{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T11:05:53Z","timestamp":1779793553431,"version":"3.53.1"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100012704","name":"University of Agder","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100012704","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s10489-026-07190-5","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T14:27:55Z","timestamp":1774621675000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["3DA-net: a dual-attention-based network integrating global and local context for enhanced 3D object detection"],"prefix":"10.1007","volume":"56","author":[{"given":"Soumya","family":"A","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1023-2118","authenticated-orcid":false,"given":"Linga Reddy","family":"Cenkeramaddi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Krishna Mohan","family":"C","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"key":"7190_CR1","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: Deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"7190_CR2","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"},{"key":"7190_CR3","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":"7190_CR4","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W.-L., Garg, D., Hariharan, B., Campbell, M., Weinberger, K.Q.: Pseudo-lidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00864"},{"key":"7190_CR5","doi-asserted-by":"crossref","unstructured":"Premebida, C., Carreira, J., Batista, J., Nunes, U.: Pedestrian detection combining rgb and dense lidar data. In: 2014 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 4112\u20134117 (2014). IEEE","DOI":"10.1109\/IROS.2014.6943141"},{"key":"7190_CR6","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez, A., Villalonga, G., Xu, J., V\u00e1zquez, D., Amores, J., L\u00f3pez, A.M.: Multiview random forest of local experts combining rgb and lidar data for pedestrian detection. In: 2015 IEEE Intelligent Vehicles Symposium (IV), pp. 356\u2013361 (2015)","DOI":"10.1109\/IVS.2015.7225711"},{"key":"7190_CR7","doi-asserted-by":"crossref","unstructured":"He, C., Zeng, H., Huang, J., Hua, X.-S., Zhang, L.: Structure aware single-stage 3d object detection from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11873\u201311882 (2020)","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"7190_CR8","doi-asserted-by":"crossref","unstructured":"Engelcke, M., Rao, D., Wang, D.Z., Tong, C.H., Posner, I.: Vote3deep: Fast object detection in 3d point clouds using efficient convolutional neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 1355\u20131361 (2017). IEEE","DOI":"10.1109\/ICRA.2017.7989161"},{"key":"7190_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113861","volume":"167","author":"K Kim","year":"2021","unstructured":"Kim K, Kim C, Jang C, Sunwoo M, Jo K (2021) Deep learning-based dynamic object classification using lidar point cloud augmented by layer-based accumulation for intelligent vehicles. Expert Syst Appl 167:113861","journal-title":"Expert Syst Appl"},{"key":"7190_CR10","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1016\/j.neucom.2022.06.054","volume":"501","author":"S Liu","year":"2022","unstructured":"Liu S, Huang W, Cao Y, Li D, Chen S (2022) Sms-net: Sparse multi-scale voxel feature aggregation network for lidar-based 3d object detection. Neurocomputing 501:555\u2013565","journal-title":"Neurocomputing"},{"key":"7190_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108684","volume":"128","author":"Z Li","year":"2022","unstructured":"Li Z, Yao Y, Quan Z, Xie J, Yang W (2022) Spatial information enhancement network for 3d object detection from point cloud. Pattern Recogn 128:108684","journal-title":"Pattern Recogn"},{"key":"7190_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108967","volume":"132","author":"H Guan","year":"2022","unstructured":"Guan H, Song C, Zhang Z, Tan T (2022) Monopoly: A practical monocular 3d object detector. Pattern Recogn 132:108967","journal-title":"Pattern Recogn"},{"key":"7190_CR13","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.patcog.2018.08.005","volume":"85","author":"Illumination-aware faster r-cnn for robust multispectral pedestrian detection","year":"2019","unstructured":"Illumination-aware faster r-cnn for robust multispectral pedestrian detection (2019) Pattern Recogn 85:161\u2013171","journal-title":"Pattern Recogn"},{"key":"7190_CR14","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.patrec.2017.09.038","volume":"115","author":"A Asvadi","year":"2018","unstructured":"Asvadi A, Garrote L, Premebida C, Peixoto P, Nunes UJ (2018) Multimodal vehicle detection: fusing 3d-lidar and color camera data. Pattern Recogn Lett 115:20\u201329","journal-title":"Pattern Recogn Lett"},{"key":"7190_CR15","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.patrec.2023.04.002","volume":"170","author":"P An","year":"2023","unstructured":"An P, Liang J, Ma T, Chen Y, Wang L, Ma J (2023) Prouda: Progressive unsupervised data augmentation for semi-supervised 3d object detection on point cloud. Pattern Recogn Lett 170:64\u201369","journal-title":"Pattern Recogn Lett"},{"key":"7190_CR16","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1016\/j.patrec.2023.03.016","volume":"168","author":"Z Huang","year":"2023","unstructured":"Huang Z, Zheng Z, Zhao J, Hu H, Wang Z, Chen D (2023) Psa-det3d: Pillar set abstraction for 3d object detection. Pattern Recogn Lett 168:138\u2013145","journal-title":"Pattern Recogn Lett"},{"key":"7190_CR17","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.patrec.2023.02.006","volume":"167","author":"H Sun","year":"2023","unstructured":"Sun H, Cao J, Pang Y (2023) Semantic-aware self-supervised depth estimation for stereo 3d detection. Pattern Recogn Lett 167:164\u2013170","journal-title":"Pattern Recogn Lett"},{"key":"7190_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107884","volume":"115","author":"Q Wang","year":"2021","unstructured":"Wang Q, Chen J, Deng J, Zhang X (2021) 3d-centernet: 3d object detection network for point clouds with center estimation priority. Pattern Recogn 115:107884","journal-title":"Pattern Recogn"},{"key":"7190_CR19","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems. 30 (2017)"},{"key":"7190_CR20","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929. (2020)"},{"key":"7190_CR21","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229 (2020). Springer","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"7190_CR22","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"6","key":"7190_CR23","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1007\/s10489-024-06168-5","volume":"55","author":"V Gupta","year":"2025","unstructured":"Gupta V, Srivastava V, Yadav A, Vishwakarma DK, Kumar N (2025) Freqfacenet: an enhanced transformer architecture with dual-order frequency attention for deepfake detection. Appl Intell 55(6):477","journal-title":"Appl Intell"},{"key":"7190_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, Q., Gao, M., Guo, X., Zhai, W.: Scansleepnet: A spatial-channel attention network for sleep stage classification: Y. liu et al. Applied Intelligence. 55(10), 741 (2025)","DOI":"10.1007\/s10489-025-06587-y"},{"issue":"7","key":"7190_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10489-025-06484-4","volume":"55","author":"SH Mostafaei","year":"2025","unstructured":"Mostafaei SH, Tanha J, Sharafkhaneh A (2025) Ensemblesleepnet: a novel ensemble deep learning model based on transformers and attention mechanisms using multimodal data for sleep stages classification. Appl Intell 55(7):1\u201321","journal-title":"Appl Intell"},{"key":"7190_CR26","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H.S., Koltun, V.: Point transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 16259\u201316268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"issue":"11","key":"7190_CR27","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1007\/s10489-025-06661-5","volume":"55","author":"Y Xu","year":"2025","unstructured":"Xu Y, Zhang R, Shi P, Zhou B, Ou H, Wang R (2025) Image-based instance segmentation dense point cloud multimodal 3d object detection. Appl Intell 55(11):770","journal-title":"Appl Intell"},{"issue":"12","key":"7190_CR28","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1007\/s10489-025-06742-5","volume":"55","author":"J Di","year":"2025","unstructured":"Di J, Hu Z, Zhang H, Zhang Q, Sun Z (2025) Dual cross transformer based on multi-scale fusion for fine-grained action recognition. Appl Intell 55(12):832","journal-title":"Appl Intell"},{"issue":"12","key":"7190_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10489-025-06680-2","volume":"55","author":"F Liu","year":"2025","unstructured":"Liu F, Zhou T, Wang W, Ma J, Li D, Xi W (2025) Pointcoca: Point contrastive captioner pre-trained with prompt-driven datasets generation enhances point cloud shape understanding. Appl Intell 55(12):1\u201312","journal-title":"Appl Intell"},{"key":"7190_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, Z., Cao, Y., Hu, H., Tong, X.: Group-free 3d object detection via transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2949\u20132958 (2021)","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"7190_CR31","doi-asserted-by":"crossref","unstructured":"Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2906\u20132917 (2021)","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"7190_CR32","doi-asserted-by":"crossref","unstructured":"Bai, X., Hu, Z., Zhu, X., Huang, Q., Chen, Y., Fu, H., Tai, C.-L.: Transfusion: Robust lidar-camera fusion for 3d object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1090\u20131099 (2022)","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"7190_CR33","doi-asserted-by":"crossref","unstructured":"Sheng, H., Cai, S., Liu, Y., Deng, B., Huang, J., Hua, X.-S., Zhao, M.-J.: Improving 3d object detection with channel-wise transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2743\u20132752 (2021)","DOI":"10.1109\/ICCV48922.2021.00274"},{"issue":"8","key":"7190_CR34","doi-asserted-by":"publisher","first-page":"9822","DOI":"10.1109\/TPAMI.2021.3125981","volume":"45","author":"J Yin","year":"2021","unstructured":"Yin J, Shen J, Gao X, Crandall DJ, Yang R (2021) Graph neural network and spatiotemporal transformer attention for 3d video object detection from point clouds. IEEE Trans Pattern Anal Mach Intell 45(8):9822\u20139835","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"7190_CR35","doi-asserted-by":"publisher","first-page":"2068","DOI":"10.1109\/TCSVT.2021.3082763","volume":"32","author":"Z Yuan","year":"2021","unstructured":"Yuan Z, Song X, Bai L, Wang Z, Ouyang W (2021) Temporal-channel transformer for 3d lidar-based video object detection for autonomous driving. IEEE Trans Circuits Syst Video Technol 32(4):2068\u20132078","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7190_CR36","doi-asserted-by":"crossref","unstructured":"He, C., Li, R., Li, S., Zhang, L.: Voxel set transformer: A set-to-set approach to 3d object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8417\u20138427 (2022)","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"7190_CR37","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361 (2012). IEEE","DOI":"10.1109\/CVPR.2012.6248074"},{"issue":"2","key":"7190_CR38","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"T Lin","year":"2020","unstructured":"Lin T, Goyal P, Girshick RB, He K, Doll\u00e1r P (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42(2):318\u2013327","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7190_CR39","unstructured":"Wang, D.Z., Posner, I.: Voting for voting in online point cloud object detection. In: Robotics: Science and Systems, vol. 1, pp. 10\u201315 (2015). Rome, Italy"},{"issue":"10","key":"7190_CR40","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 (2018) Second: Sparsely embedded convolutional detection. Sensors 18(10):3337","journal-title":"Sensors"},{"issue":"8","key":"7190_CR41","first-page":"2647","volume":"43","author":"S Shi","year":"2020","unstructured":"Shi S, Wang Z, Shi J, Wang X, Li H (2020) From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network. IEEE Trans Pattern Anal Mach Intell 43(8):2647\u20132664","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7190_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111856","volume":"162","author":"F Sun","year":"2024","unstructured":"Sun F, Tong G, Song Y (2024) Efficient flexible voxel-based two-stage network for 3d object detection in autonomous driving. Appl Soft Comput 162:111856","journal-title":"Appl Soft Comput"},{"key":"7190_CR43","doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.L.: Joint 3d proposal generation and object detection from view aggregation. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1\u20138 (2018). IEEE","DOI":"10.1109\/IROS.2018.8594049"},{"key":"7190_CR44","doi-asserted-by":"crossref","unstructured":"Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel r-cnn: Towards high performance voxel-based 3d object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"7190_CR45","doi-asserted-by":"crossref","unstructured":"Wang, B., Xia, C., Gao, X., Yang, Y., Ge, B., Li, K.-C., Zhang, Y.: Pv-mm3d: Point-voxel parallel dual-stream framework with dual-attention region adaptive fusion for multimodal 3d object detection. Information Fusion, 103983 (2025)","DOI":"10.1016\/j.inffus.2025.103983"},{"issue":"5","key":"7190_CR46","doi-asserted-by":"publisher","first-page":"7126","DOI":"10.1109\/JSEN.2024.3350770","volume":"24","author":"HA Hoang","year":"2024","unstructured":"Hoang HA, Bui DC, Yoo M (2024) Tsstdet: Transformation-based 3-d object detection via a spatial shape transformer. IEEE Sens J 24(5):7126\u20137139","journal-title":"IEEE Sens J"},{"key":"7190_CR47","doi-asserted-by":"crossref","unstructured":"Song, X., Yang, Y., Zhou, Z., Chen, J., Zhao, Q., Hei, X.: A dual-branch noise-resistant sparse convolution method for multi-modal 3d object detection in autonomous driving. Applied Soft Computing, 114252 (2025)","DOI":"10.1016\/j.asoc.2025.114252"},{"key":"7190_CR48","doi-asserted-by":"crossref","unstructured":"Beltr\u00e1n, J., Guindel, C., Moreno, F.M., Cruzado, D., Garcia, F., De La Escalera, A.: Birdnet: a 3d object detection framework from lidar information. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 3517\u20133523 (2018). IEEE","DOI":"10.1109\/ITSC.2018.8569311"},{"key":"7190_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xie, Z., Zhang, F., Zhao, Y.: Multi-scale hierarchical voxel-aware transformer network for 3d object detection in open-pit mines. Expert Systems with Applications, 130467 (2025)","DOI":"10.1016\/j.eswa.2025.130467"},{"key":"7190_CR50","doi-asserted-by":"crossref","unstructured":"Lu, J., Ji, G., Cai, C., Qin, K.: A transformer based on voxel spatial-channel attention for 3d object detection. Pattern Recognition Letters. (2025)","DOI":"10.1016\/j.patrec.2025.04.034"},{"key":"7190_CR51","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhao, X., Huang, T., Hu, R., Zhou, Y., Bai, X.: Tanet: Robust 3d object detection from point clouds with triple attention. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11677\u201311684 (2020)","DOI":"10.1609\/aaai.v34i07.6837"},{"key":"7190_CR52","doi-asserted-by":"crossref","unstructured":"Wu, H., Wen, C., Shi, S., Li, X., Wang, C.: Virtual sparse convolution for multimodal 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21653\u201321662 (2023)","DOI":"10.1109\/CVPR52729.2023.02074"},{"issue":"6","key":"7190_CR53","doi-asserted-by":"publisher","first-page":"5598","DOI":"10.1109\/TITS.2023.3347078","volume":"25","author":"G Xie","year":"2024","unstructured":"Xie G, Chen Z, Gao M, Hu M, Qin X (2024) Ppf-det: point-pixel fusion for multi-modal 3d object detection. IEEE Trans Intell Transp Syst 25(6):5598\u20135611","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"3","key":"7190_CR54","doi-asserted-by":"publisher","first-page":"1508","DOI":"10.1109\/TCSVT.2023.3296583","volume":"34","author":"C Yu","year":"2023","unstructured":"Yu C, Peng B, Huang Q, Lei J (2023) Pipc-3ddet: Harnessing perspective information and proposal correlation for 3d point cloud object detection. IEEE Trans Circuits Syst Video Technol 34(3):1508\u20131518","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7190_CR55","first-page":"1","volume":"71","author":"H Wang","year":"2022","unstructured":"Wang H, Chen Z, Cai Y, Chen L, Li Y, Sotelo MA, Li Z (2022) Voxel-rcnn-complex: An effective 3-d point cloud object detector for complex traffic conditions. IEEE Trans Instrum Meas 71:1\u201312","journal-title":"IEEE Trans Instrum Meas"},{"key":"7190_CR56","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., Li, H.: 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":"7190_CR57","doi-asserted-by":"crossref","unstructured":"Mao, J., Xue, Y., Niu, M., Bai, H., Feng, J., Liang, X., Xu, H., Xu, C.: Voxel transformer for 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3164\u20133173 (2021)","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"7190_CR58","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., Vora, S., Liong, V.E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., Beijbom, O.: nuscenes: A multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"7190_CR59","unstructured":"Sylvain, G.: The 1cycle policy. Github. Apr 2018 https:\/\/sgugger.github.io\/the-1cycle-policy.html github. io\/the-1cycle-policy. html. (2018)"},{"key":"7190_CR60","unstructured":"Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3d object detection. arXiv preprint arXiv:1908.09492. (2019)"},{"key":"7190_CR61","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3d object detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11784\u201311793 (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"issue":"23","key":"7190_CR62","doi-asserted-by":"publisher","first-page":"9319","DOI":"10.3390\/s23239319","volume":"23","author":"G Li","year":"2023","unstructured":"Li G, Mo Z, Ling BW-K (2023) Amff-net: An effective 3d object detector based on attention and multi-scale feature fusion. Sensors 23(23):9319","journal-title":"Sensors"},{"key":"7190_CR63","doi-asserted-by":"crossref","unstructured":"Yin, J., Shen, J., Guan, C., Zhou, D., Yang, R.: Lidar-based online 3d video object detection with graph-based message passing and spatiotemporal transformer attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11495\u201311504 (2020)","DOI":"10.1109\/CVPR42600.2020.01151"},{"key":"7190_CR64","first-page":"21224","volume":"33","author":"Q Chen","year":"2020","unstructured":"Chen Q, Sun L, Cheung E, Yuille AL (2020) Every view counts: Cross-view consistency in 3d object detection with hybrid-cylindrical-spherical voxelization. Adv Neural Inf Process Syst 33:21224\u201321235","journal-title":"Adv Neural Inf Process Syst"},{"key":"7190_CR65","doi-asserted-by":"crossref","unstructured":"Deng, S., Liang, Z., Sun, L., Jia, K.: Vista: Boosting 3d object detection via dual cross-view spatial attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8448\u20138457 (2022)","DOI":"10.1109\/CVPR52688.2022.00826"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-026-07190-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-026-07190-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-026-07190-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T10:49:22Z","timestamp":1779792562000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-026-07190-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":65,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["7190"],"URL":"https:\/\/doi.org\/10.1007\/s10489-026-07190-5","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,27]]},"assertion":[{"value":"2 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"176"}}