{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T23:37:33Z","timestamp":1769902653042,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92267107"],"award-info":[{"award-number":["92267107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3904605"],"award-info":[{"award-number":["2023YFC3904605"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-08219-1","type":"journal-article","created":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T09:33:04Z","timestamp":1769851984000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CSFEVoxNet: 3D object detection method integrating cross-scale feature enhancement and voxel projection"],"prefix":"10.1007","volume":"82","author":[{"given":"Yongping","family":"Du","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honggui","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufeng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,31]]},"reference":[{"key":"8219_CR1","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1109\/TMM.2023.3278172","volume":"26","author":"J Sun","year":"2024","unstructured":"Sun J, Ji L, Zhu J (2024) Shared coupling - bridge scheme for weakly supervised local feature learning. IEEE Trans Multimedia 26:1200\u20131212. https:\/\/doi.org\/10.1109\/TMM.2023.3278172","journal-title":"IEEE Trans Multimedia"},{"key":"8219_CR2","doi-asserted-by":"publisher","unstructured":"Chen J, Mai H, Luo L, Chen X, Wu K (2021) Effective feature fusion network in BIFPN for small object detection. 2021 IEEE International Conference on Image Processing (ICIP), IEEE, pp. 699\u2013703. https:\/\/doi.org\/10.1109\/ICIP42928.2021.9506347","DOI":"10.1109\/ICIP42928.2021.9506347"},{"key":"8219_CR3","doi-asserted-by":"publisher","unstructured":"Zhang R, Liu Q, Wu K (2023) EFPNet: Effective fusion pyramid network for tiny person detection in UAV images. 2023 CAAI International Conference on Artificial Intelligence (CICAI), CAAI, pp. 281\u2013292. https:\/\/doi.org\/10.1007\/978-981-99-8850-1_23","DOI":"10.1007\/978-981-99-8850-1_23"},{"key":"8219_CR4","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TIP.2024.3512352","volume":"34","author":"Z Li","year":"2025","unstructured":"Li Z, Ma J (2025) Learning feature matching via matchable keypoint - assisted graph neural network. IEEE Trans Image Process 34:154\u2013169. https:\/\/doi.org\/10.1109\/TIP.2024.3512352","journal-title":"IEEE Trans Image Process"},{"key":"8219_CR5","doi-asserted-by":"publisher","unstructured":"Wang W, Lu Y, Zheng G, Zhan S, Ye X, Tan Z, Wang J, Wang G, Li X (2024) BEVSpread: Spread voxel pooling for bird's - eye - view representation in vision - based roadside 3D object detection. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 14718\u201314727. https:\/\/doi.org\/10.1109\/CVPR52733.2024.01394","DOI":"10.1109\/CVPR52733.2024.01394"},{"key":"8219_CR6","doi-asserted-by":"crossref","unstructured":"Liu X, Xue N, Wu T (2022) Learning auxiliary monocular contexts helps monocular 3D object detection. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, AAAI, pp. 1810\u20131818. 10.1609\/ aaai.v36i2.20074","DOI":"10.1609\/aaai.v36i2.20074"},{"key":"8219_CR7","doi-asserted-by":"publisher","unstructured":"Ma X, Zhang Y, Xu D, Zhou D, Yi S, Li H, Ouyang W (2021) Delving into localization errors for monocular 3D object detection. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 4719\u20134728. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00469","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"8219_CR8","doi-asserted-by":"publisher","unstructured":"Wang Y, Chao WL, Garg D, Hariharan B, Campbell M, Weinberger KQ (2019) Pseudo - LiDAR from visual depth estimation: Bridging the gap in 3D object detection for autonomous driving. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 8437\u20138445. https:\/\/doi.org\/10.1109\/CVPR.2019.00864","DOI":"10.1109\/CVPR.2019.00864"},{"key":"8219_CR9","doi-asserted-by":"publisher","unstructured":"Park D, Ambrus R, Guizilini V, Li J, Gaidon A (2021) Is pseudo - LiDAR needed for monocular 3D object detection?. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE, pp. 3122\u20133132. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00313","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"8219_CR10","doi-asserted-by":"publisher","unstructured":"Rukhovich D et al., (2022) ImVoxelNet: Image to voxels projection for monocular and multi - view general - purpose 3D object detection. 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE, pp. 1265\u20131274. https:\/\/doi.org\/10.1109\/WACV51458.2022.00133","DOI":"10.1109\/WACV51458.2022.00133"},{"key":"8219_CR11","unstructured":"Zhang R, Yu Z, Cao S-Y, Zhu L, Zhang G, Bai X, Shen H-L (2025) Boosting multi-view indoor 3D object detection via adaptive 3D volume construction. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), accepted for publication"},{"key":"8219_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2025.113140","volume":"177","author":"Z Chen","year":"2025","unstructured":"Chen Z, Peng C, Liu S, Ding W (2025) Visual object tracking: review and challenges. Appl Soft Comput 177:113140. https:\/\/doi.org\/10.1016\/j.asoc.2025.113140","journal-title":"Appl Soft Comput"},{"key":"8219_CR13","doi-asserted-by":"publisher","unstructured":"Luo Z, Fu W, Liu S, Anwar S, Saqib M, Bakshi S, Muhammad K (2024) Cefdet: Cognitive effectiveness network based on fuzzy inference for action detection. Proceedings of the 32nd ACM International Conference on Multimedia (ACM MM \u201924), ACM, pp. 7985\u20137994. https:\/\/doi.org\/10.1145\/3664647.3681226","DOI":"10.1145\/3664647.3681226"},{"key":"8219_CR14","doi-asserted-by":"publisher","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 936\u2013944. https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"8219_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127809","volume":"593","author":"B Han","year":"2024","unstructured":"Han B, He L et al (2024) Weighted parallel decoupled feature pyramid network for object detection. Neurocomputing 593:127809. https:\/\/doi.org\/10.1016\/j.neucom.2024.127809","journal-title":"Neurocomputing"},{"key":"8219_CR16","doi-asserted-by":"publisher","unstructured":"Shi Z, Hu J, Ren J, Ye H, Yuan X, Ouyang Y, He J, Ji B, Guo J (2025) HS - FPN: High frequency and spatial perception FPN for tiny object detection. Proc. AAAI Conf. Artif. Intell. (AAAI), AAAI, pp. 6896\u20136904. https:\/\/doi.org\/10.1609\/aaai.v39i7.32740","DOI":"10.1609\/aaai.v39i7.32740"},{"issue":"9","key":"8219_CR17","doi-asserted-by":"publisher","first-page":"7820","DOI":"10.1109\/TCSVT.2024.3376773","volume":"34","author":"G Yang","year":"2024","unstructured":"Yang G, Lei J, Tian H, Feng Z, Liang R (2024) Asymptotic feature pyramid network for labeling pixels and regions. IEEE Trans Circuits Syst Video Technol 34(9):7820\u20137829. https:\/\/doi.org\/10.1109\/TCSVT.2024.3376773","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"8219_CR18","doi-asserted-by":"publisher","first-page":"4341","DOI":"10.1109\/TIP.2023.3297408","volume":"32","author":"Y Quan","year":"2023","unstructured":"Quan Y, Zhang D, Zhang L, Tang J (2023) Centralized feature pyramid for object detection. IEEE Trans Image Process 32:4341\u20134354. https:\/\/doi.org\/10.1109\/TIP.2023.3297408","journal-title":"IEEE Trans Image Process"},{"issue":"10","key":"8219_CR19","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2021","unstructured":"Wang J et al (2021) Deep high - resolution representation learning for visual recognition. IEEE Trans Pattern Anal Mach Intell 43(10):3349\u20133364. https:\/\/doi.org\/10.1109\/TPAMI.2020.2983686","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8219_CR20","doi-asserted-by":"publisher","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End - to - end object detection with transformers. Computer Vision \u2013 ECCV 2020, vol. 12346, Springer. https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"8219_CR21","doi-asserted-by":"publisher","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE, pp. 9992\u201310002. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"8219_CR22","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze - and - excitation networks. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE, pp. 7132\u20137141. 10.1109\/ CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"8219_CR23","doi-asserted-by":"publisher","unstructured":"Tian Z, Shen C, Chen H, He T (2019) FCOS: Fully convolutional one - stage object detection. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE, pp. 9626\u20139635. https:\/\/doi.org\/10.1109\/ICCV.2019.00972","DOI":"10.1109\/ICCV.2019.00972"},{"key":"8219_CR24","doi-asserted-by":"publisher","unstructured":"Song S, Lichtenberg SP, Xiao J (2015) SUN RGB - D: A RGB - D scene understanding benchmark suite. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 567\u2013576. https:\/\/doi.org\/10.1109\/CVPR.2015.7298655","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"8219_CR25","doi-asserted-by":"publisher","unstructured":"Chen K, Wang J, Pang J, Cao Y, Xiong Y, Li X, Sun S, Feng W, Liu Z, Xu J, Zhang Z, Cheng D, Zhu C, Cheng T, Zhao Q, Li B, Lu X, Zhu R, Wu Y, Dai J, Wang J, Shi J, Ouyang W, Loy CC, Lin D (2019) MMDetection: Open MMLab detection toolbox and benchmark, arXiv preprint arXiv:1906.07155. https:\/\/doi.org\/10.48550\/arxiv.1906.07155","DOI":"10.48550\/arxiv.1906.07155"},{"key":"8219_CR26","doi-asserted-by":"publisher","unstructured":"Nie Y, Han X, Guo S, Zheng Y, Chang J, Zhang JJ (2020) Total3DUnderstanding: Joint layout, object pose and mesh reconstruction for indoor scenes from a single image. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 52\u201361. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00013","DOI":"10.1109\/CVPR42600.2020.00013"},{"key":"8219_CR27","doi-asserted-by":"publisher","unstructured":"Brazil G, Kumar A et al., (2023) Omni3D: A large benchmark and model for 3D object detection in the wild. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 13154\u201313164. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01264","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"8219_CR28","doi-asserted-by":"publisher","unstructured":"Ge H, Yu X-h, Zhao C, Guo L, Huang Y, Liu R, Itti L, Wu J (2023) 3Dcopy - paste: Physically plausible object insertion for monocular 3D detection. Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS '23), Curran Associates Inc., pp. 17057\u201317071. https:\/\/doi.org\/10.48550\/arXiv.2312.05277","DOI":"10.48550\/arXiv.2312.05277"},{"key":"8219_CR29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_5","author":"Z Wang","year":"2024","unstructured":"Wang Z, Li Y, Liu T, Zhao H, Wang S (2024) OV-Uni3DETR: towards unified open-vocabulary 3D object detection via cycle-modality propagation. European Conference on Computer Vision (ECCV). https:\/\/doi.org\/10.1007\/978-3-031-72970-6_5","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"8219_CR30","doi-asserted-by":"publisher","unstructured":"Lazarow J, Griffiths D, Kohavi G, Crespo F, Dehghan A (2024S) Cubify Anything: Scaling indoor 3D object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 22225\u201322233. https:\/\/doi.org\/10.1109\/CVPR52734.2025.02070","DOI":"10.1109\/CVPR52734.2025.02070"},{"key":"8219_CR31","doi-asserted-by":"publisher","first-page":"7960","DOI":"10.1109\/TPAMI.2025.3574363","volume":"47","author":"Z Li","year":"2025","unstructured":"Li Z, Xu X, Lim S-N, Zhao H (2025) Toward unified 3D object detection via algorithm and data unification. IEEE Trans Pattern Anal Mach Intell 47:7960\u20137975. https:\/\/doi.org\/10.1109\/TPAMI.2025.3574363","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8219_CR32","doi-asserted-by":"publisher","first-page":"72145","DOI":"10.52202\/079017-2303","volume":"37","author":"R Huang","year":"2024","unstructured":"Huang R, Zheng H, Wang Y, Xia Z, Pavone M, Huang G (2024) Training an open-vocabulary monocular 3D detection model without 3D data. Adv Neural Inf Process Syst 37:72145\u201372169. https:\/\/doi.org\/10.52202\/079017-2303","journal-title":"Adv Neural Inf Process Syst"},{"key":"8219_CR33","doi-asserted-by":"publisher","unstructured":"Dai A, Chang AX et al., (2017) T. Funkhouser, and M. Nie\u00dfner, ScanNet: Richly annotated 3D reconstructions of indoor scenes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2432\u20132443. https:\/\/doi.org\/10.1109\/CVPR.2017.261","DOI":"10.1109\/CVPR.2017.261"},{"key":"8219_CR34","doi-asserted-by":"publisher","unstructured":"Dehghan A, Baruch G, Chen Z, Feigin Y, Fu P, Gebauer T, Kurz D, Dimry T, Joffe B, Schwartz A, Shulman E (2021) ARKitScenes: A diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data. Proceedings of the Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track. https:\/\/doi.org\/10.48550\/arXiv.2111.08897","DOI":"10.48550\/arXiv.2111.08897"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-08219-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-08219-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-08219-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T09:33:07Z","timestamp":1769851987000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-08219-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":34,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["8219"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-08219-1","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,31]]},"assertion":[{"value":"11 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"109"}}