{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:08:55Z","timestamp":1764266935625,"version":"3.46.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T00:00:00Z","timestamp":1704412800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T00:00:00Z","timestamp":1704412800000},"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":["Mach Learn"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s10994-023-06430-w","type":"journal-article","created":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T12:01:58Z","timestamp":1704456118000},"page":"3829-3848","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Task-decoupled interactive embedding network for object detection"],"prefix":"10.1007","volume":"113","author":[{"given":"Mai","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1200-5525","authenticated-orcid":false,"given":"Jichao","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Pang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,5]]},"reference":[{"key":"6430_CR1","unstructured":"Ba, J. L., Kiros, J. R., & Hinton, G. E. (2016) Layer normalization. arXiv:1607.06450"},{"key":"6430_CR2","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., et\u00a0al. (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition (pp. 248\u2013255). Ieee.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6430_CR3","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929"},{"key":"6430_CR5","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S. A., Van Gool, L., et al. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111, 98\u2013136.","journal-title":"International Journal of Computer Vision"},{"key":"6430_CR4","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., et al. (2010). The pascal visual object classes (voc) challenge. International Journal of Computer vision, 88, 303\u2013338.","journal-title":"International Journal of Computer vision"},{"key":"6430_CR6","doi-asserted-by":"crossref","unstructured":"Fan, Z., Ma, Y., Li, Z., et\u00a0al. (2021). Generalized few-shot object detection without forgetting. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4527\u20134536).","DOI":"10.1109\/CVPR46437.2021.00450"},{"key":"6430_CR7","doi-asserted-by":"crossref","unstructured":"Guirguis, K., Hendawy, A., Eskandar, G., et\u00a0al. (2022) Cfa: Constraint-based finetuning approach for generalized few-shot object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4039\u20134049).","DOI":"10.1109\/CVPRW56347.2022.00449"},{"key":"6430_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, A., Narayan, S., Joseph, K., et\u00a0al. (2022) Ow-detr: Open-world detection transformer. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9235\u20139244).","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"6430_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., et\u00a0al. (2021). Masked autoencoders are scalable vision learners. arXiv:2111.06377","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"6430_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r. P., et\u00a0al. (2017) Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"key":"6430_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, B., Luo, R., Mao, J., et\u00a0al. (2018). Acquisition of localization confidence for accurate object detection. In Proceedings of the European conference on computer vision (ECCV) (pp. 784\u2013799).","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"6430_CR12","doi-asserted-by":"crossref","unstructured":"Joseph, K., Khan, S., Khan, F.S., et\u00a0al. (2021). Towards open world object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5830\u20135840).","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"6430_CR13","doi-asserted-by":"crossref","unstructured":"Kang, B., Liu, Z., Wang, X., et\u00a0al. (2019). Few-shot object detection via feature reweighting. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 8420\u20138429).","DOI":"10.1109\/ICCV.2019.00851"},{"issue":"2","key":"6430_CR14","doi-asserted-by":"publisher","first-page":"5453","DOI":"10.1109\/LRA.2022.3146922","volume":"7","author":"D Kim","year":"2022","unstructured":"Kim, D., Lin, T. Y., Angelova, A., et al. (2022). Learning open-world object proposals without learning to classify. IEEE Robotics and Automation Letters, 7(2), 5453\u20135460.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"6430_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Mao, H., Girshick, R. B., et\u00a0al. (2022). Exploring plain vision transformer backbones for object detection. arXiv:abs\/2203.16527","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"6430_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., et\u00a0al. (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":"6430_CR16","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., et\u00a0al. (2014). Microsoft coco: Common objects in context. In Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6\u201312, 2014, proceedings, Part V 13 (pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"6430_CR18","unstructured":"Liu, Y., Sangineto, E., Bi, W., et\u00a0al. (2021a). Efficient training of visual transformers with small datasets. In Conference on neural information processing systems (NeurIPS)"},{"key":"6430_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et\u00a0al. (2021b). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"6430_CR20","unstructured":"Lu, Z., Xie, H., Liu, C., et\u00a0al. (2022) Bridging the gap between vision transformers and convolutional neural networks on small datasets. In Oh, A. H., Agarwal, A., Belgrave, D., et\u00a0al (Eds.), Advances in neural information processing systems. https:\/\/openreview.net\/forum?id=bfz-jhJ8wn"},{"key":"6430_CR21","doi-asserted-by":"crossref","unstructured":"Ma, J., Niu, Y., Xu, J., et\u00a0al. (2023). Digeo: Discriminative geometry-aware learning for generalized few-shot object detection. arXiv:2303.09674","DOI":"10.1109\/CVPR52729.2023.00313"},{"key":"6430_CR22","unstructured":"O\u00a0Pinheiro, P. O., Collobert, R., Doll\u00e1r, P. (2015). Learning to segment object candidates. Advances in Neural Information Processing Systems, 28."},{"issue":"1","key":"6430_CR23","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1109\/TPAMI.2016.2537320","volume":"39","author":"J Pont-Tuset","year":"2016","unstructured":"Pont-Tuset, J., Arbelaez, P., Barron, J. T., et al. (2016). Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(1), 128\u2013140.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"6430_CR24","unstructured":"Ren, S., He, K., Girshick, R., et\u00a0al. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28."},{"key":"6430_CR25","doi-asserted-by":"crossref","unstructured":"Saito, K., Hu, P., Darrell, T., et al. (2022). Learning to detect every thing in an open world. In X. X. I. V. Part (Ed.), Computer vision-ECCV 2022: 17th European conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings (pp. 268\u2013284). Springer.","DOI":"10.1007\/978-3-031-20053-3_16"},{"key":"6430_CR26","doi-asserted-by":"crossref","unstructured":"Shao, S., Li, Z., Zhang, T., et\u00a0al. (2019) Objects365: A large-scale, high-quality dataset for object detection. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 8430\u20138439).","DOI":"10.1109\/ICCV.2019.00852"},{"key":"6430_CR27","unstructured":"Tian, K., Jiang, Y., Diao, Q., et\u00a0al. (2023). Designing bert for convolutional networks: Sparse and hierarchical masked modeling. arXiv:2301.03580"},{"key":"6430_CR28","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., et\u00a0al. (2019) Fcos: Fully convolutional one-stage object detection. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9627\u20139636).","DOI":"10.1109\/ICCV.2019.00972"},{"key":"6430_CR29","unstructured":"Vu, T., Jang, H., Pham, T.X., et\u00a0al. (2019) Cascade rpn: Delving into high-quality region proposal network with adaptive convolution. Advances in Neural Information Processing Systems, 32."},{"key":"6430_CR30","doi-asserted-by":"crossref","unstructured":"Wang, W., Feiszli, M., Wang, H., et\u00a0al. (2022). Open-world instance segmentation: Exploiting pseudo ground truth from learned pairwise affinity. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4422\u20134432).","DOI":"10.1109\/CVPR52688.2022.00438"},{"key":"6430_CR31","unstructured":"Wang, X., Huang, T. E., Darrell, T., et\u00a0al. (2020). Frustratingly simple few-shot object detection. arXiv:2003.06957"},{"key":"6430_CR32","doi-asserted-by":"crossref","unstructured":"Wu, J., Liu, S., Huang, D., et\u00a0al. (2020). Multi-scale positive sample refinement for few-shot object detection. In Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVI 16 (pp. 456\u2013472). Springer.","DOI":"10.1007\/978-3-030-58517-4_27"},{"key":"6430_CR33","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Marlet, R. (2020). Few-shot object detection and viewpoint estimation for objects in the wild. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-58520-4_12"},{"key":"6430_CR34","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., Cao, Y., et\u00a0al. (2022) Simmim: A simple framework for masked image modeling. In International conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"6430_CR35","doi-asserted-by":"crossref","unstructured":"Yan, X., Chen, Z., Xu, A., et\u00a0al. (2019) Meta r-cnn: Towards general solver for instance-level low-shot learning. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9577\u20139586).","DOI":"10.1109\/ICCV.2019.00967"},{"key":"6430_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, G., Luo, Z., Cui, K., et\u00a0al. (2022) Meta-detr: Image-level few-shot detection with inter-class correlation exploitation. In IEEE transactions on pattern analysis and machine intelligence.","DOI":"10.1109\/TPAMI.2022.3195735"},{"key":"6430_CR37","doi-asserted-by":"crossref","unstructured":"Zitnick, C.L., Doll\u00e1r, P. (2014). Edge boxes: Locating object proposals from edges. In Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13 (pp. 391\u2013405). Springer.","DOI":"10.1007\/978-3-319-10602-1_26"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06430-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-023-06430-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06430-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:05:26Z","timestamp":1764266726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-023-06430-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,5]]},"references-count":37,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["6430"],"URL":"https:\/\/doi.org\/10.1007\/s10994-023-06430-w","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2024,1,5]]},"assertion":[{"value":"9 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 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":"We declare that we have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}