{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:33:44Z","timestamp":1757313224534,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030660956"},{"type":"electronic","value":"9783030660963"}],"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\/978-3-030-66096-3_3","type":"book-chapter","created":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T07:03:14Z","timestamp":1609570994000},"page":"33-38","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["C4AV: Learning Cross-Modal Representations from Transformers"],"prefix":"10.1007","author":[{"given":"Shujie","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,3]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Alberti, C., Ling, J., Collins, M., Reitter, D.: Fusion of detected objects in text for visual question answering. arXiv preprint arXiv:1908.05054 (2019)","DOI":"10.18653\/v1\/D19-1219"},{"key":"3_CR2","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: A multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. arXiv preprint arXiv:2005.12872 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Dai, H., Luo, S., Ding, Y., Shao, L.: Commands for autonomous vehicles by progressively stacking visual-linguistic representations. In: ECCV workshop (2020)","DOI":"10.1007\/978-3-030-66096-3_2"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Deruyttere, T., Collell, G., Moens, M.F.: Giving commands to a self-driving car: A multimodal reasoner for visual grounding. arXiv preprint arXiv:2003.08717 (2020)","DOI":"10.1016\/j.engappai.2021.104257"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Deruyttere, T., Vandenhende, S., Grujicic, D., Van Gool, L., Moens, M.F.: Talk2car: Taking control of your self-driving car. arXiv preprint arXiv:1909.10838 (2019)","DOI":"10.18653\/v1\/D19-1215"},{"key":"3_CR9","unstructured":"Fan, A., Grave, E., Joulin, A.: Reducing transformer depth on demand with structured dropout. arXiv preprint arXiv:1909.11556 (2019)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Guo, M., Zhang, Y., Liu, T.: Gaussian transformer: a lightweight approach for natural language inference. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 6489\u20136496 (2019)","DOI":"10.1609\/aaai.v33i01.33016489"},{"key":"3_CR11","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":"3_CR12","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":"3_CR13","unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. arXiv preprint arXiv:1803.03067 (2018)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D., Zhou, M.: Unicoder-vl: a universal encoder for vision and language by cross-modal pre-training. In: AAAI, pp. 11336\u201311344 (2020)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"3_CR15","unstructured":"Li, J., et al.: 3D iou-net: Iou guided 3D object detector for point clouds. arXiv preprint arXiv:2004.04962 (2020)"},{"key":"3_CR16","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: Visualbert: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"3_CR17","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, pp. 13\u201323 (2019)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: multi-task vision and language representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10437\u201310446 (2020)","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"3_CR19","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8026\u20138037 (2019)"},{"issue":"1","key":"3_CR20","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/S0893-6080(98)00116-6","volume":"12","author":"N Qian","year":"1999","unstructured":"Qian, N.: On the momentum term in gradient descent learning algorithms. Neural Netw. 12(1), 145\u2013151 (1999)","journal-title":"Neural Netw."},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Raganato, A., et al.: An analysis of encoder representations in transformer-based machine translation. In: Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. The Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/W18-5431"},{"key":"3_CR22","unstructured":"Su, W., et al.: Vl-bert: Pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"3_CR23","unstructured":"Sur, C.: Self-segregating and coordinated-segregating transformer for focused deep multi-modular network for visual question answering. arXiv preprint arXiv:2006.14264 (2020)"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: Lxmert: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the conference. Association for Computational Linguistics. Meeting, vol. 2019, p. 6558. NIH Public Access (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"3_CR26","unstructured":"Vandenhende, S., Deruyttere, T., Grujicic, D.: A baseline for the commands for autonomous vehicles challenge. arXiv preprint arXiv:2004.13822 (2020)"},{"key":"3_CR27","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Xia, Y., He, T., Tan, X., Tian, F., He, D., Qin, T.: Tied transformers: neural machine translation with shared encoder and decoder. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 5466\u20135473 (2019)","DOI":"10.1609\/aaai.v33i01.33015466"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J.J., Gao, J.: Unified vision-language pre-training for image captioning and VQA. In: AAAI, pp. 13041\u201313049 (2020)","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"3_CR30","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-66096-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T00:05:52Z","timestamp":1735776352000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-66096-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030660956","9783030660963"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66096-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"3 January 2021","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)"}}]}}