{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T04:12:26Z","timestamp":1751515946124,"version":"3.41.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFB3900804","2021YFB3900804","2021YFB3900804","2021YFB3900804"],"award-info":[{"award-number":["2021YFB3900804","2021YFB3900804","2021YFB3900804","2021YFB3900804"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s10044-025-01467-0","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T14:02:49Z","timestamp":1747922569000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Region-aligned single-stage point cloud object detector with direct feature compression and cross-semantic attention mechanism"],"prefix":"10.1007","volume":"28","author":[{"given":"Zhuo","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuguo","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,22]]},"reference":[{"issue":"12","key":"1467_CR1","doi-asserted-by":"publisher","first-page":"4338","DOI":"10.1109\/TPAMI.2020.3005434","volume":"43","author":"Y Guo","year":"2020","unstructured":"Guo Y, Wang H, Hu Q, Liu H, Liu L, Bennamoun M (2020) Deep learning for 3d point clouds: a survey. IEEE Trans Pattern Anal Mach Intell 43(12):4338\u20134364. https:\/\/doi.org\/10.1109\/TPAMI.2020.3005434","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1467_CR2","doi-asserted-by":"publisher","unstructured":"Zhou Y, Tuzel O (2018) Voxelnet: end-to-end learning for point cloud based 3d object detection. In: Paper Presented at the Proceedings of the IEEE Conference on computer vision and pattern recognition, 4490\u20134499. https:\/\/doi.org\/10.1109\/CVPR.2018.00472","DOI":"10.1109\/CVPR.2018.00472"},{"issue":"10","key":"1467_CR3","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2020","unstructured":"Yan Y, Mao Y, Li B (2020) Second: sparsely em-bedded convolutional detection. Sensors 18(10):3337. https:\/\/doi.org\/10.3390\/s18103337","journal-title":"Sensors"},{"key":"1467_CR4","doi-asserted-by":"publisher","unstructured":"Lang AH, Vora S, Caesar H, Zhou L, Yang J, Beijbom O (2019) Pointpillars: fast encoders for object detection from point clouds. In: Paper Presented at the Proceedings of the IEEE Conference on computer vision and pattern recognition, 12697\u201312705. https:\/\/doi.org\/10.1109\/CVPR.2019.01298","DOI":"10.1109\/CVPR.2019.01298"},{"key":"1467_CR5","doi-asserted-by":"publisher","unstructured":"He C, Zeng H, Huang J, Hua X-S, Zhang L (2020) Structure aware single-stage 3D object detection from point cloud. In: Paper Presented at the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), 11870\u201311879. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01189","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"1467_CR6","doi-asserted-by":"publisher","unstructured":"Shi S, Wang X, Li H (2019) PointRCNN: 3D object proposal generation and detection from point cloud. In: Paper Presented at the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), 770\u2013779. https:\/\/doi.org\/10.1109\/CVPR.2019.00086","DOI":"10.1109\/CVPR.2019.00086"},{"key":"1467_CR7","doi-asserted-by":"publisher","unstructured":"Shi S, Guo C, Jiang L, Wang Z, Shi J, Wang X, Li H (2020) PV-RCNN: point-voxel feature set abstraction for 3D object detection. In: Paper Presented at the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), 10526\u201310535. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01054","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"1467_CR8","doi-asserted-by":"publisher","unstructured":"Deng J, Shi S, Li P, Zhou W, Zhang Y, Li H (2021) Voxel r-cnn: towards high performance voxel-based 3d object detection. In: Paper Presented at the Proceedings of the AAAI Conference on artificial intelligence 35(2):1201\u20131209. https:\/\/doi.org\/10.1609\/aaai.v35i2.16207","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"1467_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108796","volume":"130","author":"R Qian","year":"2022","unstructured":"Qian R, Lai X, Li X (2022) 3d object detection for autonomous driving: a survey. Pattern Recognit 130:108796. https:\/\/doi.org\/10.1016\/j.patcog.2022.108796","journal-title":"Pattern Recognit"},{"key":"1467_CR10","doi-asserted-by":"publisher","unstructured":"Zhang Y, Hu Q, Xu G, Ma Y, Wan J, Guo Y (2022) Not all points are equal: learning highly efficient point-based detectors for 3D LiDAR point clouds. In: Paper Presented at the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), 18931\u201318940. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01838","DOI":"10.1109\/CVPR52688.2022.01838"},{"issue":"3","key":"1467_CR11","doi-asserted-by":"publisher","first-page":"3223","DOI":"10.1109\/TITS.2022.3225880","volume":"24","author":"K Ning","year":"2020","unstructured":"Ning K, Liu Y, Su Y, Jiang K (2020) Point-voxel and bird-eye-view representation aggregation network for single stage 3d object detection. IEEE Trans Intell Transp Syst 24(3):3223\u20133235. https:\/\/doi.org\/10.1109\/TITS.2022.3225880","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"1467_CR12","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. Preprint at arXiv:2010.11929"},{"key":"1467_CR13","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. In: Paper Presented at the Proceedings of the IEEE\/CVF International Conference on computer vision (ICCV), 9992\u201310002. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1467_CR14","doi-asserted-by":"crossref","unstructured":"Li J, Luo C, Yang X (2023) PillarNeXt: Rethinking network designs for 3D object detection in LiDAR point clouds. In: Paper Presented at the Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), 17567\u201317576","DOI":"10.1109\/CVPR52729.2023.01685"},{"key":"1467_CR15","doi-asserted-by":"publisher","unstructured":"Zheng W, Tang W, Jiang L, Fu C-W (2021) SE-SSD: self-ensembling single-stage object detector from point cloud. In: Paper Presented at the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), 14489\u201314498. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01426","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"1467_CR16","doi-asserted-by":"publisher","unstructured":"Yang H, Wang W, Chen M, Lin B, He T, Chen H, He X, Ouyang W (2023) Pvt-ssd: single-stage 3d object detec-tor with point-voxel transformer. In: Paper Presented at the Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, 13476\u201313487. https:\/\/doi.org\/10.1109\/CVPR52729.2023.01295","DOI":"10.1109\/CVPR52729.2023.01295"},{"key":"1467_CR17","doi-asserted-by":"publisher","unstructured":"Chen X, Ma H, Wan J, Li B, Xia T (2023) Multi-view 3D object detection network for autonomous driving. In: Paper Presented at the IEEE Conference on computer vision and pattern recognition (CVPR), 6526\u20136534. https:\/\/doi.org\/10.1109\/CVPR.2017.691","DOI":"10.1109\/CVPR.2017.691"},{"key":"1467_CR18","unstructured":"Ali W, Abdelkarim S, Zidan M, Zahran M, El\u00a0Sallab A (2017) YOLO3D: end-to-end real-time 3D oriented object bounding box detection from LiDAR point cloud. In: Paper Presented at the Proceedings of the European Conference on computer vision (ECCV) Workshops, 0\u20130"},{"key":"1467_CR19","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Paper Presented at the Proceedings of the IEEE Conference on computer vision and pattern recognition, 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"1467_CR20","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: Paper Presented at the Proceedings of the IEEE Conference on computer vision and pattern recognition, 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"1467_CR21","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Paper Presented at the Proceedings of the IEEE International Conference on computer vision, 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"1467_CR22","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast R-CNN. In: Paper Presented at the Proceedings of the IEEE International Conference on computer vision, 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"1467_CR23","first-page":"0","volume":"28","author":"Shaoqing Ren","year":"2015","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems (NIPS). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2015\/file\/14bfa6bb14875e45bba028a21ed38046-Paper.pdf","journal-title":"Advances in neural information processing systems (NIPS)"},{"key":"1467_CR24","doi-asserted-by":"publisher","unstructured":"Zheng W, Tang W, Chen S, Jiang L, Fu C-W (2021) CIA-SSD: confident IOU-aware single-stage object detector from point cloud. In: Paper Presented at the Proceedings of the AAAI Conference on artificial intelligence 35:3555\u20133562. https:\/\/doi.org\/10.1609\/aaai.v35i4.16470","DOI":"10.1609\/aaai.v35i4.16470"},{"key":"1467_CR25","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Paper at arXiv:1706.03762"},{"issue":"1","key":"1467_CR26","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1109\/TPAMI.2012.89","volume":"35","author":"A Borji","year":"2012","unstructured":"Borji A, Itti L (2012) State-of-the-art in visual attention modeling. IEEE Trans Pattern Anal Mach Intell 35(1):185\u2013207","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1467_CR27","doi-asserted-by":"publisher","first-page":"5455","DOI":"10.1007\/s10462-020-09825-6","volume":"53","author":"A Khan","year":"2020","unstructured":"Khan A, Sohail A, Zahoora U, Qureshi AS (2020) A survey of the recent architectures of deep convolutional neural networks. Artif Intell Rev 53:5455\u20135516","journal-title":"Artif Intell Rev"},{"key":"1467_CR28","unstructured":"Khan A, Rauf Z, Sohail A, Rehman A, Asif H, Asif A, Farooq U (2020) A survey of the vision transformers and its CNN-transformer based variants. Preprint at arXiv:2305.09880"},{"key":"1467_CR29","doi-asserted-by":"crossref","unstructured":"Zhao H, Jiang L, Jia J, Torr PH, Koltun V (2021) Point transformer. In: Paper Presented at the Proceedings of the IEEE\/CVF International Conference on computer vision (ICCV), 16259\u201316268","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"1467_CR30","doi-asserted-by":"crossref","unstructured":"Sun P, Tan M, Wang W, Liu C, Xia F, Leng Z, Anguelov D (2022) Swformer: sparse window trans-former for 3D object detection in point clouds. In: Paper Presented at the European Conference on computer vision, 426\u2013442","DOI":"10.1007\/978-3-031-20080-9_25"},{"key":"1467_CR31","doi-asserted-by":"crossref","unstructured":"Pan X, Xia Z, Song S, Li LE, Huang G (2021) 3d object detection with pointformer. In: Paper Presented at the Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, 7463\u20137472","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"1467_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3203163","volume":"60","author":"H Wu","year":"2020","unstructured":"Wu H, Deng J, Wen C, Li X, Wang C, Li J (2020) Casa: a cascade attention network for 3-d object detection from lidar point clouds. IEEE Trans Geosci Remote Sens 60:1\u201311. https:\/\/doi.org\/10.1109\/TGRS.2022.3203163","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"1467_CR33","doi-asserted-by":"publisher","first-page":"5168","DOI":"10.1109\/TIP.2021.3079796","volume":"30","author":"G Wang","year":"2021","unstructured":"Wang G, Wu X, Liu Z, Wang H (2021) Hierarchical attention learning of scene flow in 3d point clouds. IEEE Trans Image Process 30:5168\u20135181","journal-title":"IEEE Trans Image Process"},{"key":"1467_CR34","doi-asserted-by":"publisher","unstructured":"Liu Z, Yang X, Tang H, Yang S, Han S (2023) Flat-former: flattened window attention for efficient point cloud transformer. In: Paper Presented at the Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), 1200\u20131211. https:\/\/doi.org\/10.1109\/CVPR52729.2023.00122","DOI":"10.1109\/CVPR52729.2023.00122"},{"key":"1467_CR35","doi-asserted-by":"publisher","unstructured":"Bhattacharyya P, Huang C, Czarnecki K (2021) SA-Det3D: self-attention based context-aware 3D object detection. In: Paper Presented at the IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), 3022\u20133031. https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00337","DOI":"10.1109\/ICCVW54120.2021.00337"},{"key":"1467_CR36","doi-asserted-by":"publisher","unstructured":"Sheng H, Cai S, Liu Y, Deng B, Huang J, Hua X-S, Zhao M-J (2021) Improving 3D object detection with channel-wise transformer. In: Paper Presented at the IEEE\/CVF International Conference on Computer Vision (ICCV), 2723\u20132732. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00274","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"1467_CR37","doi-asserted-by":"publisher","unstructured":"Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Paper Presented at the IEEE\/CVF International Conference on Computer Vision (ICCV), 3354\u20133361. https:\/\/doi.org\/10.1109\/CVPR.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"1467_CR38","unstructured":"OpenPCDet Development Team (2020) OpenPCDet: an open-source toolbox for 3D object detection from point clouds. https:\/\/github.com\/open-mmlab\/OpenPCDet. Accessed 5 December 2023"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-025-01467-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-025-01467-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-025-01467-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T16:39:35Z","timestamp":1751474375000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-025-01467-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,22]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["1467"],"URL":"https:\/\/doi.org\/10.1007\/s10044-025-01467-0","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"type":"print","value":"1433-7541"},{"type":"electronic","value":"1433-755X"}],"subject":[],"published":{"date-parts":[[2025,5,22]]},"assertion":[{"value":"18 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2025","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":"105"}}