{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T22:57:27Z","timestamp":1780959447860,"version":"3.54.1"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T00:00:00Z","timestamp":1776816000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001777","name":"University of Wollongong","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001777","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113702","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T06:49:59Z","timestamp":1776840599000},"page":"113702","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Efficient spatial pyramid for object detection"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1393-3841","authenticated-orcid":false,"given":"Banu Wirawan","family":"Yohanes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip O.","family":"Ogunbona","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113702_b1","doi-asserted-by":"crossref","unstructured":"V.N. Nguyen, Y. Hu, Y. Xiao, M. Salzmann, V. Lepetit, Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 6771\u20136780.","DOI":"10.1109\/CVPR52688.2022.00665"},{"key":"10.1016\/j.patcog.2026.113702_b2","series-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VII","first-page":"86","article-title":"AR-Net: Adaptive frame resolution for efficient action recognition","author":"Meng","year":"2020"},{"key":"10.1016\/j.patcog.2026.113702_b3","doi-asserted-by":"crossref","unstructured":"R. Gao, L. Wang, MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2023, pp. 9901\u20139910.","DOI":"10.1109\/ICCV51070.2023.00908"},{"key":"10.1016\/j.patcog.2026.113702_b4","series-title":"Computer Vision \u2013 ECCV 2016","first-page":"21","article-title":"SSD: Single shot MultiBox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.patcog.2026.113702_b5","doi-asserted-by":"crossref","unstructured":"J. Redmon, S. Divvala, R. Girshick, A. Farhadi, You Only Look Once: Unified, Real-Time Object Detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2016, pp. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"10.1016\/j.patcog.2026.113702_b6","series-title":"Computer Vision \u2013 ECCV 2020","first-page":"213","article-title":"End-to-End object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.patcog.2026.113702_b7","doi-asserted-by":"crossref","unstructured":"S. Zhang, X. Wang, J. Wang, J. Pang, C. Lyu, W. Zhang, P. Luo, K. Chen, Dense Distinct Query for End-to-End Object Detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 7329\u20137338.","DOI":"10.1109\/CVPR52729.2023.00708"},{"issue":"2","key":"10.1016\/j.patcog.2026.113702_b8","doi-asserted-by":"crossref","first-page":"1699","DOI":"10.1109\/TIV.2022.3213796","article-title":"Performance and challenges of 3D object detection methods in complex scenes for autonomous driving","volume":"8","author":"Wang","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.patcog.2026.113702_b9","doi-asserted-by":"crossref","unstructured":"T. Cheng, L. Song, Y. Ge, W. Liu, X. Wang, Y. Shan, YOLO-World: Real-Time Open-Vocabulary Object Detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 16901\u201316911.","DOI":"10.1109\/CVPR52733.2024.01599"},{"issue":"12","key":"10.1016\/j.patcog.2026.113702_b10","doi-asserted-by":"crossref","first-page":"8704","DOI":"10.1109\/TPAMI.2019.2918284","article-title":"Convolutional networks with dense connectivity","volume":"44","author":"Huang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113702_b11","doi-asserted-by":"crossref","unstructured":"X. Li, Y. Yang, Q. Zhao, T. Shen, Z. Lin, H. Liu, Spatial Pyramid Based Graph Reasoning for Semantic Segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020, pp. 8950\u20138959.","DOI":"10.1109\/CVPR42600.2020.00897"},{"key":"10.1016\/j.patcog.2026.113702_b12","series-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"10.1016\/j.patcog.2026.113702_b13","unstructured":"S. Mehta, M. Rastegari, MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer, in: International Conference on Learning Representations, 2022."},{"key":"10.1016\/j.patcog.2026.113702_b14","doi-asserted-by":"crossref","unstructured":"M. Tan, R. Pang, Q.V. Le, EfficientDet: Scalable and Efficient Object Detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020, pp. 10781\u201310790.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"10.1016\/j.patcog.2026.113702_b15","series-title":"Advances in Neural Information Processing Systems","first-page":"13266","article-title":"Representing long-range context for graph neural networks with global attention","volume":"34","author":"Wu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113702_b16","series-title":"Proceedings of the Twentieth International Conference on International Conference on Machine Learning","first-page":"856","article-title":"Feature selection for high-dimensional data: a fast correlation-based filter solution","author":"Yu","year":"2003"},{"key":"10.1016\/j.patcog.2026.113702_b17","doi-asserted-by":"crossref","unstructured":"A. Lavin, S. Gray, Fast Algorithms for Convolutional Neural Networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2016, pp. 4013\u20134021.","DOI":"10.1109\/CVPR.2016.435"},{"key":"10.1016\/j.patcog.2026.113702_b18","series-title":"Computer Vision \u2013 ECCV 2014","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.patcog.2026.113702_b19","doi-asserted-by":"crossref","unstructured":"A. Geiger, P. Lenz, R. Urtasun, Are we ready for autonomous driving? The KITTI vision benchmark suite, in: 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 3354\u20133361.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"10.1016\/j.patcog.2026.113702_b20","series-title":"Ultralytics YOLOv8","author":"Jocher","year":"2023"},{"key":"10.1016\/j.patcog.2026.113702_b21","doi-asserted-by":"crossref","unstructured":"T.-Y. Lin, P. Goyal, R. Girshick, K. He, P. Doll\u00e1r, Focal Loss for Dense Object Detection, in: 2017 IEEE International Conference on Computer Vision, ICCV, 2017, pp. 2999\u20133007.","DOI":"10.1109\/ICCV.2017.324"},{"key":"10.1016\/j.patcog.2026.113702_b22","doi-asserted-by":"crossref","unstructured":"B. Wu, F. Iandola, P.H. Jin, K. Keutzer, SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 129\u2013137.","DOI":"10.1109\/CVPRW.2017.60"},{"key":"10.1016\/j.patcog.2026.113702_b23","series-title":"BMVC","article-title":"Tiny-DSOD: Lightweight object detection for resource-restricted usage","author":"Yuxi Li","year":"2018"},{"key":"10.1016\/j.patcog.2026.113702_b24","doi-asserted-by":"crossref","unstructured":"M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L.-C. Chen, MobileNetV2: Inverted Residuals and Linear Bottlenecks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2018, pp. 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"10.1016\/j.patcog.2026.113702_b25","series-title":"Proceedings of the 36th International Conference on Machine Learning","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume":"Vol. 97","author":"Tan","year":"2019"},{"key":"10.1016\/j.patcog.2026.113702_b26","doi-asserted-by":"crossref","unstructured":"B.W. Yohanes, P. Ogunbona, W. Li, Joint Task of Image Segmentation and Classification for Object Detection, in: 2024 International Conference on Digital Image Computing: Techniques and Applications, DICTA, 2024, pp. 182\u2013189.","DOI":"10.1109\/DICTA63115.2024.00037"},{"key":"10.1016\/j.patcog.2026.113702_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111209","article-title":"BiFPN-YOLO: One-stage object detection integrating bi-directional feature pyramid networks","volume":"160","author":"Doherty","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113702_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.132172","article-title":"Unrolling operator splitting in learning PDEs for object detection","volume":"668","author":"Yohanes","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.113702_b29","series-title":"Advances in Neural Information Processing Systems","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume":"Vol. 29","author":"Defferrard","year":"2016"},{"key":"10.1016\/j.patcog.2026.113702_b30","unstructured":"T.N. Kipf, M. Welling, Semi-Supervised Classification with Graph Convolutional Networks, in: International Conference on Learning Representations, 2017."},{"issue":"9","key":"10.1016\/j.patcog.2026.113702_b31","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113702_b32","doi-asserted-by":"crossref","unstructured":"J. Hu, L. Shen, G. Sun, Squeeze-and-Excitation Networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2018, pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10.1016\/j.patcog.2026.113702_b33","series-title":"Advances in Neural Information Processing Systems","first-page":"4800","article-title":"Hierarchical graph representation learning with differentiable pooling","volume":"Vol. 31","author":"Ying","year":"2018"},{"key":"10.1016\/j.patcog.2026.113702_b34","series-title":"International Conference on Machine Learning","first-page":"24017","article-title":"Structural entropy guided graph hierarchical pooling","author":"Wu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113702_b35","doi-asserted-by":"crossref","unstructured":"N. Zhang, Z. Pan, T.H. Li, W. Gao, G. Li, Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 1244\u20131254.","DOI":"10.1109\/CVPR52729.2023.00126"},{"key":"10.1016\/j.patcog.2026.113702_b36","series-title":"Spectral networks and locally connected networks on graphs","author":"Bruna","year":"2014"},{"key":"10.1016\/j.patcog.2026.113702_b37","series-title":"Advances in Neural Information Processing Systems","first-page":"1853","article-title":"Symbolic graph reasoning meets convolutions","volume":"Vol. 31","author":"Liang","year":"2018"},{"key":"10.1016\/j.patcog.2026.113702_b38","doi-asserted-by":"crossref","unstructured":"Y. Chen, M. Rohrbach, Z. Yan, Y. Shuicheng, J. Feng, Y. Kalantidis, Graph-Based Global Reasoning Networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019, pp. 433\u2013442.","DOI":"10.1109\/CVPR.2019.00052"},{"key":"10.1016\/j.patcog.2026.113702_b39","doi-asserted-by":"crossref","unstructured":"T.-Y. Lin, P. Dollar, R. Girshick, K. He, B. Hariharan, S. Belongie, Feature Pyramid Networks for Object Detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017, pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"10.1016\/j.patcog.2026.113702_b40","series-title":"Proceedings of the 36th International Conference on Machine Learning","first-page":"5827","article-title":"A Tail-Index analysis of stochastic gradient noise in deep neural networks","volume":"Vol. 97","author":"Simsekli","year":"2019"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006679?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006679?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T21:57:21Z","timestamp":1780955841000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326006679"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":40,"alternative-id":["S0031320326006679"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113702","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Efficient spatial pyramid for object detection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113702","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113702"}}