{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T17:17:04Z","timestamp":1742923024858,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031463136"},{"type":"electronic","value":"9783031463143"}],"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\/978-3-031-46314-3_26","type":"book-chapter","created":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T06:03:06Z","timestamp":1698472986000},"page":"322-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Referring Expression Comprehension Based on Cross Modal Feature Fusion and Iterative Reasoning"],"prefix":"10.1007","author":[{"given":"Chao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,29]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Yu, L., Lin, Z., et al.: Mattnet: modular attention network for referring expression comprehension. In: CVPR, pp. 1307\u20131315 (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., et al.: Neighbourhood watch: Referring expression comprehension via language-guided graph attention networks. In: CVPR, pp. 1960\u20131968 (2019)","DOI":"10.1109\/CVPR.2019.00206"},{"key":"26_CR3","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: ICCV, pp. 4673\u20134682 (2019)","DOI":"10.1109\/ICCV.2019.00477"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Dynamic graph attention for referring expression comprehension. In: ICCV, pp. 4644\u20134653 (2019)","DOI":"10.1109\/ICCV.2019.00474"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: A fast and accurate one-stage approach to visual grounding. In: ICCV, pp. 4683\u20134693 (2019)","DOI":"10.1109\/ICCV.2019.00478"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Luo, G., et al.: Multi-task collaborative network for joint referring expression comprehension and segmentation. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp.10034\u201310043 (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"26_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/978-3-030-58568-6_23","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Yang","year":"2020","unstructured":"Yang, Z., Chen, T., Wang, L., Luo, J.: Improving one-stage visual grounding by recursive sub-query construction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 387\u2013404. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_23"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Huang, B., Lian, D., et al.: Look before you leap: Learning landmark features for one-stage visual grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16888\u201316897 (2021)","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: Transvg: End-to-end visual grounding with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1769\u20131779 (2021)","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Yang, Z., Liu, D., et al.:Transvg++: End-to-end visual grounding with language conditioned vision transformer. arXiv preprint arXiv:2206.06619 (2022)","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"26_CR11","unstructured":"Devlin, J., Chang, M.-W. Lee, K. Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 (2018)"},{"key":"26_CR12","unstructured":"Liu, Y., et al.: Roberta: A robustly optimized bert pretraining approach. arXiv:1907.11692 (2019)"},{"key":"26_CR13","unstructured":"Lan, Z, et al.: Albert: A lite bert for self-supervised learning of language representations. In: ICLR (2020)"},{"key":"26_CR14","unstructured":"Cheng, B., et al.: Per-pixel classification is not all you need for semantic segmentation. In: NeurIPS, pp. 17864\u201317875 (2021)"},{"key":"26_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00a0\u00d7\u00a016 words: Transformers for image recognition at scale. In: ICLR (2021)"},{"key":"26_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Max-deeplab: End-to-end panoptic segmentation with mask transformers. In: CVPR, pp. 5463\u20135474 (2021)","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"26_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., et al.: 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)","DOI":"10.3115\/v1\/D14-1086"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Mao, J., et al.: Generation and comprehension of unambiguous object descriptions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"26_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1007\/978-3-319-46493-0_48","volume-title":"Computer Vision \u2013 ECCV 2016","author":"VK Nagaraja","year":"2016","unstructured":"Nagaraja, V.K., Morariu, V.I., Davis, L.S.: Modeling context between objects for referring expression understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 792\u2013807. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_48"},{"key":"26_CR22","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2018)"},{"key":"26_CR23","first-page":"1036","volume":"35","author":"L Chen","year":"2021","unstructured":"Chen, L., et al.: Ref-nms: breaking proposal bottlenecks in two-stage referring expression grounding. Proc. AAAI Conf. Artif. Intell. 35, 1036\u20131044 (2021)","journal-title":"Proc. AAAI Conf. Artif. Intell."}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46314-3_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:07:07Z","timestamp":1701112027000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46314-3_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031463136","9783031463143"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46314-3_26","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":"29 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","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 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icig2023.csig.org.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":"Conference Management Toolkit","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"409","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":"166","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":"41% - 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":"3","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)"}}]}}