{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T13:42:55Z","timestamp":1762177375754,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695378"},{"type":"electronic","value":"9783030695385"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69538-5_1","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T21:16:40Z","timestamp":1614201400000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object Localization"],"prefix":"10.1007","author":[{"given":"Minsong","family":"Ki","sequence":"first","affiliation":[]},{"given":"Youngjung","family":"Uh","sequence":"additional","affiliation":[]},{"given":"Wonyoung","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Hyeran","family":"Byun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Chen, K., et al.: Towards accurate one-stage object detection with AP-loss. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5119\u20135127 (2019)","DOI":"10.1109\/CVPR.2019.00526"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 840\u2013849 (2019)","DOI":"10.1109\/CVPR.2019.00093"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Girshick, R., He, K., Doll\u00e1r, P.: TensorMask: a foundation for dense object segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2061\u20132069 (2019)","DOI":"10.1109\/ICCV.2019.00215"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Robinson, A., Lawin, F.J., Danelljan, M., Khan, F.S., Felsberg, M.: Learning fast and robust target models for video object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7406\u20137415 (2020)","DOI":"10.1109\/CVPR42600.2020.00743"},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/978-3-030-20870-7_16","volume-title":"Computer Vision \u2013 ACCV 2018","author":"Z Li","year":"2019","unstructured":"Li, Z., Zhou, F., Yang, L.: Fast single shot instance segmentation. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11364, pp. 257\u2013272. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20870-7_16"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wei, Y., Feng, J., Yang, Y., Huang, T.S.: Adversarial complementary learning for weakly supervised object localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1325\u20131334 (2018)","DOI":"10.1109\/CVPR.2018.00144"},{"key":"1_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1007\/978-3-030-01258-8_37","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Zhang","year":"2018","unstructured":"Zhang, X., Wei, Y., Kang, G., Yang, Y., Huang, T.: Self-produced guidance for weakly-supervised object localization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 610\u2013625. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_37"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Choe, J., Shim, H.: Attention-based dropout layer for weakly supervised object localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2219\u20132228 (2019)","DOI":"10.1109\/CVPR.2019.00232"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Yang, S., Kim, Y., Kim, Y., Kim, C.: Combinational class activation maps for weakly supervised object localization. In: The IEEE Winter Conference on Applications of Computer Vision, pp. 2941\u20132949 (2020)","DOI":"10.1109\/WACV45572.2020.9093566"},{"key":"1_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1007\/978-3-030-20870-7_39","volume-title":"Computer Vision \u2013 ACCV 2018","author":"J Son","year":"2019","unstructured":"Son, J., Kim, D., Lee, S., Kwak, S., Cho, M., Han, B.: Forget and diversify: regularized refinement for weakly supervised object detection. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11364, pp. 632\u2013648. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20870-7_39"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Lee, P., Uh, Y., Byun, H.: Background suppression network for weakly-supervised temporal action localization. In: AAAI, pp. 11320\u201311327 (2020)","DOI":"10.1609\/aaai.v34i07.6793"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Kumar Singh, K., Jae Lee, Y.: Hide-and-seek: forcing a network to be meticulous for weakly-supervised object and action localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3524\u20133533 (2017)","DOI":"10.1109\/ICCV.2017.381"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Wei, Y., Feng, J., Liang, X., Cheng, M.M., Zhao, Y., Yan, S.: Object region mining with adversarial erasing: a simple classification to semantic segmentation approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1568\u20131576 (2017)","DOI":"10.1109\/CVPR.2017.687"},{"key":"1_CR15","unstructured":"Hou, Q., Jiang, P., Wei, Y., Cheng, M.M.: Self-erasing network for integral object attention. In: Advances in Neural Information Processing Systems, pp. 549\u2013559 (2018)"},{"key":"1_CR16","unstructured":"Welinder, P., et al.: Caltech-UCSD Birds 200. Technical report CNS-TR-2010-001, California Institute of Technology (2010)"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Choe, J., Oh, S.J., Lee, S., Chun, S., Akata, Z., Shim, H.: Evaluating weakly supervised object localization methods right. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3133\u20133142 (2020)","DOI":"10.1109\/CVPR42600.2020.00320"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Mai, J., Yang, M., Luo, W.: Erasing integrated learning: a simple yet effective approach for weakly supervised object localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8766\u20138775 (2020)","DOI":"10.1109\/CVPR42600.2020.00879"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), vol. 2, pp. 1735\u20131742. IEEE (2006)","DOI":"10.1109\/CVPR.2006.100"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"1_CR21","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709 (2020)"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Chen, W., Chen, X., Zhang, J., Huang, K.: Beyond triplet loss: a deep quadruplet network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 403\u2013412 (2017)","DOI":"10.1109\/CVPR.2017.145"},{"key":"1_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Baek, K., Lee, M., Shim, H.: PsyNet: self-supervised approach to object localization using point symmetric transformation. In: AAAI, pp. 10451\u201310459 (2020)","DOI":"10.1609\/aaai.v34i07.6615"},{"key":"1_CR26","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"key":"1_CR27","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do ImageNet classifiers generalize to imagenet? arXiv preprint arXiv:1902.10811 (2019)"},{"key":"1_CR28","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 International Conference on Computer Vision, pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"1_CR29","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1_CR31","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"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69538-5_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T20:19:33Z","timestamp":1724530773000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69538-5_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695378","9783030695385"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69538-5_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"33% - 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","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","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)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}