{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T18:15:20Z","timestamp":1768328120234,"version":"3.49.0"},"reference-count":55,"publisher":"Elsevier BV","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.elsevier.com\/tdm\/userlicense\/1.0\/"},{"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.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.cviu.2025.104572","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T00:15:16Z","timestamp":1764202516000},"page":"104572","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["What2Keep: A communication-efficient collaborative perception framework for 3D detection via keeping valuable information"],"prefix":"10.1016","volume":"263","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9555-2687","authenticated-orcid":false,"given":"Hongkun","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengbin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2025.104572_b1","doi-asserted-by":"crossref","DOI":"10.1109\/TITS.2024.3436012","article-title":"A survey and framework of cooperative perception: From heterogeneous singleton to hierarchical cooperation","author":"Bai","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.cviu.2025.104572_b2","unstructured":"Dosovitskiy,\u00a0A., Ros,\u00a0G., Codevilla,\u00a0F., Lopez,\u00a0A., Koltun,\u00a0V., 2017. CARLA: An open urban driving simulator. In: Conference on Robot Learning (CoRL). pp. 1\u201316."},{"key":"10.1016\/j.cviu.2025.104572_b3","series-title":"2023 IEEE Intelligent Vehicles Symposium","first-page":"1","article-title":"Survey on lidar perception in adverse weather conditions","author":"Dreissig","year":"2023"},{"issue":"10","key":"10.1016\/j.cviu.2025.104572_b4","doi-asserted-by":"crossref","first-page":"7572","DOI":"10.1109\/JIOT.2021.3130054","article-title":"Autonomous driving security: State of the art and challenges","volume":"9","author":"Gao","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.cviu.2025.104572_b5","series-title":"STAMP: Scalable task and model-agnostic collaborative perception","author":"Gao","year":"2025"},{"issue":"3","key":"10.1016\/j.cviu.2025.104572_b6","doi-asserted-by":"crossref","first-page":"1972","DOI":"10.1109\/COMST.2021.3057017","article-title":"A tutorial on 5G NR V2X communications","volume":"23","author":"Garcia","year":"2021","journal-title":"IEEE Commun. Surv. & Tutorials"},{"key":"10.1016\/j.cviu.2025.104572_b7","doi-asserted-by":"crossref","unstructured":"Gu,\u00a0J., Zhang,\u00a0J., Zhang,\u00a0M., Meng,\u00a0W., Xu,\u00a0S., Zhang,\u00a0J., Zhang,\u00a0X., 2023. Feaco: Reaching robust feature-level consensus in noisy pose conditions. In: Proceedings of the 31st ACM International Conference on Multimedia. pp. 3628\u20133636.","DOI":"10.1145\/3581783.3611880"},{"issue":"6","key":"10.1016\/j.cviu.2025.104572_b8","first-page":"131","article-title":"Collaborative perception in autonomous driving: Methods, datasets, and challenges","volume":"15","author":"Han","year":"2023","journal-title":"IEEE Intell. Transp. Syst. Mag."},{"key":"10.1016\/j.cviu.2025.104572_b9","series-title":"Collaborative perception for connected and autonomous driving: Challenges, possible solutions and opportunities","author":"Hu","year":"2024"},{"key":"10.1016\/j.cviu.2025.104572_b10","series-title":"Advances in Neural Information Processing Systems","article-title":"Where2comm: Communication-efficient collaborative perception via spatial confidence maps","author":"Hu","year":"2022"},{"key":"10.1016\/j.cviu.2025.104572_b11","doi-asserted-by":"crossref","unstructured":"Hu,\u00a0Y., Peng,\u00a0J., Liu,\u00a0S., Ge,\u00a0J., Liu,\u00a0S., Chen,\u00a0S., 2024b. Communication-efficient collaborative perception via information filling with codebook. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15481\u201315490.","DOI":"10.1109\/CVPR52733.2024.01466"},{"key":"10.1016\/j.cviu.2025.104572_b12","series-title":"Autonomous driving with deep learning: A survey of state-of-art technologies","author":"Huang","year":"2020"},{"key":"10.1016\/j.cviu.2025.104572_b13","series-title":"V2X cooperative perception for autonomous driving: Recent advances and challenges","author":"Huang","year":"2023"},{"key":"10.1016\/j.cviu.2025.104572_b14","doi-asserted-by":"crossref","unstructured":"Huang,\u00a0Z., Wang,\u00a0S., Wang,\u00a0Y., Li,\u00a0W., Li,\u00a0D., Wang,\u00a0L., 2024. Roco: Robust cooperative perception by iterative object matching and pose adjustment. In: Proceedings of the 32nd ACM International Conference on Multimedia. pp. 7833\u20137842.","DOI":"10.1145\/3664647.3680559"},{"key":"10.1016\/j.cviu.2025.104572_b15","series-title":"CoDiff: Conditional diffusion model for collaborative 3D object detection","author":"Huang","year":"2025"},{"key":"10.1016\/j.cviu.2025.104572_b16","series-title":"V2X-R: Cooperative lidar-4D radar fusion with denoising diffusion for 3D object detection","author":"Huang","year":"2025"},{"key":"10.1016\/j.cviu.2025.104572_b17","series-title":"C-MASS: Combinatorial mobility-aware sensor scheduling for collaborative perception with second-order topology approximation","author":"Jia","year":"2024"},{"key":"10.1016\/j.cviu.2025.104572_b18","unstructured":"Kingma,\u00a0D.P., Ba,\u00a0J., 2015. Adam: A Method for Stochastic Optimization. In: International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.cviu.2025.104572_b19","doi-asserted-by":"crossref","unstructured":"Lang,\u00a0A.H., Vora,\u00a0S., Caesar,\u00a0H., Zhou,\u00a0L., Yang,\u00a0J., Beijbom,\u00a0O., 2019. Pointpillars: Fast encoders for object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 12697\u201312705.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"10.1016\/j.cviu.2025.104572_b20","series-title":"European Conference on Computer Vision","first-page":"316","article-title":"Latency-aware collaborative perception","author":"Lei","year":"2022"},{"issue":"4","key":"10.1016\/j.cviu.2025.104572_b21","doi-asserted-by":"crossref","first-page":"10914","DOI":"10.1109\/LRA.2022.3192802","article-title":"V2X-Sim: Multi-agent collaborative perception dataset and benchmark for autonomous driving","volume":"7","author":"Li","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.cviu.2025.104572_b22","first-page":"29541","article-title":"Learning distilled collaboration graph for multi-agent perception","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst. (NIPS)"},{"key":"10.1016\/j.cviu.2025.104572_b23","doi-asserted-by":"crossref","unstructured":"Lin,\u00a0T.-Y., Goyal,\u00a0P., Girshick,\u00a0R., He,\u00a0K., Doll\u00e1r,\u00a0P., 2017. Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"10.1016\/j.cviu.2025.104572_b24","series-title":"V2x-pc: Vehicle-to-everything collaborative perception via point cluster","author":"Liu","year":"2024"},{"key":"10.1016\/j.cviu.2025.104572_b25","unstructured":"Liu, S., Gao, C., Chen, Y., Peng, X., Kong, X., Wang, K., Xu, R., Jiang, W., Xiang, H., Ma, J., et al., 2023. Towards vehicle-to-everything autonomous driving: A survey on collaborative perception. arXiv 2023, arXiv preprint arXiv:2308.16714."},{"key":"10.1016\/j.cviu.2025.104572_b26","series-title":"An extensible framework for open heterogeneous collaborative perception","author":"Lu","year":"2024"},{"key":"10.1016\/j.cviu.2025.104572_b27","series-title":"2023 IEEE International Conference on Robotics and Automation","first-page":"4812","article-title":"Robust collaborative 3d object detection in presence of pose errors","author":"Lu","year":"2023"},{"key":"10.1016\/j.cviu.2025.104572_b28","doi-asserted-by":"crossref","unstructured":"Luo,\u00a0G., Zhang,\u00a0H., Yuan,\u00a0Q., Li,\u00a0J., 2022. Complementarity-enhanced and redundancy-minimized collaboration network for multi-agent perception. In: Proceedings of the 30th ACM International Conference on Multimedia. pp. 3578\u20133586.","DOI":"10.1145\/3503161.3548197"},{"issue":"6","key":"10.1016\/j.cviu.2025.104572_b29","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1109\/JPROC.2022.3173031","article-title":"6G for vehicle-to-everything (V2X) communications: Enabling technologies, challenges, and opportunities","volume":"110","author":"Noor-A-Rahim","year":"2022","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.cviu.2025.104572_b30","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst. (NIPS)"},{"key":"10.1016\/j.cviu.2025.104572_b31","doi-asserted-by":"crossref","unstructured":"Qiao,\u00a0D., Zulkernine,\u00a0F., 2023. Adaptive feature fusion for cooperative perception using lidar point clouds. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 1186\u20131195.","DOI":"10.1109\/WACV56688.2023.00124"},{"key":"10.1016\/j.cviu.2025.104572_b32","series-title":"European Conference on Computer Vision","first-page":"162","article-title":"Hetecooper: Feature collaboration graph for heterogeneous collaborative perception","author":"Shao","year":"2024"},{"key":"10.1016\/j.cviu.2025.104572_b33","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0T., Chen,\u00a0G., Chen,\u00a0K., Liu,\u00a0Z., Zhang,\u00a0B., Knoll,\u00a0A., Jiang,\u00a0C., 2023a. Umc: A unified bandwidth-efficient and multi-resolution based collaborative perception framework. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 8187\u20138196.","DOI":"10.1109\/ICCV51070.2023.00752"},{"key":"10.1016\/j.cviu.2025.104572_b34","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0T.-H., Manivasagam,\u00a0S., Liang,\u00a0M., Yang,\u00a0B., Zeng,\u00a0W., Urtasun,\u00a0R., 2020. V2vnet: Vehicle-to-vehicle communication for joint perception and prediction. In: Proceedings of the European Conference on Computer Vision. ECCV, pp. 605\u2013621.","DOI":"10.1007\/978-3-030-58536-5_36"},{"key":"10.1016\/j.cviu.2025.104572_b35","doi-asserted-by":"crossref","unstructured":"Wang,\u00a0B., Zhang,\u00a0L., Wang,\u00a0Z., Zhao,\u00a0Y., Zhou,\u00a0T., 2023b. Core: Cooperative reconstruction for multi-agent perception. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 8710\u20138720.","DOI":"10.1109\/ICCV51070.2023.00800"},{"key":"10.1016\/j.cviu.2025.104572_b36","first-page":"28462","article-title":"Asynchrony-robust collaborative perception via bird\u2019s eye view flow","volume":"36","author":"Wei","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2025.104572_b37","series-title":"One is plenty: A polymorphic feature interpreter for immutable heterogeneous collaborative perception","author":"Xia","year":"2024"},{"key":"10.1016\/j.cviu.2025.104572_b38","doi-asserted-by":"crossref","unstructured":"Xiang,\u00a0H., Xu,\u00a0R., Ma,\u00a0J., 2023. HM-ViT: Hetero-modal vehicle-to-vehicle cooperative perception with vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 284\u2013295.","DOI":"10.1109\/ICCV51070.2023.00033"},{"key":"10.1016\/j.cviu.2025.104572_b39","series-title":"2023 IEEE International Conference on Robotics and Automation","first-page":"1471","article-title":"Model-agnostic multi-agent perception framework","author":"Xu","year":"2023"},{"key":"10.1016\/j.cviu.2025.104572_b40","series-title":"2021 IEEE International Intelligent Transportation Systems Conference","first-page":"1155","article-title":"OpenCDA: an open cooperative driving automation framework integrated with co-simulation","author":"Xu","year":"2021"},{"key":"10.1016\/j.cviu.2025.104572_b41","series-title":"2023 IEEE International Conference on Robotics and Automation","first-page":"6035","article-title":"Bridging the domain gap for multi-agent perception","author":"Xu","year":"2023"},{"key":"10.1016\/j.cviu.2025.104572_b42","series-title":"CoDynTrust: Robust asynchronous collaborative perception via dynamic feature trust modulus","author":"Xu","year":"2025"},{"key":"10.1016\/j.cviu.2025.104572_b43","unstructured":"Xu,\u00a0R., Tu,\u00a0Z., Xiang,\u00a0H., Shao,\u00a0W., Zhou,\u00a0B., Ma,\u00a0J., 2022a. CoBEVT: Cooperative Bird\u2019s Eye View Semantic Segmentation with Sparse Transformers. In: Conference on Robot Learning (CoRL)."},{"key":"10.1016\/j.cviu.2025.104572_b44","doi-asserted-by":"crossref","unstructured":"Xu,\u00a0R., Xia,\u00a0X., Li,\u00a0J., Li,\u00a0H., Zhang,\u00a0S., Tu,\u00a0Z., Meng,\u00a0Z., Xiang,\u00a0H., Dong,\u00a0X., Song,\u00a0R., et al., 2023c. 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.","DOI":"10.1109\/CVPR52729.2023.01318"},{"key":"10.1016\/j.cviu.2025.104572_b45","doi-asserted-by":"crossref","unstructured":"Xu,\u00a0R., Xiang,\u00a0H., Tu,\u00a0Z., Xia,\u00a0X., Yang,\u00a0M.-H., Ma,\u00a0J., 2022b. V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer. In: Proceedings of the European Conference on Computer Vision. ECCV.","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"10.1016\/j.cviu.2025.104572_b46","doi-asserted-by":"crossref","unstructured":"Xu,\u00a0R., Xiang,\u00a0H., Xia,\u00a0X., Han,\u00a0X., Li,\u00a0J., Ma,\u00a0J., 2022c. Opv2v: An open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication. In: Proceedings of the International Conference on Robotics and Automation. ICRA, pp. 2583\u20132589.","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"10.1016\/j.cviu.2025.104572_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102869","article-title":"Diff-PC: Identity-preserving and 3D-aware controllable diffusion for zero-shot portrait customization","volume":"117","author":"Xu","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.cviu.2025.104572_b48","series-title":"CoSDH: Communication-efficient collaborative perception via supply-demand awareness and intermediate-late hybridization","author":"Xu","year":"2025"},{"key":"10.1016\/j.cviu.2025.104572_b49","first-page":"25151","article-title":"How2comm: Communication-efficient and collaboration-pragmatic multi-agent perception","volume":"36","author":"Yang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2025.104572_b50","doi-asserted-by":"crossref","unstructured":"Yang,\u00a0K., Yang,\u00a0D., Zhang,\u00a0J., Li,\u00a0M., Liu,\u00a0Y., Liu,\u00a0J., Wang,\u00a0H., Sun,\u00a0P., Song,\u00a0L., 2023b. Spatio-temporal domain awareness for multi-agent collaborative perception. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 23383\u201323392.","DOI":"10.1109\/ICCV51070.2023.02137"},{"key":"10.1016\/j.cviu.2025.104572_b51","doi-asserted-by":"crossref","unstructured":"Yang,\u00a0K., Yang,\u00a0D., Zhang,\u00a0J., Wang,\u00a0H., Sun,\u00a0P., Song,\u00a0L., 2023c. What2comm: Towards communication-efficient collaborative perception via feature decoupling. In: Proceedings of the 31st ACM International Conference on Multimedia. pp. 7686\u20137695.","DOI":"10.1145\/3581783.3611699"},{"key":"10.1016\/j.cviu.2025.104572_b52","doi-asserted-by":"crossref","unstructured":"Yu,\u00a0H., Luo,\u00a0Y., Shu,\u00a0M., Huo,\u00a0Y., Yang,\u00a0Z., Shi,\u00a0Y., Guo,\u00a0Z., Li,\u00a0H., Hu,\u00a0X., Yuan,\u00a0J., et al., 2022. 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\u201321370.","DOI":"10.1109\/CVPR52688.2022.02067"},{"key":"10.1016\/j.cviu.2025.104572_b53","doi-asserted-by":"crossref","unstructured":"Yuan,\u00a0Y., Xia,\u00a0Y., Cremers,\u00a0D., Sester,\u00a0M., 2025. SparseAlign: A Fully Sparse Framework for Cooperative Object Detection. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 22296\u201322305.","DOI":"10.1109\/CVPR52734.2025.02077"},{"key":"10.1016\/j.cviu.2025.104572_b54","series-title":"DSRC: Learning density-insensitive and semantic-aware collaborative representation against corruptions","author":"Zhang","year":"2025"},{"key":"10.1016\/j.cviu.2025.104572_b55","doi-asserted-by":"crossref","unstructured":"Zhang,\u00a0J., Yang,\u00a0K., Wang,\u00a0Y., Wang,\u00a0H., Sun,\u00a0P., Song,\u00a0L., 2024. Ermvp: Communication-efficient and collaboration-robust multi-vehicle perception in challenging environments. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12575\u201312584.","DOI":"10.1109\/CVPR52733.2024.01195"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314225002954?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314225002954?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T12:12:53Z","timestamp":1768306373000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314225002954"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":55,"alternative-id":["S1077314225002954"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2025.104572","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"What2Keep: A communication-efficient collaborative perception framework for 3D detection via keeping valuable information","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2025.104572","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104572"}}