{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T16:48:30Z","timestamp":1791046110506,"version":"4.1.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T00:00:00Z","timestamp":1634256000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T00:00:00Z","timestamp":1634256000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61876152"],"award-info":[{"award-number":["61876152"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U19B2037"],"award-info":[{"award-number":["U19B2037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People\u2019s Republic of China","doi-asserted-by":"publisher","award":["2020AAA0106900"],"award-info":[{"award-number":["2020AAA0106900"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1007\/s11263-021-01523-2","type":"journal-article","created":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T09:45:09Z","timestamp":1634291109000},"page":"3299-3312","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["NAS-FCOS: Efficient Search for Object Detection Architectures"],"prefix":"10.1007","volume":"129","author":[{"given":"Ning","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7689-3405","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,10,15]]},"reference":[{"key":"1523_CR1","unstructured":"Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934"},{"key":"1523_CR2","unstructured":"Cai, H., Zhu, L., & Han, S. (2019). ProxylessNAS: Direct neural architecture search on target task and hardware. In Proceedings of international conference learning representations."},{"key":"1523_CR3","doi-asserted-by":"crossref","unstructured":"Chen, B., Ghiasi, G., Liu, H., Lin, T. Y., Kalenichenko, D., Adam, H., & Le, Q. V. (2020). Mnasfpn: Learning latency-aware pyramid architecture for object detection on mobile devices. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13607\u201313616","DOI":"10.1109\/CVPR42600.2020.01362"},{"key":"1523_CR4","unstructured":"Chen, Y., Yang, T., Zhang, X., Meng, G., Pan, C., & Sun, J. (2019). DetNAS: Neural architecture search on object detection. In Proceedings of advances in neural information processing systems."},{"key":"1523_CR5","doi-asserted-by":"crossref","unstructured":"Du, X., Lin, T. Y., Jin, P., Ghiasi, G., Tan, M., Cui, Y., Le, Q. V., & Song, X. (2020). Spinenet: Learning scale-permuted backbone for recognition and localization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11592\u201311601.","DOI":"10.1109\/CVPR42600.2020.01161"},{"key":"1523_CR6","doi-asserted-by":"crossref","unstructured":"Elsken, T., Metzen, J.H., & Hutter, F. (2019). Neural architecture search: A survey. The Journal of Machine Learning Research.","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"1523_CR7","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T. Y., Pang, R., & Le, Q. V. (2019). NAS-FPN: Learning scalable feature pyramid architecture for object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00720"},{"key":"1523_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2015.169"},{"key":"1523_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2014.81"},{"key":"1523_CR10","doi-asserted-by":"crossref","unstructured":"Guo, J., Han, K., Wang, Y., Zhang, C., Yang, Z., Wu, H., Chen, X., & Xu, C. (2020a). Hit-detector: Hierarchical trinity architecture search for object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11405\u201311414.","DOI":"10.1109\/CVPR42600.2020.01142"},{"key":"1523_CR11","doi-asserted-by":"crossref","unstructured":"Guo, Z., Zhang, X., Mu, H., Heng, W., Liu, Z., Wei, Y., & Sun, J. (2020b). Single path one-shot neural architecture search with uniform sampling. In Proceedings of European conference on computer vision, pp. 544\u2013560.","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"1523_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pp. 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"1523_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Identity mappings in deep residual networks. In Proceedings of European conference on computer vision, pp. 630\u2013645.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"1523_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, C., Xu, H., Zhang, W., Liang, X., & Li, Z. (2020). Sp-nas: Serial-to-parallel backbone search for object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11863\u201311872.","DOI":"10.1109\/CVPR42600.2020.01188"},{"key":"1523_CR15","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., & Doll\u00e1r, P. (2019). Panoptic feature pyramid networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00656"},{"key":"1523_CR16","doi-asserted-by":"crossref","unstructured":"Kong, T., Sun, F., Liu, H., Jiang, Y., & Shi, J. (2019) Foveabox: Beyond anchor-based object detector. arXiv preprint arXiv:1904.03797","DOI":"10.1109\/TIP.2020.3002345"},{"key":"1523_CR17","doi-asserted-by":"crossref","unstructured":"Law, H., & Deng, J. (2018). Cornernet: Detecting objects as paired keypoints. In Proceedings of the European conference on computer vision, pp. 734\u2013750.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"1523_CR18","unstructured":"Liang, F., Lin, C., Guo, R., Sun, M., Wu, W., Yan, J., & Ouyang, W. (2020). Computation reallocation for object detection. In Proceedings of international conference on learning representations."},{"key":"1523_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"1523_CR20","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 Proceedings of the IEEE international conference on computer vision, pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"1523_CR21","doi-asserted-by":"crossref","unstructured":"Liu, C., Chen, L. C., Schroff, F., Adam, H., Hua, W., Yuille, A., & Fei-Fei, L. (2019). Auto-deeplab: Hierarchical neural architecture search for semantic image segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00017"},{"key":"1523_CR22","doi-asserted-by":"crossref","unstructured":"Liu, H., Peng, C., Yu, C., Wang, J., Liu, X., Yu, G., & Jiang, W. (2019). An end-to-end network for panoptic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00633"},{"key":"1523_CR23","unstructured":"Liu, H., Simonyan, K., & Yang, Y. (2019). Darts: Differentiable architecture search. In Proceedings of international conference on learning representations."},{"key":"1523_CR24","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. (2016). SSD: Single shot multibox detector. In Proceedings of European conference on computer vision, pp. 21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1523_CR25","doi-asserted-by":"crossref","unstructured":"Nekrasov, V., Chen, H., Shen, C., & Reid, I. (2019). Fast neural architecture search of compact semantic segmentation models via auxiliary cells. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00934"},{"key":"1523_CR26","unstructured":"Peng, J., Sun, M., Zhang, Z. X., Tan, T., & Yan, J. (2019). Efficient neural architecture transformation search in channel-level for object detection. In Proceedings of advances in neural information processing system, pp. 14313\u201314322."},{"key":"1523_CR27","unstructured":"Pham, H., Guan, M. Y., Zoph, B., Le, Q. V., & Dean, J. (2018). Efficient neural architecture search via parameter sharing. In Proceedings of international conference on machine learning."},{"key":"1523_CR28","doi-asserted-by":"crossref","unstructured":"Redmon, J., & Farhadi, A. (2017). Yolo9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.690"},{"key":"1523_CR29","unstructured":"Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"1523_CR30","doi-asserted-by":"crossref","unstructured":"Redmon Joseph, S. D. R. G., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.91"},{"key":"1523_CR31","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, pp. 91\u201399."},{"key":"1523_CR32","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition., pp. 4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1523_CR33","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347."},{"key":"1523_CR34","doi-asserted-by":"crossref","unstructured":"Stamoulis, D., Ding, R., Wang, D., Lymberopoulos, D., Priyantha, B., Liu, J., & Marculescu, D. (2019). Single-path NAS: Designing hardware-efficient convnets in less than 4 hours. arXiv preprint arXiv:1904.02877.","DOI":"10.1007\/978-3-030-46147-8_29"},{"key":"1523_CR35","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., & Le, Q. V. (2020). Efficientdet: Scalable and efficient object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10781\u201310790.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"1523_CR36","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., & He, T. (2019). FCOS: Fully convolutional one-stage object detection. In Proceedings of the IEEE\/CVF international conference on computer vision.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"1523_CR37","doi-asserted-by":"crossref","unstructured":"Uijlings, J., Sande, K. V. D., Gevers, T., & Smeulders, A. (2013). Selective search for object recognition. International Journal of Computer Vision.","DOI":"10.1007\/s11263-013-0620-5"},{"key":"1523_CR38","doi-asserted-by":"crossref","unstructured":"Wu, Y., & He, K. (2018). Group normalization. In Proceedings of the European conference on computer vision, pp. 3\u201319.","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"1523_CR39","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. In Proceedings of the European conference on computer vision.","DOI":"10.1109\/CVPR.2017.634"},{"key":"1523_CR40","unstructured":"Xiong, Y., Liu, H., Gupta, S., Akin, B., Bender, G., Kindermans, P.J., Tan, M., Singh, V., & Chen, B. (2020). MobileDets: Searching for object detection architectures for mobile accelerators. arXiv preprint arXiv:2004.14525"},{"key":"1523_CR41","doi-asserted-by":"crossref","unstructured":"Xu, H., Yao, L., Zhang, W., Liang, X., & Li, Z. (2019). Auto-FPN: Automatic network architecture adaptation for object detection beyond classification. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 6649\u20136658.","DOI":"10.1109\/ICCV.2019.00675"},{"key":"1523_CR42","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yinghao, X., Han, X., Zheng, Z., Raquel, U., Liwei, W., et al. (2020). Dense reppoints: Representing visual objects with dense point sets. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-030-58589-1_14"},{"key":"1523_CR43","doi-asserted-by":"crossref","unstructured":"Yao, L., Xu, H., Zhang, W., Liang, X., & Li, Z. (2020). SM-NAS: Structural-to-modular neural architecture search for object detection. In Proceedings of the AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v34i07.6958"},{"key":"1523_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, T., & Wu, X. (2019). Pyramid feature attention network for saliency detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00320"},{"key":"1523_CR45","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Deng, Z., Guo, S., Scott, M. R., & Huang, W. (2020). Representation sharing for fast object detector search and beyond. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-030-58529-7_28"},{"key":"1523_CR46","unstructured":"Zhou, H., Yang, M., Wang, J., & Pan, W. (2019). BayesNAS: A bayesian approach for neural architecture search. In International conference on machine learning."},{"key":"1523_CR47","unstructured":"Zhou, X., Wang, D., & Kr\u00e4henb\u00fchl, P. (2019). Objects as points. arXiv preprint arXiv:1904.07850."},{"key":"1523_CR48","doi-asserted-by":"crossref","unstructured":"Zhu, C., He, Y., & Savvides, M. (2019). Feature selective anchor-free module for single-shot object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00093"},{"key":"1523_CR49","doi-asserted-by":"crossref","unstructured":"Zhu, X., Hu, H., Lin, S., & Dai, J. (2019). Deformable convnets v2: More deformable, better results. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00953"},{"key":"1523_CR50","unstructured":"Zoph, B., & Le, Q. V. (2017). Neural architecture search with reinforcement learning. In Proceedings of international conference on learning representations."},{"key":"1523_CR51","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Jonathon, S., & Le, Q. V. (2018). Learning transferable architectures for scalable image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01523-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01523-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01523-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T07:20:22Z","timestamp":1635492022000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01523-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,15]]},"references-count":51,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["1523"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01523-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,15]]},"assertion":[{"value":"7 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}