{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:21:23Z","timestamp":1781587283514,"version":"3.54.5"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198113","type":"print"},{"value":"9783031198120","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19812-0_24","type":"book-chapter","created":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T14:03:42Z","timestamp":1667052222000},"page":"409-424","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":87,"title":["Fine-Grained Scene Graph Generation with\u00a0Data Transfer"],"prefix":"10.1007","author":[{"given":"Ao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maosong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,30]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Abdelkarim, S., Agarwal, A., Achlioptas, P., Chen, J., Huang, J., Li, B., Church, K., Elhoseiny, M.: Exploring long tail visual relationship recognition with large vocabulary. In: Proceedings of ICCV, pp. 15921\u201315930 (2021)","DOI":"10.1109\/ICCV48922.2021.01562"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., Parikh, D.: VQA: Visual question answering. In: Proceedings of ICCV, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Chen, T., Yu, W., Chen, R., Lin, L.: Knowledge-embedded routing network for scene graph generation. In: Proceedings of CVPR, pp. 6163\u20136171 (2019)","DOI":"10.1109\/CVPR.2019.00632"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Chiou, M.J., Ding, H., Yan, H., Wang, C., Zimmermann, R., Feng, J.: Recovering the unbiased scene graphs from the biased ones. In: Proceedings of ACM Multimedia, pp. 1581\u20131590 (2021)","DOI":"10.1145\/3474085.3475297"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Desai, A., Wu, T.Y., Tripathi, S., Vasconcelos, N.: Learning of visual relations: The devil is in the tails. In: Proceedings of ICCV, pp. 15404\u201315413 (2021)","DOI":"10.1109\/ICCV48922.2021.01512"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Gu, J., Joty, S., Cai, J., Zhao, H., Yang, X., Wang, G.: Unpaired image captioning via scene graph alignments. In: Proceedings of ICCV, pp. 10323\u201310332 (2019)","DOI":"10.1109\/ICCV.2019.01042"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Guo, Y., et al.: From general to specific: Informative scene graph generation via balance adjustment. In: Proceedings of ICCV, pp. 16383\u201316392 (2021)","DOI":"10.1109\/ICCV48922.2021.01607"},{"key":"24_CR8","unstructured":"He, T., Gao, L., Song, J., Cai, J., Li, Y.F.: Semantic compositional learning for low-shot scene graph generation. In: Proceedings of ICCV, pp. 2961\u20132969 (2021)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: Proceedings of CVPR, pp. 3668\u20133678 (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"24_CR10","unstructured":"Kipper, K., Korhonen, A., Ryant, N., Palmer, M.: Extending VerbNet with novel verb classes. In: LREC, pp. 1027\u20131032 (2006)"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Krishna, R., Zhu, Y., et al.: Visual Genome: Connecting language and vision using crowdsourced dense image annotations. In: IJCV, pp. 32\u201373 (2017)","DOI":"10.1007\/s11263-016-0981-7"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, S., Wan, B., He, X.: Bipartite graph network with adaptive message passing for unbiased scene graph generation. In: Proceedings of CVPR, pp. 11109\u201311119 (2021)","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, X., Xiao, J., Ji, W., Chua, T.S.: Invariant grounding for video question answering. In: Proceedings of CVPR, pp. 2928\u20132937 (2022)","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, X., Shang, X., Chua, T.S.: Interventional video relation detection. In: Proceedings of ACM Multimedia, pp. 4091\u20134099 (2021)","DOI":"10.1145\/3474085.3475540"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of CVPR, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Lin, X., Ding, C., Zeng, J., Tao, D.: Gps-Net: Graph property sensing network for scene graph generation. In: Proceedings of CVPR, pp. 3746\u20133753 (2020)","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"24_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Lu","year":"2016","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Miller, G.A.: WordNet: a lexical database for english. Commun. ACM 39\u201341 (1995)","DOI":"10.1145\/219717.219748"},{"key":"24_CR20","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: Proceedings of NIPS, pp. 91\u201399 (2015)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Suhail, M., et al.: Energy-based learning for scene graph generation. In: Proceedings of CVPR, pp. 13936\u201313945 (2021)","DOI":"10.1109\/CVPR46437.2021.01372"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., Zhang, H.: Unbiased scene graph generation from biased training. In: Proceedings of CVPR, pp. 3716\u20133725 (2020)","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., Liu, W.: Learning to compose dynamic tree structures for visual contexts. In: Proceedings of CVPR, pp. 6619\u20136628 (2019)","DOI":"10.1109\/CVPR.2019.00678"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Teney, D., Liu, L., van Den Hengel, A.: Graph-structured representations for visual question answering. In: Proceedings of CVPR, pp. 1\u20139 (2017)","DOI":"10.1109\/CVPR.2017.344"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Wan, A., et al.: NBDT: Neural-backed decision trees, pp. 1027\u20131032 (2021)","DOI":"10.17762\/pae.v58i1.851"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, R., Yao, Z., Shan, S., Chen, X.: Cross-modal scene graph matching for relationship-aware image-text retrieval. In: Proceedings of WACV, pp. 1508\u20131517 (2020)","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Wei, M., Chen, L., Ji, W., Yue, X., Chua, T.S.: Rethinking the two-stage framework for grounded situation recognition. In: Proceedings of AAAI, pp. 2651\u20132658 (2022)","DOI":"10.1609\/aaai.v36i3.20167"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Xiao, J., Yao, A., Liu, Z., Li, Y., Ji, W., Chua, T.S.: Video as conditional graph hierarchy for multi-granular question answering. In: Proceedings of AAAI, pp. 2804\u20132812 (2022)","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of CVPR, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"24_CR30","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 CVPR, pp. 5410\u20135419 (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Yan, S., et al.: PCPL: Predicate-correlation perception learning for unbiased scene graph generation. In: Proceedings of ACM Multimedia, pp. 265\u2013273 (2020)","DOI":"10.1145\/3394171.3413722"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., Cai, J.: Auto-encoding scene graphs for image captioning. In: Proceedings of CVPR, pp. 10685\u201310694 (2019)","DOI":"10.1109\/CVPR.2019.01094"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: PEVL: Position-enhanced pre-training and prompt tuning for vision-language models. arXiv preprint arXiv:2205.11169 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.763"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: Visual distant supervision for scene graph generation. In: Proceedings of ICCV, pp. 15816\u201315826 (2021)","DOI":"10.1109\/ICCV48922.2021.01552"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Yao, Y., Zhang, A., Zhang, Z., Liu, Z., Chua, T.S., Sun, M.: CPT: Colorful prompt tuning for pre-trained vision-language models. arXiv preprint arXiv:2109.11797 (2021)","DOI":"10.18653\/v1\/2022.findings-acl.273"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Yu, J., Chai, Y., Wang, Y., Hu, Y., Wu, Q.: CogTree: Cognition tree loss for unbiased scene graph generation, pp. 1274\u20131280 (2021)","DOI":"10.24963\/ijcai.2021\/176"},{"key":"24_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1007\/978-3-030-58592-1_36","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Zareian","year":"2020","unstructured":"Zareian, A., Karaman, S., Chang, S.-F.: Bridging knowledge graphs to generate scene graphs. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 606\u2013623. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_36"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural Motifs: Scene graph parsing with global context. In: Proceedings of CVPR, pp. 5831\u20135840 (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"24_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, J., Kalantidis, Y., Rohrbach, M., Paluri, M., Elgammal, A., Elhoseiny, M.: Large-scale visual relationship understanding. In: Proceedings of the AAAI, pp. 9185\u20139194 (2019)","DOI":"10.1609\/aaai.v33i01.33019185"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Wu, Q., Shen, C., Reid, I., van den Hengel, A.: HCVRD: a benchmark for large-scale human-centered visual relationship detection. In: Proceedings of AAAI, pp. 7631\u20137638 (2018)","DOI":"10.1609\/aaai.v32i1.12260"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19812-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T19:31:47Z","timestamp":1701286307000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19812-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198113","9783031198120"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19812-0_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"30 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}