{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:20:17Z","timestamp":1742955617433,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819988495"},{"type":"electronic","value":"9789819988501"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8850-1_13","type":"book-chapter","created":{"date-parts":[[2024,2,3]],"date-time":"2024-02-03T18:02:05Z","timestamp":1706983325000},"page":"156-169","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Weakly-Supervised Grounding for\u00a0VQA with\u00a0Dual Visual-Linguistic Interaction"],"prefix":"10.1007","author":[{"given":"Yi","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junwen","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qilong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanlin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiguo","family":"Nie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yudong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghua","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,4]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D., Kembhavi, A., Don\u2019t just assume; look and answer: overcoming priors for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4971\u20134980 (2018)","DOI":"10.1109\/CVPR.2018.00522"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Chen, C., Anjum, S., Gurari, D.: Grounding answers for visual questions asked by visually impaired people. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19098\u201319107 (2022)","DOI":"10.1109\/CVPR52688.2022.01851"},{"key":"13_CR4","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":"13_CR5","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (2018)"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: Vizwiz-priv: a dataset for recognizing the presence and purpose of private visual information in images taken by blind people. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 939\u2013948 (2019)","DOI":"10.1109\/CVPR.2019.00103"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.: ClevR: 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":"13_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1007\/978-3-031-19833-5_38","volume-title":"Computer Vision - ECCV 2022","author":"AU Khan","year":"2022","unstructured":"Khan, A.U., Kuehne, H., Gan, C., Da Vitoria Lobo, N., Shah, M.: Weakly supervised grounding for VQA in vision-language transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13695, pp. 652\u2013670. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_38"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32\u201373 (2017)","DOI":"10.1007\/s11263-016-0981-7"},{"key":"13_CR11","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"13_CR12","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: Vision and language representation learning with momentum distillation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 9694\u20139705 (2021)"},{"key":"13_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"13_CR14","unstructured":"Loshchilov, I., Hutter, F.: Fixing weight decay regularization in Adam (2017)"},{"key":"13_CR15","unstructured":"Pan, J., et al.: Tell me the evidence? Dual visual-linguistic interaction for answer grounding. arXiv preprint arXiv:2207.05703 (2022)"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Ramakrishnan, S.K., Pal, A., Sharma, G., Mittal, A.: An empirical evaluation of visual question answering for novel objects. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4392\u20134401 (2017)","DOI":"10.1109\/CVPR.2017.773"},{"key":"13_CR17","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"13_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"13_CR19","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402 (2022)"},{"key":"13_CR20","unstructured":"Schuhmann, C., et al.: Laion-400m: open dataset of clip-filtered 400 million image-text pairs. In: NeurIPS Workshop Datacentric AI, number FZJ-2022-00923. J\u00fclich Supercomputing Center (2021)"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Su, H., Jampani, V., Sun, D., Gallo, O., Learned-Miller, E., Kautz, J.: Pixel-adaptive convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11166\u201311175 (2019)","DOI":"10.1109\/CVPR.2019.01142"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LxMERT: learning cross-modality encoder representations from transformers. 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), pp. 5100\u20135111 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"13_CR24","unstructured":"Urooj, A., Kuehne, H., Duarte, K., Gan, C., Lobo, N., Shah, M.: Found a reason for me? Weakly-supervised grounded visual question answering using capsules. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8465\u20138474 (2021)"},{"key":"13_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L., Scene graph generation by iterative message passing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5410\u20135419 (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"13_CR27","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)"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.S.: LAVT: language-aware vision transformer for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18155\u201318165 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8850-1_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,3]],"date-time":"2024-02-03T18:04:00Z","timestamp":1706983440000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8850-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819988495","9789819988501"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8850-1_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"4 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fuzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.cn\/#\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"376","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":"101","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":"16","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":"2.9","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":"1.9","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)"}}]}}