{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:17:05Z","timestamp":1777655825223,"version":"3.51.4"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T00:00:00Z","timestamp":1724889600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T00:00:00Z","timestamp":1724889600000},"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":["61976029"],"award-info":[{"award-number":["61976029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s00138-024-01604-5","type":"journal-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T03:43:05Z","timestamp":1724902985000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Object Recognition Consistency in Regression for Active Detection"],"prefix":"10.1007","volume":"35","author":[{"given":"Ming","family":"Jing","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhilong","family":"Ou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,29]]},"reference":[{"issue":"12","key":"1604_CR1","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"1604_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, W., Shi, H., Tang, S., Xiao, J., Yu, Q., Zhuang, Y.: Consensus graph representation learning for better grounded image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 3394\u20133402 (2021)","DOI":"10.1609\/aaai.v35i4.16452"},{"key":"1604_CR3","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"issue":"5","key":"1604_CR4","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s00138-023-01442-x","volume":"34","author":"R Wu","year":"2023","unstructured":"Wu, R., Xin, Y., Dong, Y., Qian, J.: A dual-path u-net for pulmonary vessel segmentation method based on lightweight 3d attention. Mach. Vis. Appl. (MVA) 34(5), 87 (2023)","journal-title":"Mach. Vis. Appl. (MVA)"},{"issue":"5","key":"1604_CR5","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/s00138-023-01435-w","volume":"34","author":"M Mousa-Pasandi","year":"2023","unstructured":"Mousa-Pasandi, M., Liu, T., Massoud, Y., Lagani\u00e8re, R.: Rgb-lidar fusion for accurate 2d and 3d object detection. Mach. Vis. Appl. (MVA) 34(5), 86 (2023)","journal-title":"Mach. Vis. Appl. (MVA)"},{"issue":"5","key":"1604_CR6","first-page":"1","volume":"34","author":"P Bhadra","year":"2023","unstructured":"Bhadra, P., Balabantaray, A., Pasayat, A.K.: Mfemanet: an effective disaster image classification approach for practical risk assessment. Mach. Vis. Appl. (MVA) 34(5), 1\u201323 (2023)","journal-title":"Mach. Vis. Appl. (MVA)"},{"key":"1604_CR7","doi-asserted-by":"crossref","unstructured":"Kapoor, A., Grauman, K., Urtasun, R., Darrell, T.: Active learning with gaussian processes for object categorization. In: International Conference on Computer Vision (ICCV), pp. 1\u20138 (2007)","DOI":"10.1109\/ICCV.2007.4408844"},{"key":"1604_CR8","doi-asserted-by":"crossref","unstructured":"Freytag, A., Rodner, E., Denzler, J.: Selecting influential examples: Active learning with expected model output changes. In: European Conference on Computer Vision (ECCV), pp. 562\u2013577 (2014)","DOI":"10.1007\/978-3-319-10593-2_37"},{"key":"1604_CR9","unstructured":"Gal, Y., Islam, R., Ghahramani, Z.: Deep bayesian active learning with image data. In: Proceedings of the 34th International Conference on Machine Learning (ICML), pp. 1183\u20131192 (2017)"},{"key":"1604_CR10","unstructured":"Sener, O., Savarese, S.: Active learning for convolutional neural networks: A core-set approach. In: 6th International Conference on Learning Representations (ICLR) (2018)"},{"key":"1604_CR11","doi-asserted-by":"crossref","unstructured":"Aghdam, H.H., Gonzalez-Garcia, A., Weijer, J.v.d., L\u00f3pez, A.M.: Active learning for deep detection neural networks. In: International Conference on Computer Vision (ICCV), pp. 3672\u20133680 (2019)","DOI":"10.1109\/ICCV.2019.00377"},{"key":"1604_CR12","unstructured":"Roy, S., Unmesh, A., Namboodiri, V.P.: Deep active learning for object detection. In: The British Machine Vision Conference (BMVC), pp. 91\u2013102 (2018)"},{"key":"1604_CR13","doi-asserted-by":"crossref","unstructured":"Yoo, D., Kweon, I.S.: Learning loss for active learning. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 93\u2013102 (2019)","DOI":"10.1109\/CVPR.2019.00018"},{"key":"1604_CR14","doi-asserted-by":"crossref","unstructured":"Haussmann, E., Fenzi, M., Chitta, K., Ivanecky, J., Xu, H., Roy, D., Mittel, A., Koumchatzky, N., Farabet, C., Alvarez, J.M.: Scalable active learning for object detection. In: 2020 IEEE Intelligent Vehicles Symposium (IV), pp. 1430\u20131435 (2020)","DOI":"10.1109\/IV47402.2020.9304793"},{"key":"1604_CR15","doi-asserted-by":"crossref","unstructured":"Yuan, T., Wan, F., Fu, M., Liu, J., Xu, S., Ji, X., Ye, Q.: Multiple instance active learning for object detection. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5330\u20135339 (2021)","DOI":"10.1109\/CVPR46437.2021.00529"},{"key":"1604_CR16","doi-asserted-by":"crossref","unstructured":"Wang, K., Yan, X., Zhang, D., Zhang, L., Lin, L.: Towards human-machine cooperation: Self-supervised sample mining for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1605\u20131613 (2018)","DOI":"10.1109\/CVPR.2018.00173"},{"key":"1604_CR17","doi-asserted-by":"crossref","unstructured":"Wu, J., Chen, J., Huang, D.: Entropy-based active learning for object detection with progressive diversity constraint. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9397\u20139406 (2022)","DOI":"10.1109\/CVPR52688.2022.00918"},{"key":"1604_CR18","doi-asserted-by":"crossref","unstructured":"Park, Y., Choi, W., Kim, S., Han, D.-J., Moon, J.: Active learning for object detection with evidential deep learning and hierarchical uncertainty aggregation. In: 11th International Conference on Learning Representations(ICLR) (2022)","DOI":"10.1109\/CVPRW56347.2022.00306"},{"key":"1604_CR19","unstructured":"Liang, Z., Zeng, X., Zhao, R., Luo, P.: Meanap-guided reinforced active learning for object detection. arXiv preprint arXiv:2310.08387 (2023)"},{"key":"1604_CR20","doi-asserted-by":"crossref","unstructured":"Kao, C.-C., Lee, T.-Y., Sen, P., Liu, M.-Y.: Localization-aware active learning for object detection. In: Asian Conference on Computer Vision (ACCV), pp. 506\u2013522 (2018)","DOI":"10.1007\/978-3-030-20876-9_32"},{"key":"1604_CR21","doi-asserted-by":"crossref","unstructured":"Choi, J., Elezi, I., Lee, H.-J., Farabet, C., Alvarez, J.M.: Active learning for deep object detection via probabilistic modeling. In: International Conference on Computer Vision (ICCV), pp. 10264\u201310273 (2021)","DOI":"10.1109\/ICCV48922.2021.01010"},{"issue":"2","key":"1604_CR22","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. (IJCV) 88(2), 303\u2013338 (2010). https:\/\/doi.org\/10.1007\/s11263-009-0275-4","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"1604_CR23","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: European Conference on Computer Vision (ECCV), pp. 740\u2013755 (2014). https:\/\/doi.org\/10.48550\/arXiv.1405.0312","DOI":"10.48550\/arXiv.1405.0312"},{"key":"1604_CR24","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1604_CR25","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"1604_CR26","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"1604_CR27","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"1604_CR28","unstructured":"Fu, C.-Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 (2017)"},{"key":"1604_CR29","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: Ssd: Single shot multibox detector. In: European Conference on Computer Vision (ECCV), pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1604_CR30","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"1604_CR31","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: International Conference on Computer Vision (ICCV), pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1604_CR32","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 91\u201399 (2015)"},{"key":"1604_CR33","doi-asserted-by":"crossref","unstructured":"Beluch, W.H., Genewein, T., N\u00fcrnberger, A., K\u00f6hler, J.M.: The power of ensembles for active learning in image classification. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9368\u20139377 (2018)","DOI":"10.1109\/CVPR.2018.00976"},{"key":"1604_CR34","doi-asserted-by":"crossref","unstructured":"Joshi, A.J., Porikli, F., Papanikolopoulos, N.: Multi-class active learning for image classification. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2372\u20132379 (2009)","DOI":"10.1109\/CVPRW.2009.5206627"},{"key":"1604_CR35","doi-asserted-by":"crossref","unstructured":"Huang, S., Wang, T., Xiong, H., Huan, J., Dou, D.: Semi-supervised active learning with temporal output discrepancy. In: International Conference on Computer Vision (ICCV), pp. 3447\u20133456 (2021)","DOI":"10.1109\/ICCV48922.2021.00343"},{"key":"1604_CR36","doi-asserted-by":"crossref","unstructured":"Agarwal, S., Arora, H., Anand, S., Arora, C.: Contextual diversity for active learning. In: European Conference on Computer Vision (ECCV), pp. 137\u2013153 (2020)","DOI":"10.1007\/978-3-030-58517-4_9"},{"key":"1604_CR37","doi-asserted-by":"crossref","unstructured":"Sinha, S., Ebrahimi, S., Darrell, T.: Variational adversarial active learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5972\u20135981 (2019)","DOI":"10.1109\/ICCV.2019.00607"},{"key":"1604_CR38","doi-asserted-by":"crossref","unstructured":"Feng, D., Wei, X., Rosenbaum, L., Maki, A., Dietmayer, K.: Deep active learning for efficient training of a lidar 3d object detector. In: 2019 IEEE Intelligent Vehicles Symposium (IV), pp. 667\u2013674 (2019)","DOI":"10.1109\/IVS.2019.8814236"},{"key":"1604_CR39","unstructured":"Gal, Y., Ghahramani, Z.: Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In: International Conference on Machine Learning (ICML), pp. 1050\u20131059 (2016)"},{"key":"1604_CR40","unstructured":"Kirsch, A., Van\u00a0Amersfoort, J., Gal, Y.: Batchbald: Efficient and diverse batch acquisition for deep bayesian active learning. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 7024\u20137035 (2019)"},{"key":"1604_CR41","unstructured":"Hekimoglu, A., Brucker, A., Kayali, A.K., Schmidt, M., Marcos-Ramiro, A.: Active learning for object detection with non-redundant informative sampling. arXiv preprint arXiv:2307.08414 (2023)"},{"key":"1604_CR42","doi-asserted-by":"crossref","unstructured":"Yu, W., Zhu, S., Yang, T., Chen, C.: Consistency-based active learning for object detection. In: Conference on Computer Vision and Pattern Recognition(CVPR), pp. 3951\u20133960 (2022)","DOI":"10.1109\/CVPRW56347.2022.00440"},{"key":"1604_CR43","doi-asserted-by":"crossref","unstructured":"Wu, Z., Wang, L., Wang, W., Xia, Q., Chen, C., Hao, A., Li, S.: Pixel is all you need: adversarial trajectory-ensemble active learning for salient object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 2883\u20132891 (2023)","DOI":"10.1609\/aaai.v37i3.25390"},{"key":"1604_CR44","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations (ICLR) (2015)"},{"key":"1604_CR45","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Conference on Computer Vision and Pattern Recognition(CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1604_CR46","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01604-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-024-01604-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01604-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T04:08:00Z","timestamp":1726027680000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-024-01604-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,29]]},"references-count":46,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["1604"],"URL":"https:\/\/doi.org\/10.1007\/s00138-024-01604-5","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,29]]},"assertion":[{"value":"28 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 May 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2024","order":4,"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":"121"}}