5_36","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T-H Wang","year":"2020","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"},{"key":"10_CR30","unstructured":"Wu, Z., Jain, P., Wright, M.A., Mirhoseini, A., Gonzalez, J., Stoica, I.: Representing long-range context for graph neural networks with global attention. arXiv abs\/2201.08821 (2022). https:\/\/api.semanticscholar.org\/CorpusID:246210055"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Xiang, H., Xu, R., Ma, J.: HM-VIT: hetero-modal vehicle-to-vehicle cooperative perception with vision transformer. arXiv preprint arXiv:2304.10628 (2023)","DOI":"10.1109\/ICCV51070.2023.00033"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Xu, R., Chen, W., Xiang, H., Xia, X., Liu, L., Ma, J.: Model-agnostic multi-agent perception framework. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 1471\u20131478. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161460"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Xu, R., Guo, Y., Han, X., Xia, X., Xiang, H., Ma, J.: Opencda: an open cooperative driving automation framework integrated with co-simulation. In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 1155\u20131162 (2021). https:\/\/api.semanticscholar.org\/CorpusID:260953729","DOI":"10.1109\/ITSC48978.2021.9564825"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Xu, R., Li, J., Dong, X., Yu, H., Ma, J.: Bridging the domain gap for multi-agent perception. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 6035\u20136042. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160871"},{"key":"10_CR35","unstructured":"Xu, R., Tu, Z., Xiang, H., Shao, W., Zhou, B., Ma, J.: Cobevt: cooperative bird\u2019s eye view semantic segmentation with sparse transformers. arXiv preprint arXiv:2207.02202 (2022)"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Xu, R., et al.: V2v4real: a real-world large-scale dataset for vehicle-to-vehicle cooperative perception. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13712\u201313722 (2023)","DOI":"10.1109\/CVPR52729.2023.01318"},{"key":"10_CR37","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/978-3-031-19842-7_7","volume-title":"ECCV 2022","author":"R Xu","year":"2022","unstructured":"Xu, R., Xiang, H., Tu, Z., Xia, X., Yang, M.H., Ma, J.: V2X-ViT: vehicle-to-everything cooperative perception with vision transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13699, pp. 107\u2013124. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19842-7_7"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Xu, R., Xiang, H., Xia, X., Han, X., Li, J., Ma, J.: Opv2v: an open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 2583\u20132589. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812038"},{"issue":"10","key":"10_CR39","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":"10_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Resnest: split-attention networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2736\u20132746 (2022)","DOI":"10.1109\/CVPRW56347.2022.00309"},{"issue":"6","key":"10_CR41","doi-asserted-by":"publisher","first-page":"3400","DOI":"10.1109\/TSMC.2022.3228314","volume":"53","author":"H Zhang","year":"2023","unstructured":"Zhang, H., Luo, G., Li, Y., Wang, F.Y.: Parallel vision for intelligent transportation systems in metaverse: challenges, solutions, and potential applications. IEEE Trans. Syst. Man Cybern. Syst. 53(6), 3400\u20133413 (2023). https:\/\/doi.org\/10.1109\/TSMC.2022.3228314","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"10_CR42","unstructured":"Zhang, J., Zhang, H., Sun, L., Xia, C.: Graph-bert: only attention is needed for learning graph representations. arXiv abs\/2001.05140 (2020). https:\/\/api.semanticscholar.org\/CorpusID:210698881"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: EMP: edge-assisted multi-vehicle perception. In: Proceedings of the 27th Annual International Conference on Mobile Computing and Networking (2021). https:\/\/api.semanticscholar.org\/CorpusID:238997956","DOI":"10.1145\/3447993.3483242"},{"key":"10_CR44","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","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72949-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:43:07Z","timestamp":1730302987000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72949-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031729485","9783031729492"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72949-2_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}