{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:15:35Z","timestamp":1742912135422,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031243486"},{"type":"electronic","value":"9783031243493"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-24349-3_7","type":"book-chapter","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T10:09:17Z","timestamp":1680516557000},"page":"106-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vision and\u00a0Multi-modal Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7249-8715","authenticated-orcid":false,"given":"Camille","family":"Guinaudeau","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,4]]},"reference":[{"key":"7_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of the International Conference on Learning Representations (2015)"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., Shlens, J., Le, Q.V.: Attention augmented convolutional networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3286\u20133295 (2019)","DOI":"10.1109\/ICCV.2019.00338"},{"key":"7_CR3","first-page":"352","volume":"31","author":"Y Chen","year":"2018","unstructured":"Chen, Y., Kalantidis, Y., Li, J., Yan, S., Feng, J.: A$$\\hat{}$$ 2-nets: double attention networks. Adv. Neural. Inf. Process. Syst. 31, 352\u2013361 (2018)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR4","unstructured":"Chu, X., et al.: Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882 (2021)"},{"key":"7_CR5","unstructured":"Chu, X., Zhang, B., Tian, Z., Wei, X., Xia, H.: Do we really need explicit position encodings for vision transformers? arXiv e-prints, pages arXiv-2102 (2021)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Yvon, F.: Transformers in natural language processing. Advanced Course on Human-Centered AI (2022)","DOI":"10.1007\/978-3-031-24349-3_6"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Crowley, J.: Convolutional neural networks. Advanced Course on Human-Centered AI (2022)","DOI":"10.1007\/978-3-031-24349-3_5"},{"key":"7_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Evrard, M.: Transformers in automatic speech recognition. Advanced Course on Human-Centered AI (2022)","DOI":"10.1007\/978-3-031-24349-3_8"},{"key":"7_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-030-58548-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"V Gabeur","year":"2020","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 214\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_13"},{"key":"7_CR11","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"},{"issue":"1","key":"7_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-01821-3","volume":"8","author":"S Khan","year":"2018","unstructured":"Khan, S., Rahmani, H., Shah, S.A.A., Bennamoun, M.: A guide to convolutional neural networks for computer vision. Synthesis Lect. Comput. Vis. 8(1), 1\u2013207 (2018)","journal-title":"Synthesis Lect. Comput. Vis."},{"key":"7_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/978-3-030-58558-7_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Kolesnikov","year":"2020","unstructured":"Kolesnikov, A., et al.: Big transfer (BiT): general visual representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 491\u2013507. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_29"},{"key":"7_CR14","first-page":"84","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 84\u201390 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"4","key":"7_CR15","first-page":"385","volume":"8","author":"DP Tian","year":"2013","unstructured":"Tian, D.P.: A review on image feature extraction and representation techniques. Int. J. Multimed. Ubiquit. Eng. 8(4), 385\u2013396 (2013)","journal-title":"Int. J. Multimed. Ubiquit. Eng."},{"key":"7_CR16","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. Image 2, T2 (2021)"},{"key":"7_CR17","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? In: Advances in Neural Information Processing Systems (2021)"},{"key":"7_CR18","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"7_CR19","unstructured":"Ren, Y., et al.: FastSpeech: fast, robust and controllable text to speech. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Sterpu, G., Saam, C., Harte, N.: Should we hard-code the recurrence concept or learn it instead? Exploring the transformer architecture for audio-visual speech recognition. In: Interspeech (2020)","DOI":"10.21437\/Interspeech.2020-2480"},{"key":"7_CR21","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"7_CR22","first-page":"8252","volume":"32","author":"H Touvron","year":"2019","unstructured":"Touvron, H., Vedaldi, A., Douze, M., Jegou, H.: Fixing the train-test resolution discrepancy. Adv. Neural. Inf. Process. Syst. 32, 8252\u20138262 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"7_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-030-58548-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Wang","year":"2020","unstructured":"Wang, H., Zhu, Y., Green, B., Adam, H., Yuille, A., Chen, L.-C.: Axial-deeplab: stand-alone axial-attention for panoptic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 108\u2013126. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_7"},{"key":"7_CR25","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":"7_CR26","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: CvT: introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.-T., Hovy, E., Le, Q.V.: Self-training with noisy student improves ImageNet classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10687\u201310698 (2020)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"7_CR28","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"}],"container-title":["Lecture Notes in Computer Science","Human-Centered Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-24349-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,10]],"date-time":"2023-12-10T04:03:01Z","timestamp":1702180981000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-24349-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031243486","9783031243493"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-24349-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"4 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ECCAI Advanced Course on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Berlin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"11 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acai-agents2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.humane-ai.eu\/event\/acai2021\/","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":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"21","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":"21","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":"100% - 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":"2","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":"1","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}