{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T17:00:52Z","timestamp":1781024452078,"version":"3.54.1"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":["Image and Vision Computing"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.imavis.2026.106023","type":"journal-article","created":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T15:24:59Z","timestamp":1778945099000},"page":"106023","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A multi-view feature collaborative optimization method for object detection"],"prefix":"10.1016","volume":"172","author":[{"given":"Jiaji","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runhai","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangning","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaihang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.imavis.2026.106023_b1","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106023_b2","doi-asserted-by":"crossref","unstructured":"T.-Y. Lin, P. Goyal, R. Girshick, K. He, P. Doll\u00e1r, Focal loss for dense object detection, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"10.1016\/j.imavis.2026.106023_b3","series-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"10.1016\/j.imavis.2026.106023_b4","series-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"issue":"1","key":"10.1016\/j.imavis.2026.106023_b5","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1038\/s41597-025-04482-2","article-title":"MMFW-UAV dataset: multi-sensor and multi-view fixed-wing UAV dataset for air-to-air vision tasks","volume":"12","author":"Liu","year":"2025","journal-title":"Sci. Data"},{"key":"10.1016\/j.imavis.2026.106023_b6","doi-asserted-by":"crossref","unstructured":"L. Fan, D. Fan, Z. Hu, Y. Ding, D. Di, K. Yi, M. Pagnucco, Y. Song, Manta: A large-scale multi-view and visual-text anomaly detection dataset for tiny objects, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 25518\u201325527.","DOI":"10.1109\/CVPR52734.2025.02376"},{"issue":"11","key":"10.1016\/j.imavis.2026.106023_b7","doi-asserted-by":"crossref","first-page":"2129","DOI":"10.3390\/electronics14112129","article-title":"A globally collaborative multi-view k-Means clustering","volume":"14","author":"Sinaga","year":"2025","journal-title":"Electronics"},{"key":"10.1016\/j.imavis.2026.106023_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2025.105493","article-title":"Strengthening incomplete multi-view clustering: An attention contrastive learning method","volume":"157","author":"Hou","year":"2025","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106023_b9","doi-asserted-by":"crossref","unstructured":"G. Ke, B. Wang, X. Wang, S. He, Rethinking multi-view representation learning via distilled disentangling, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 26774\u201326783.","DOI":"10.1109\/CVPR52733.2024.02528"},{"key":"10.1016\/j.imavis.2026.106023_b10","doi-asserted-by":"crossref","unstructured":"X. Yu, M. Xu, Y. Zhang, H. Liu, C. Ye, Y. Wu, Z. Yan, C. Zhu, Z. Xiong, T. Liang, et al., Mvimgnet: A large-scale dataset of multi-view images, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 9150\u20139161.","DOI":"10.1109\/CVPR52729.2023.00883"},{"issue":"6","key":"10.1016\/j.imavis.2026.106023_b11","first-page":"1","article-title":"MvImgNet2. 0: A larger-scale dataset of multi-view images","volume":"43","author":"Wu","year":"2024","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.imavis.2026.106023_b12","doi-asserted-by":"crossref","unstructured":"C. Wang, W. Zhu, B.-B. Gao, Z. Gan, J. Zhang, Z. Gu, S. Qian, M. Chen, L. Ma, Real-iad: A real-world multi-view dataset for benchmarking versatile industrial anomaly detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 22883\u201322892.","DOI":"10.1109\/CVPR52733.2024.02159"},{"key":"10.1016\/j.imavis.2026.106023_b13","doi-asserted-by":"crossref","unstructured":"M. Engilberge, H. Shi, Z. Wang, P. Fua, Two-level data augmentation for calibrated multi-view detection, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 128\u2013136.","DOI":"10.1109\/WACV56688.2023.00021"},{"issue":"1","key":"10.1016\/j.imavis.2026.106023_b14","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1007\/s10489-023-05163-6","article-title":"Multi-view and multi-augmentation for self-supervised visual representation learning","volume":"54","author":"Huang","year":"2024","journal-title":"Appl. Intell."},{"key":"10.1016\/j.imavis.2026.106023_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108064","article-title":"Collaborative feature-weighted multi-view fuzzy c-means clustering","volume":"119","author":"Yang","year":"2021","journal-title":"Pattern Recognit."},{"issue":"4","key":"10.1016\/j.imavis.2026.106023_b16","doi-asserted-by":"crossref","first-page":"2056","DOI":"10.1109\/TCSVT.2023.3300319","article-title":"A clustering-guided contrastive fusion for multi-view representation learning","volume":"34","author":"Ke","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.imavis.2026.106023_b17","doi-asserted-by":"crossref","unstructured":"Y. Pang, X. Zhao, T.-Z. Xiang, L. Zhang, H. Lu, Zoom in and out: A mixed-scale triplet network for camouflaged object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 2160\u20132170.","DOI":"10.1109\/CVPR52688.2022.00220"},{"issue":"12","key":"10.1016\/j.imavis.2026.106023_b18","doi-asserted-by":"crossref","first-page":"9205","DOI":"10.1109\/TPAMI.2024.3417329","article-title":"Zoomnext: A unified collaborative pyramid network for camouflaged object detection","volume":"46","author":"Pang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2026.106023_b19","doi-asserted-by":"crossref","unstructured":"D. Zheng, X. Zheng, L.T. Yang, Y. Gao, C. Zhu, Y. Ruan, Mffn: Multi-view feature fusion network for camouflaged object detection, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 6232\u20136242.","DOI":"10.1109\/WACV56688.2023.00617"},{"issue":"11","key":"10.1016\/j.imavis.2026.106023_b20","doi-asserted-by":"crossref","first-page":"11184","DOI":"10.1109\/TCSVT.2024.3417607","article-title":"A universal multi-view guided network for salient object and camouflaged object detection","volume":"34","author":"Song","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.imavis.2026.106023_b21","article-title":"Stealth sight: A multi perspective approach for camouflaged object detection","volume":"157","author":"Jayanthan","year":"2025","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106023_b22","article-title":"More observation leads to more clarity: Multi-view collaboration network for camouflaged object detection","author":"Wang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.imavis.2026.106023_b23","series-title":"Learning multi-view anomaly detection","author":"He","year":"2024"},{"key":"10.1016\/j.imavis.2026.106023_b24","series-title":"Learning multi-view multi-class anomaly detection","author":"Yu","year":"2025"},{"key":"10.1016\/j.imavis.2026.106023_b25","doi-asserted-by":"crossref","DOI":"10.1109\/TMECH.2025.3566311","article-title":"Multi-View attention guided feature learning for unsupervised surface defect detection","author":"Zhou","year":"2025","journal-title":"IEEE\/ASME Trans. Mechatronics"},{"key":"10.1016\/j.imavis.2026.106023_b26","series-title":"European Conference on Computer Vision","first-page":"369","article-title":"Giqa: Generated image quality assessment","author":"Gu","year":"2020"},{"key":"10.1016\/j.imavis.2026.106023_b27","doi-asserted-by":"crossref","unstructured":"S.A. Golestaneh, S. Dadsetan, K.M. Kitani, No-reference image quality assessment via transformers, relative ranking, and self-consistency, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 1220\u20131230.","DOI":"10.1109\/WACV51458.2022.00404"},{"key":"10.1016\/j.imavis.2026.106023_b28","doi-asserted-by":"crossref","unstructured":"R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra, Grad-cam: Visual explanations from deep networks via gradient-based localization, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"issue":"9","key":"10.1016\/j.imavis.2026.106023_b29","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.imavis.2026.106023_b30","doi-asserted-by":"crossref","unstructured":"H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia, Pyramid scene parsing network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"},{"issue":"4","key":"10.1016\/j.imavis.2026.106023_b31","doi-asserted-by":"crossref","first-page":"1486","DOI":"10.1109\/TSMC.2018.2871750","article-title":"Detection of power line insulator defects using aerial images analyzed with convolutional neural networks","volume":"50","author":"Tao","year":"2018","journal-title":"IEEE Trans. Syst. Man Cybern.: Syst."},{"key":"10.1016\/j.imavis.2026.106023_b32","series-title":"VPMBGI: Vietnamese public merged dataset of broken glass insulator for UAV inspection of power lines","year":"2023"},{"key":"10.1016\/j.imavis.2026.106023_b33","series-title":"Insulator defect detection","author":"Kulkarni","year":"2021"},{"issue":"11","key":"10.1016\/j.imavis.2026.106023_b34","doi-asserted-by":"crossref","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","article-title":"Detection and tracking meet drones challenge","volume":"44","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2026.106023_b35","series-title":"Ultralytics YOLO","author":"Jocher","year":"2023"},{"key":"10.1016\/j.imavis.2026.106023_b36","doi-asserted-by":"crossref","unstructured":"Y. Zhao, W. Lv, S. Xu, J. Wei, G. Wang, Q. Dang, Y. Liu, J. Chen, Detrs beat yolos on real-time object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 16965\u201316974.","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"10.1016\/j.imavis.2026.106023_b37","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume":"33","author":"Li","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106023_b38","series-title":"2021 IEEE\/CVF International Conference on Computer Vision","first-page":"3490","article-title":"Tood: Task-aligned one-stage object detection","author":"Feng","year":"2021"},{"key":"10.1016\/j.imavis.2026.106023_b39","article-title":"YOLO-DTAD: Dynamic task alignment detection model for multi-category power defects image","author":"Jiao","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.imavis.2026.106023_b40","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"Yolov9: Learning what you want to learn using programmable gradient information","author":"Wang","year":"2024"},{"key":"10.1016\/j.imavis.2026.106023_b41","first-page":"107984","article-title":"Yolov10: Real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.imavis.2026.106023_b42","series-title":"2018 IEEE Winter Conference on Applications of Computer Vision","first-page":"839","article-title":"Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks","author":"Chattopadhay","year":"2018"}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001307?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001307?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:28:37Z","timestamp":1781022517000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885626001307"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":42,"alternative-id":["S0262885626001307"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106023","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A multi-view feature collaborative optimization method for object detection","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106023","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"106023"}}