{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:45:21Z","timestamp":1757310321989,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"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_2","type":"book-chapter","created":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T07:03:14Z","timestamp":1609570994000},"page":"27-32","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Commands for Autonomous Vehicles by Progressively Stacking Visual-Linguistic Representations"],"prefix":"10.1007","author":[{"given":"Hang","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujie","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,3]]},"reference":[{"key":"2_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":"2_CR2","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":"2_CR3","doi-asserted-by":"crossref","unstructured":"Clark, K., Khandelwal, U., Levy, O., Manning, C.D.: What does bert look at? an analysis of bert\u2019s attention. arXiv preprint arXiv:1906.04341 (2019)","DOI":"10.18653\/v1\/W19-4828"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Deng, C., Wu, Q., Wu, Q., Hu, F., Lyu, F., Tan, M.: Visual grounding via accumulated attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7746\u20137755 (2018)","DOI":"10.1109\/CVPR.2018.00808"},{"key":"2_CR5","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":"2_CR6","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":"2_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv preprint arXiv:1606.01847 (2016)","DOI":"10.18653\/v1\/D16-1044"},{"key":"2_CR9","unstructured":"Gong, L., He, D., Li, Z., Qin, T., Wang, L., Liu, T.: Efficient training of bert by progressively stacking. In: International Conference on Machine Learning, pp. 2337\u20132346 (2019)"},{"key":"2_CR10","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":"2_CR11","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"2_CR12","unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. arXiv preprint arXiv:1803.03067 (2018)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al: A diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Inferring and executing programs for visual reasoning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2989\u20132998 (2017)","DOI":"10.1109\/ICCV.2017.325"},{"issue":"4","key":"2_CR16","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee, J., et al.: Biobert: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4), 1234\u20131240 (2020)","journal-title":"Bioinformatics"},{"key":"2_CR17","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":"2_CR18","unstructured":"Li, J., Luo, S., Zhu, Z., Dai, H., Krylov, A.S., Ding, Y., Shao, L.: 3D IOU-net: IOU guided 3D object detector for point clouds. arXiv preprint arXiv:2004.04962 (2020)"},{"key":"2_CR19","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":"2_CR20","doi-asserted-by":"crossref","unstructured":"Liu, D., Zhang, H., Wu, F., Zha, Z.J.: Learning to assemble neural module tree networks for visual grounding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4673\u20134682 (2019)","DOI":"10.1109\/ICCV.2019.00477"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., Lapata, M.: Text summarization with pretrained encoders. arXiv preprint arXiv:1908.08345 (2019)","DOI":"10.18653\/v1\/D19-1387"},{"key":"2_CR22","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":"2_CR23","doi-asserted-by":"crossref","unstructured":"Luo, S., Dai, H., Shao, L., Ding, Y.: C4av: cross-modal representations from transformer. In: ECCV workshop (2020)","DOI":"10.1007\/978-3-030-66096-3_3"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J.R., Bethard, S., McClosky, D.: The stanford corenlp natural language processing toolkit. In: Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 55\u201360 (2014)","DOI":"10.3115\/v1\/P14-5010"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: Film: visual reasoning with a general conditioning layer. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"2_CR26","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"2_CR27","unstructured":"Su, W., et al.: Vl-bert: pre-training of generic visual-linguistic representations. In: International Conference on Learning Representations (2020)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Sun, F., et al.: Bert4rec: sequential recommendation with bidirectional encoder representations from transformer. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 1441\u20131450 (2019)","DOI":"10.1145\/3357384.3357895"},{"key":"2_CR29","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":"2_CR30","unstructured":"Vandenhende, S., Deruyttere, T., Grujicic, D.: A baseline for the commands for autonomous vehicles challenge. arXiv preprint arXiv:2004.13822 (2020)"},{"issue":"3","key":"2_CR31","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/MCI.2018.2840738","volume":"13","author":"T Young","year":"2018","unstructured":"Young, T., Hazarika, D., Poria, S., Cambria, E.: Recent trends in deep learning based natural language processing. IEEE Comput. Intell. Mag. 13(3), 55\u201375 (2018)","journal-title":"IEEE Comput. Intell. Mag."},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Niebles, J.C., Soto, A.: Interpretable visual question answering by visual grounding from attention supervision mining. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 349\u2013357. IEEE (2019)","DOI":"10.1109\/WACV.2019.00043"},{"key":"2_CR33","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. In: arXiv preprint arXiv:1904.07850 (2019)"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697\u20138710 (2018)","DOI":"10.1109\/CVPR.2018.00907"}],"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_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T00:05:24Z","timestamp":1735776324000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-66096-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030660956","9783030660963"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66096-3_2","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)"}}]}}