{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T03:24:23Z","timestamp":1783653863030,"version":"3.55.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030586201","type":"print"},{"value":"9783030586218","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58621-8_38","type":"book-chapter","created":{"date-parts":[[2020,11,26]],"date-time":"2020-11-26T19:03:23Z","timestamp":1606417403000},"page":"652-669","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Why Do These Match? Explaining the Behavior of Image Similarity Models"],"prefix":"10.1007","author":[{"given":"Bryan A.","family":"Plummer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mariya I.","family":"Vasileva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vitali","family":"Petsiuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kate","family":"Saenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Forsyth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,27]]},"reference":[{"key":"38_CR1","doi-asserted-by":"crossref","unstructured":"Ak, K.E., Kassim, A.A., Lim, J.H., Tham, J.Y.: Learning attribute representations with localization for flexible fashion search. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00804"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Bansal, A., Sikka, K., Sharma, G., Chellappa, R., Divakaran, A.: Zero-shot object detection. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"38_CR3","doi-asserted-by":"crossref","unstructured":"Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: Quantifying interpretability of deep visual representations. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.354"},{"key":"38_CR4","doi-asserted-by":"crossref","unstructured":"Cao, C., et al.: Look and think twice: Capturing top-down visual attention with feedback convolutional neural networks. In: The IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.338"},{"key":"38_CR5","unstructured":"Chang, C.H., Creager, E., Goldenberg, A., Duvenaud, D.: Explaining image classifiers by counterfactual generation. In: The International Conference on Learning Representations (2019)"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Fong, R., Vedaldi, A.: Net2vec: Quantifying and explaining how concepts are encoded by filters in deep neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00910"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Fong, R.C., Vedaldi, A.: Interpretable explanations of black boxes by meaningful perturbation. In: The IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.371"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Gordo, A., Larlus, D.: Beyond instance-level image retrieval: Leveraging captions to learn a global visual representation for semantic retrieval. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.560"},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Han, X., Song, X., Yin, J., Wang, Y., Nie, L.: Prototype-guided attribute-wise interpretable scheme for clothing matching. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (2019)","DOI":"10.1145\/3331184.3331245"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Han, X., et al.: Automatic spatially-aware fashion concept discovery. In: The IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.163"},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"Han, X., Wu, Z., Jiang, Y.G., Davis, L.S.: Learning fashion compatibility with bidirectional LSTMs. In: ACM International Conference on Multimedia (2017)","DOI":"10.1145\/3123266.3123394"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Akata, Z., Rohrbach, M., Donahue, J., Schiele, B., Darrell, T.: Generating visual explanations. In: The European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46493-0_1"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Hu, R., Darrell, T., Akata, Z.: Grounding visual explanations. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01216-8_17"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Hsiao, W.L., Grauman, K.: Creating capsule wardrobes from fashion images. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00748"},{"issue":"1","key":"38_CR16","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1214\/aoms\/1177703732","volume":"53","author":"PJ Huber","year":"1964","unstructured":"Huber, P.J.: Robust estimation of a location parameter. Ann. Stat. 53(1), 73\u2013101 (1964)","journal-title":"Ann. Stat."},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Huk Park, D., et al.: Multimodal explanations: Justifying decisions and pointing to the evidence. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00915"},{"key":"38_CR18","doi-asserted-by":"crossref","unstructured":"Kiapour, M.H., Han, X., Lazebnik, S., Berg, A.C., Berg, T.L.: Where to buy it: matching street clothing photos to online shops. In: The IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.382"},{"key":"38_CR19","unstructured":"Kim, B., et al.: Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (TCAV). In: The International Conference on Machine Learning (ICML) (2018)"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"Kim, J., Rohrbach, A., Darrell, T., Canny, J., Akata, Z.: Textual explanations for self-driving vehicles. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Lad, S., Parikh, D.: Interactively guiding semi-supervised clustering via attribute-based explanations. In: The European Conference on Computer Vision (ECCV) (2014)","DOI":"10.1007\/978-3-319-10599-4_22"},{"key":"38_CR22","doi-asserted-by":"crossref","unstructured":"Li, Q., Tao, Q., Joty, S., Cai, J., Luo, J.: VQA-E explaining, elaborating, and enhancing your answers for visual questions. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01234-2_34"},{"key":"38_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, J., Zhang, J., Huang, K.: Discriminative learning of latent features for zero-shot recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00779"},{"key":"38_CR24","doi-asserted-by":"crossref","unstructured":"Liao, L., He, X., Zhao, B., Ngo, C.W., Chua, T.S.: Interpretable multimodal retrieval for fashion products. In: Proceedings of the 26th ACM International Conference on Multimedia (2018)","DOI":"10.1145\/3240508.3240646"},{"key":"38_CR25","unstructured":"Nguyen, A., Dosovitskiy, A., Yosinski, J., Brox, T., Clune, J.: Synthesizing the preferred inputs for neurons in neural networks via deep generator networks. In: Advances in Neural Information Processing Systems (NIPS) (2016)"},{"key":"38_CR26","unstructured":"Petsiuk, V., Das, A., Saenko, K.: Rise: Randomized input sampling for explanation of black-box models. In: British Machine Vision Conference (BMVC) (2018)"},{"key":"38_CR27","doi-asserted-by":"crossref","unstructured":"Radenovi\u0107, F., Iscen, A., Tolias, G., Avrithis, Y., Chum, O.: Revisiting oxford and Paris: large-scale image retrieval benchmarking. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00598"},{"key":"38_CR28","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: \u201cwhy should i trust you?\u201d: explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"38_CR29","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: The IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"38_CR30","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. In: ICLR Workshop (2014)"},{"key":"38_CR31","doi-asserted-by":"crossref","unstructured":"Tan, R., Vasileva, M.I., Saenko, K., Plummer, B.A.: Learning similarity conditions without explicit supervision. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.01047"},{"issue":"6","key":"38_CR32","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1016\/0010-4809(81)90012-4","volume":"14","author":"RL Teach","year":"1981","unstructured":"Teach, R.L., Shortliffe, E.H.: An analysis of physician attitudes regarding computer-based clinical consultation systems. Comput. Biomed. Res. 14(6), 542\u2013558 (1981)","journal-title":"Comput. Biomed. Res."},{"key":"38_CR33","doi-asserted-by":"crossref","unstructured":"Vasileva, M.I., Plummer, B.A., Dusad, K., Rajpal, S., Kumar, R., Forsyth, D.: Learning type-aware embeddings for fashion compatibility. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01270-0_24"},{"key":"38_CR34","doi-asserted-by":"crossref","unstructured":"Vittayakorn, S., Umeda, T., Murasaki, K., Sudo, K., Okatani, T., Yamaguchi, K.: Automatic attribute discovery with neural activations. In: The European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46493-0_16"},{"key":"38_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Ye, Y., Gupta, A.: Zero-shot recognition via semantic embeddings and knowledge graphs. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00717"},{"issue":"9","key":"38_CR36","doi-asserted-by":"publisher","first-page":"2251","DOI":"10.1109\/TPAMI.2018.2857768","volume":"41","author":"Y Xian","year":"2019","unstructured":"Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning\u2014a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2251\u20132265 (2019). https:\/\/doi.org\/10.1109\/TPAMI.2018.2857768","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"38_CR37","doi-asserted-by":"crossref","unstructured":"Yang, X., et al.: Interpretable fashion matching with rich attributes. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (2019)","DOI":"10.1145\/3331184.3331242"},{"key":"38_CR38","doi-asserted-by":"crossref","unstructured":"Yelamarthi, S.K., Reddy, S.K., Mishra, A., Mittal, A.: A zero-shot framework for sketch based image retrieval. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01225-0_19"},{"key":"38_CR39","unstructured":"Yosinski, J., Clune, J., Nguyen, A., Fuchs, T., Lipson, H.: Understanding neural networks through deep visualization. In: Deep Learning Workshop, International Conference on Machine Learning (ICML) (2015)"},{"key":"38_CR40","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: The European Conference on Computer Vision (ECCV) (2014)","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"38_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lin, Z., Brandt, J., Shen, X., Sclaroff, S.: Top-down neural attention by excitation backprop. In: The European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46493-0_33"},{"key":"38_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, B., Feng, J., Wu, X., Yan, S.: Memory-augmented attribute manipulation networks for interactive fashion search. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.652"},{"key":"38_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., A., L., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58621-8_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:12:14Z","timestamp":1732579934000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58621-8_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030586201","9783030586218"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58621-8_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"27 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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 due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}