{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T22:13:02Z","timestamp":1778278382895,"version":"3.51.4"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T00:00:00Z","timestamp":1706572800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T00:00:00Z","timestamp":1706572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s11263-024-01985-0","type":"journal-article","created":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T09:02:47Z","timestamp":1706605367000},"page":"2443-2449","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-dataset Detection with Transformers"],"prefix":"10.1007","volume":"132","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0637-3943","authenticated-orcid":false,"given":"Bo","family":"Ke","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruizhi","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,30]]},"reference":[{"key":"1985_CR1","doi-asserted-by":"crossref","unstructured":"Cai, L., Zhang, Z., Zhu, Y., Zhang, L., Li, M., & Xue, X. (2022). Bigdetection: A large-scale benchmark for improved object detector pre-training. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4777\u20134787.","DOI":"10.1109\/CVPRW56347.2022.00524"},{"key":"1985_CR2","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In European conference on computer vision, pp. 213\u2013229. Springer.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1985_CR3","doi-asserted-by":"crossref","unstructured":"Jia, D., Yuan, Y., He, H., Wu, X., Yu, H., Lin, W., Sun, L., Zhang, C., & Hu, H. (2022). Detrs with hybrid matching. arXiv:2207.13080.","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"1985_CR4","first-page":"1","volume":"01","author":"G Kapidis","year":"2021","unstructured":"Kapidis, G., Poppe, R., & Veltkamp, R. C. (2021). Multi-dataset, multitask learning of egocentric vision tasks. IEEE Transactions on Pattern Analysis & Machine Intelligence, 01, 1\u20131.","journal-title":"IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"key":"1985_CR5","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.-H.P., Hilliges, O., & Black, M.J. (2021) Pare: Part attention regressor for 3d human body estimation. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 11127\u201311137.","DOI":"10.1109\/ICCV48922.2021.01094"},{"issue":"7","key":"1985_CR6","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., et al. (2020). The open images dataset v4. International Journal of Computer Vision, 128(7), 1956\u20131981.","journal-title":"International Journal of Computer Vision"},{"key":"1985_CR7","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., & Zhang, L. (2022) Dn-detr: Accelerate detr training by introducing query denoising. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13619\u201313627.","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"1985_CR8","doi-asserted-by":"publisher","first-page":"6893","DOI":"10.1109\/TIP.2022.3216771","volume":"31","author":"T Liang","year":"2022","unstructured":"Liang, T., Chu, X., Liu, Y., Wang, Y., Tang, Z., Chu, W., Chen, J., & Ling, H. (2022). Cbnet: A composite backbone network architecture for object detection. IEEE Transactions on Image Processing, 31, 6893\u20136906.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1985_CR9","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":"1985_CR10","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":"1985_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.L. (2014). Microsoft COCO: Common objects in context. In European conference on computer vision, pp. 740\u2013755. Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1985_CR12","doi-asserted-by":"publisher","first-page":"1596","DOI":"10.1109\/TIP.2020.3046864","volume":"30","author":"S Lin","year":"2020","unstructured":"Lin, S., Li, C.-T., & Kot, A. C. (2020). Multi-domain adversarial feature generalization for person re-identification. IEEE Transactions on Image Processing, 30, 1596\u20131607.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1985_CR13","unstructured":"Liu, S., Li, F., Zhang, H., Yang, X., Qi, X., Su, H., Zhu, J., & Zhang, L. (2021) Dab-detr: Dynamic anchor boxes are better queries for detr. In International conference on learning representations."},{"key":"1985_CR14","doi-asserted-by":"crossref","unstructured":"Neuhold, G., Ollmann, T., Rota\u00a0Bulo, S., & Kontschieder, P. (2017) The mapillary vistas dataset for semantic understanding of street scenes. In Proceedings of the IEEE international conference on computer vision, pp. 4990\u20134999.","DOI":"10.1109\/ICCV.2017.534"},{"key":"1985_CR15","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28"},{"key":"1985_CR16","unstructured":"Robust Vision Challenge (2022). www.robustvision.net\/leaderboard.php?benchmark=object. Accessed 23 Aug 2023"},{"key":"1985_CR17","doi-asserted-by":"crossref","unstructured":"Sun, Z., Cao, S., Yang, Y., & Kitani, K.M. (2021) Rethinking transformer-based set prediction for object detection. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 3611\u20133620.","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"1985_CR18","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Hu, H., Wang, J., Wang, L., Wei, F., Bai, X., & Liu, Z. (2021). End-to-end semi-supervised object detection with soft teacher. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3060\u20133069.","DOI":"10.1109\/ICCV48922.2021.00305"},{"issue":"10","key":"1985_CR19","doi-asserted-by":"publisher","first-page":"2759","DOI":"10.1109\/TMI.2020.3047598","volume":"40","author":"K Yan","year":"2020","unstructured":"Yan, K., Cai, J., Zheng, Y., Harrison, A. P., Jin, D., Tang, Y., Tang, Y., Huang, L., Xiao, J., & Lu, L. (2020). Learning from multiple datasets with heterogeneous and partial labels for universal lesion detection in CT. IEEE Transactions on Medical Imaging, 40(10), 2759\u20132770.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"1985_CR20","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., & Shum, H.-Y. (2022). Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv:2203.03605."},{"key":"1985_CR21","doi-asserted-by":"crossref","unstructured":"Zhao, X., Schulter, S., Sharma, G., Tsai, Y.-H., Chandraker, M., & Wu, Y. (2020). Object detection with a unified label space from multiple datasets. In European conference on computer vision, pp. 178\u2013193. Springer.","DOI":"10.1007\/978-3-030-58568-6_11"},{"key":"1985_CR22","doi-asserted-by":"crossref","unstructured":"Zhou, X., Koltun, V., & Kr\u00e4henb\u00fchl, P. (2022). Simple multi-dataset detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 7571\u20137580.","DOI":"10.1109\/CVPR52688.2022.00742"},{"key":"1985_CR23","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable detr: Deformable transformers for end-to-end object detection. In International conference on learning representations."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-01985-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-01985-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-01985-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T13:14:01Z","timestamp":1718802841000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-01985-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,30]]},"references-count":23,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["1985"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-01985-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,30]]},"assertion":[{"value":"16 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}