{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T22:40:15Z","timestamp":1743115215682,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863616"},{"type":"electronic","value":"9783030863623"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/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":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86362-3_45","type":"book-chapter","created":{"date-parts":[[2021,9,11]],"date-time":"2021-09-11T11:02:35Z","timestamp":1631358155000},"page":"555-568","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Interpretable Visual Understanding with Cognitive Attention Network"],"prefix":"10.1007","author":[{"given":"Xuejiao","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kea","family":"Turner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tyler","family":"Derr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eirini","family":"Ntoutsi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,7]]},"reference":[{"key":"45_CR1","doi-asserted-by":"crossref","unstructured":"Vuola, A., Akram, S., Kannala, J.: Mask-RCNN and U-Net ensembled for nuclei segmentation. In: 16th International Symposium on Biomedical Imaging (ISBI), pp. 208\u2013212 (2019)","DOI":"10.1109\/ISBI.2019.8759574"},{"key":"45_CR2","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 CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"45_CR3","unstructured":"Barkau, R.L.: UNet: one-dimensional unsteady flow through a full network of open channels. user\u2019s manual. Technical reports, Hydrologic Engineering Center Davis CA (1996)"},{"key":"45_CR4","doi-asserted-by":"crossref","unstructured":"Papandreou, G., et al.: Towards accurate multi-person pose estimation in the wild. In: CVPR, pp. 4903\u20134911 (2017)","DOI":"10.1109\/CVPR.2017.395"},{"key":"45_CR5","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., et al.: From recognition to cognition: visual commonsense reasoning. In: CVPR, pp. 6720\u20136731 (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"45_CR6","unstructured":"Gregor, K., Danihelka, I., et al.: DRAW: a recurrent neural network for image generation. In: International Conference on Machine Learning, pp. 1462\u20131471 (2015)"},{"key":"45_CR7","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Yu, F., Tang, J., Yin, W., et al.: ERNIE-ViL: knowledge enhanced vision-language representations through scene graph. arXiv preprint arXiv:2006.16934 (2020)","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"45_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y.-C., et al.: UNITER: learning universal image-text representations (2019)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"45_CR10","unstructured":"Lin, J., Jain, U., et al.: TAB-VCR: tags and attributes based VCR baselines (2019)"},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"Natarajan, P., Wu, S., et al.: Multimodal feature fusion for robust event detection in web videos. In: CVPR, pp. 1298\u20131305 (2012)","DOI":"10.1109\/CVPR.2012.6247814"},{"key":"45_CR12","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., et al.: Auto-encoding scene graphs for image captioning. In: CVPR, pp. 10 685\u201310 694 (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. CoRR, vol. abs\/1705.07750 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"45_CR14","doi-asserted-by":"crossref","unstructured":"Tang, X., et al.: Cognitive visual commonsense reasoning using dynamic working memory. In: International Conference on Big Data Analytics and Knowledge Discovery. Springer (2021)","DOI":"10.1007\/978-3-030-86534-4_7"},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"You, Y., Zhang, Z., et al.: ImageNet training in minutes. In: Proceedings of the 47th International Conference on Parallel Processing, pp. 1\u201310 (2018)","DOI":"10.1145\/3225058.3225069"},{"key":"45_CR16","unstructured":"Devlin, J., Chang, M.-W., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"45_CR17","unstructured":"Huang, Z., Xu, W., et al.: Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991 (2015)"},{"key":"45_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"45_CR19","doi-asserted-by":"crossref","unstructured":"Ben-younes, H., Cad\u00e9ne, R., Cord, M., Thome, N.: MUTAN: multimodal tucker fusion for visual question answering. CoRR (2017)","DOI":"10.1109\/ICCV.2017.285"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Cord, M., Thome, N.: MUTAN: multimodal tucker fusion for visual question answering. In: ICCV, pp. 2612\u20132620 (2017)","DOI":"10.1109\/ICCV.2017.285"},{"key":"45_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, W., Ntoutsi, E.: FAHT: an adaptive fairness-aware decision tree classifier. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 1480\u20131486 (2019)","DOI":"10.24963\/ijcai.2019\/205"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86362-3_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T06:11:05Z","timestamp":1725775865000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86362-3_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863616","9783030863623"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86362-3_45","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":"7 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bratislava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovakia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"496","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":"265","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":"4","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":"53% - 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":"2.5","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":"Conference was held online due to the COVID-19 pandemic.","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)"}}]}}