{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:55:26Z","timestamp":1757314526045,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"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.springer.com\/tdm"},{"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.springer.com\/tdm"}],"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_4","type":"book-chapter","created":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T07:03:14Z","timestamp":1609570994000},"page":"39-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Cosine Meets Softmax: A Tough-to-beat Baseline for Visual Grounding"],"prefix":"10.1007","author":[{"given":"Nivedita","family":"Rufus","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Unni Krishnan R","family":"Nair","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K. Madhava","family":"Krishna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vineet","family":"Gandhi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,3]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Akbari, H., Karaman, S., Bhargava, S., Chen, B., Vondrick, C., Chang, S.F.: Multi-level multimodal common semantic space for image-phrase grounding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12476\u201312486 (2019)","key":"4_CR1","DOI":"10.1109\/CVPR.2019.01276"},{"doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: Nuscenes: a multimodal dataset for autonomous driving (2019)","key":"4_CR2","DOI":"10.1109\/CVPR42600.2020.01164"},{"doi-asserted-by":"crossref","unstructured":"Chen, K., Kovvuri, R., Nevatia, R.: Query-guided regression network with context policy for phrase grounding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 824\u2013832 (2017)","key":"4_CR3","DOI":"10.1109\/ICCV.2017.95"},{"doi-asserted-by":"crossref","unstructured":"Datta, S., Sikka, K., Roy, A., Ahuja, K., Parikh, D., Divakaran, A.: Align2ground: weakly supervised phrase grounding guided by image-caption alignment. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2601\u20132610 (2019)","key":"4_CR4","DOI":"10.1109\/ICCV.2019.00269"},{"doi-asserted-by":"crossref","unstructured":"Deng, C., Wu, Q., Wu, Q., Hu, F., Lyu, F., Tan, M.: Visual grounding via accumulated attention. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7746\u20137755 (2018)","key":"4_CR5","DOI":"10.1109\/CVPR.2018.00808"},{"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 (2020)","key":"4_CR6","DOI":"10.1016\/j.engappai.2021.104257"},{"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. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019). 10.18653\/v1\/d19-1215, http:\/\/dx.doi.org\/10.18653\/v1\/D19-1215","key":"4_CR7","DOI":"10.18653\/v1\/D19-1215"},{"unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2018)","key":"4_CR8"},{"doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE International Conference on Computer Vision (2019)","key":"4_CR9","DOI":"10.1109\/ICCV.2019.00667"},{"doi-asserted-by":"crossref","unstructured":"Engilberge, M., Chevallier, L., P\u00e9rez, P., Cord, M.: Finding beans in burgers: deep semantic-visual embedding with localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3984\u20133993 (2018)","key":"4_CR10","DOI":"10.1109\/CVPR.2018.00419"},{"doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Darrell, T., Saenko, K.: Explainable neural computation via stack neural module networks. In: Proceedings of the European conference on computer vision (ECCV) (2018)","key":"4_CR11","DOI":"10.1007\/978-3-030-01234-2_4"},{"doi-asserted-by":"crossref","unstructured":"Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K., Darrell, T.: Natural language object retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","key":"4_CR12","DOI":"10.1109\/CVPR.2016.493"},{"unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning (2018)","key":"4_CR13"},{"doi-asserted-by":"crossref","unstructured":"Javed, S.A., Saxena, S., Gandhi, V.: Learning unsupervised visual grounding through semantic self-supervision. arXiv preprint arXiv:1803.06506 (2018)","key":"4_CR14","DOI":"10.24963\/ijcai.2019\/112"},{"unstructured":"Karpathy, A., Joulin, A., Fei-Fei, L.: Deep fragment embeddings for bidirectional image sentence mapping (2014)","key":"4_CR15"},{"doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: Referitgame: referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 787\u2013798 (2014)","key":"4_CR16","DOI":"10.3115\/v1\/D14-1086"},{"unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach (2019)","key":"4_CR17"},{"doi-asserted-by":"crossref","unstructured":"Musgrave, K., Belongie, S., Lim, S.N.: A metric learning reality check. arXiv preprint arXiv:2003.08505 (2020)","key":"4_CR18","DOI":"10.1007\/978-3-030-58595-2_41"},{"doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","key":"4_CR19","DOI":"10.1109\/ICCV.2015.303"},{"doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (2019). http:\/\/arxiv.org\/abs\/1908.10084","key":"4_CR20","DOI":"10.18653\/v1\/D19-1410"},{"key":"4_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/978-3-319-46448-0_49","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Rohrbach","year":"2016","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 817\u2013834. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_49"},{"unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter (2019)","key":"4_CR22"},{"doi-asserted-by":"crossref","unstructured":"Sriram, N.N., Maniar, T., Kalyanasundaram, J., Gandhi, V., Bhowmick, B., Madhava Krishna, K.: Talk to the vehicle: language conditioned autonomous navigation of self driving cars. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5284\u20135290 (2019)","key":"4_CR23","DOI":"10.1109\/IROS40897.2019.8967929"},{"unstructured":"Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks (2019)","key":"4_CR24"},{"unstructured":"Vandenhende, S., Deruyttere, T., Grujicic, D.: A baseline for the commands for autonomous vehicles challenge (2020)","key":"4_CR25"},{"issue":"2","key":"4_CR26","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., Li, Y., Huang, J., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 394\u2013407 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5005\u20135013 (2016)","key":"4_CR27","DOI":"10.1109\/CVPR.2016.541"},{"doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: Mattnet: modular attention network for referring expression comprehension. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1307\u20131315 (2018)","key":"4_CR28","DOI":"10.1109\/CVPR.2018.00142"}],"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_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T00:06:03Z","timestamp":1735776363000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-66096-3_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030660956","9783030660963"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66096-3_4","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)"}}]}}