{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T05:13:58Z","timestamp":1747458838256,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031200588"},{"type":"electronic","value":"9783031200595"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20059-5_35","type":"book-chapter","created":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:02:50Z","timestamp":1666972970000},"page":"610-626","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["SemAug: Semantically Meaningful Image Augmentations for\u00a0Object Detection Through Language Grounding"],"prefix":"10.1007","author":[{"given":"Morgan","family":"Heisler","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amin","family":"Banitalebi-Dehkordi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"35_CR1","unstructured":"Allen, J.: Natural language understanding. Benjamin-Cummings Publishing Co., Inc. (1988)"},{"key":"35_CR2","unstructured":"Authors: SemAug: Semantically Meaningful Image Augmentations for Object Detection Through Language Grounding (2022). supplied as additional material 5739-supp.pdf"},{"key":"35_CR3","unstructured":"Chen, K., et al.: MMDetection: open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"issue":"4","key":"35_CR4","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR5","unstructured":"Chen, Y., Ouyang, X., Zhu, K., Agam, G.: Mask-based data augmentation for semi-supervised semantic segmentation. arXiv preprint arXiv:2101.10156 (2021)"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: Learning augmentation strategies from data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 113\u2013123 (2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"35_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019)"},{"key":"35_CR9","unstructured":"DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Dvornik, N., Mairal, J., Schmid, C.: Modeling visual context is key to augmenting object detection datasets. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 364\u2013380 (2018)","DOI":"10.1007\/978-3-030-01258-8_23"},{"issue":"6","key":"35_CR11","doi-asserted-by":"publisher","first-page":"2014","DOI":"10.1109\/TPAMI.2019.2961896","volume":"43","author":"N Dvornik","year":"2019","unstructured":"Dvornik, N., Mairal, J., Schmid, C.: On the importance of visual context for data augmentation in scene understanding. IEEE Trans. Pattern Anal. Mach. Intell. 43(6), 2014\u20132028 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Misra, I., Hebert, M.: Cut, paste and learn: surprisingly easy synthesis for instance detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1301\u20131310 (2017)","DOI":"10.1109\/ICCV.2017.146"},{"issue":"2","key":"35_CR13","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. 88(2), 303\u2013338 (2010). https:\/\/doi.org\/10.1007\/s11263-009-0275-4","journal-title":"Int. J. Comput. Vis."},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Sun, J., Wang, R., Gou, M., Li, Y.L., Lu, C.: Instaboost: Boosting instance segmentation via probability map guided copy-pasting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 682\u2013691 (2019)","DOI":"10.1109\/ICCV.2019.00077"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. arXiv preprint arXiv:2012.07177 (2020)","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"35_CR16","doi-asserted-by":"publisher","unstructured":"Gokhale, T., Banerjee, P., Baral, C., Yang, Y.: MUTANT: a training paradigm for out-of-distribution generalization in visual question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 878\u2013892. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.63, http:\/\/aclanthology.org\/2020.emnlp-main.63","DOI":"10.18653\/v1\/2020.emnlp-main.63"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Gong, C., Wang, D., Li, M., Chandra, V., Liu, Q.: Keepaugment: a simple information-preserving data augmentation approach. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1055\u20131064 (2021)","DOI":"10.1109\/CVPR46437.2021.00111"},{"key":"35_CR18","unstructured":"Harris, E., Marcu, A., Painter, M., Niranjan, M., Hare, A.P.B.J.: Fmix: enhancing mixed sample data augmentation. arXiv preprint arXiv:2002.12047, vol. 2, no 3, p. 4 (2020)"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8340\u20138349 (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"35_CR22","unstructured":"Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., Lakshminarayanan, B.: Augmix: a simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781 (2019)"},{"issue":"6245","key":"35_CR23","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1126\/science.aaa8685","volume":"349","author":"J Hirschberg","year":"2015","unstructured":"Hirschberg, J., Manning, C.D.: Advances in natural language processing. Science 349(6245), 261\u2013266 (2015)","journal-title":"Science"},{"key":"35_CR24","unstructured":"Li, P., Li, X., Long, X.: Fencemask: a data augmentation approach for pre-extracted image features. arXiv preprint arXiv:2006.07877 (2020)"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"35_CR26","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: European Conference on Computer Vision (ECCV), pp. 740\u2013755. Springer (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"35_CR27","unstructured":"Mikolov, T., Grave, E., Bojanowski, P., Puhrsch, C., Joulin, A.: Advances in pre-training distributed word representations. In: Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018) (2018)"},{"key":"35_CR28","doi-asserted-by":"crossref","unstructured":"Olsson, V., Tranheden, W., Pinto, J., Svensson, L.: Classmix: segmentation-based data augmentation for semi-supervised learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1369\u20131378 (2021)","DOI":"10.1109\/WACV48630.2021.00141"},{"key":"35_CR29","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014). http:\/\/www.aclweb.org\/anthology\/D14-1162","DOI":"10.3115\/v1\/D14-1162"},{"key":"35_CR30","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"35_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0\/","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1\u201348 (2019). https:\/\/doi.org\/10.1186\/s40537-019-0197-0\/","journal-title":"J. Big Data"},{"key":"35_CR32","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"35_CR33","doi-asserted-by":"publisher","unstructured":"Volokitin, A., Susmelj, I., Agustsson, E., Van Gool, L., Timofte, R.: Efficiently detecting plausible locations for object placement using masked convolutions. In: European Conference on Computer Vision (ECCV), pp. 252\u2013266. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-66823-5_15","DOI":"10.1007\/978-3-030-66823-5_15"},{"key":"35_CR34","unstructured":"Wang, H., Wang, Q., Yang, F., Zhang, W., Zuo, W.: Data augmentation for object detection via progressive and selective instance-switching. arXiv preprint arXiv:1906.00358 (2019)"},{"key":"35_CR35","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, Q., Zhang, H., Yang, J., Zuo, W.: Constrained online cut-paste for object detection. In: IEEE Transactions on Circuits and Systems for Video Technology (2020)","DOI":"10.1109\/TCSVT.2020.3045978"},{"key":"35_CR36","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"35_CR37","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20059-5_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:12:21Z","timestamp":1666973541000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20059-5_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200588","9783031200595"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20059-5_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"29 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}