{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:27:13Z","timestamp":1743085633795,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031341106"},{"type":"electronic","value":"9783031341113"}],"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\/978-3-031-34111-3_32","type":"book-chapter","created":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T08:03:56Z","timestamp":1685520236000},"page":"381-392","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Pairwise Spatial Relationships for\u00a0Actions Recognition and\u00a0Scene Graph Generation"],"prefix":"10.1007","author":[{"given":"Anfel","family":"Amirat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nadia","family":"Baha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lamine","family":"Benrais","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,1]]},"reference":[{"key":"32_CR1","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":"32_CR2","doi-asserted-by":"crossref","unstructured":"Yin, G., et al.: Zoom-net: Mining deep feature interactions for visual relationship recognition. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 322\u2013338 (2018)","DOI":"10.1007\/978-3-030-01219-9_20"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Zhou, B., Wang, K., Wang, X.: Scene graph generation from objects, phrases and region captions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1261\u20131270 (2017)","DOI":"10.1109\/ICCV.2017.142"},{"issue":"4","key":"32_CR4","doi-asserted-by":"publisher","first-page":"511","DOI":"10.3390\/sym12040511","volume":"12","author":"S Li","year":"2020","unstructured":"Li, S., Tang, M., Zhang, J., Jiang, L.: Attentive gated graph neural network for image scene graph generation. Symmetry 12(4), 511 (2020)","journal-title":"Symmetry"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Tian, P., Mo, H., Jiang, L.: Exploring correlation of relationship reasoning for scene graph generation. Int. J. Mach. Learn. Cybern. 13(9), 2479\u20132493 (2022)","DOI":"10.1007\/s13042-022-01538-2"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Dornadula, A., Narcomey, A., Krishna, R., Bernstein, M., Li, F.F.: Visual relationships as functions: Enabling few-shot scene graph prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp. 0\u20130 (2019)","DOI":"10.1109\/ICCVW.2019.00214"},{"key":"32_CR7","unstructured":"Liao, W., Lan, C., Zeng, W., Yang, M.Y., Rosenhahn, B.: Exploring the semantics for visual relationship detection. arXiv preprint arXiv:1904.02104 (2019)"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3668\u20133678 (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"32_CR9","unstructured":"Ramnath, S., Saha, A., Chakrabarti, S., Khapra, M.M.: Scene Graph based Image Retrieval-A case study on the CLEVR Dataset. arXiv preprint arXiv:1911.00850 (2019)"},{"issue":"9","key":"32_CR10","doi-asserted-by":"publisher","first-page":"2559","DOI":"10.1109\/TVCG.2017.2759265","volume":"24","author":"F Fang","year":"2017","unstructured":"Fang, F., Yi, M., Feng, H., Hu, S., Xiao, C.: Narrative collage of image collections by scene graph recombination. IEEE Trans. Visual Comput. Graph. 24(9), 2559\u20132572 (2017)","journal-title":"IEEE Trans. Visual Comput. Graph."},{"key":"32_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-58574-7_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Herzig","year":"2020","unstructured":"Herzig, R., Bar, A., Xu, H., Chechik, G., Darrell, T., Globerson, A.: Learning canonical representations for scene graph to image generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 210\u2013227. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_13"},{"key":"32_CR12","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 the IEEE\/CVF International Conference on Computer Vision, pp. 10323\u201310332 (2019)","DOI":"10.1109\/ICCV.2019.01042"},{"key":"32_CR13","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/j.jvcir.2018.12.027","volume":"58","author":"N Xu","year":"2019","unstructured":"Xu, N., Liu, A.A., Liu, J., Nie, W., Su, Y.: Scene graph captioner: image captioning based on structural visual representation. J. Vis. Commun. Image Represent. 58, 477\u2013485 (2019)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"32_CR14","unstructured":"Yang, Z., Qin, Z., Yu, J., Hu, Y.: Scene graph reasoning with prior visual relationship for visual question answering. arXiv preprint arXiv:1812.09681 (2018)"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Qian, T., Chen, J., Chen, S., Wu, B., Jiang, Y.G.: Scene graph refinement network for visual question answering. In: IEEE Transactions on Multimedia (2022)","DOI":"10.1109\/TMM.2022.3169065"},{"key":"32_CR16","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":"32_CR17","doi-asserted-by":"crossref","unstructured":"Yu, R., Li, A., Morariu, V.I., Davis, L.S.: Visual relationship detection with internal and external linguistic knowledge distillation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1974\u20131982 (2017)","DOI":"10.1109\/ICCV.2017.121"},{"key":"32_CR18","unstructured":"Zhu, G., et al.: Scene graph generation: A comprehensive survey. arXiv preprint arXiv:2201.00443 (2022)"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: Scene graph parsing with global context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5831\u20135840 (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"32_CR20","unstructured":"Cong, W., Wang, W., Lee, W.C.: Scene graph generation via conditional random fields. arXiv preprint arXiv:1811.08075 (2018)"},{"key":"32_CR21","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":"32_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Wang, X., Tang, X.O.: Vip-cnn: Visual phrase guided convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1347\u20131356 (2017)","DOI":"10.1109\/CVPR.2017.766"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Dai, B., Zhang, Y., Lin, D.: Detecting visual relationships with deep relational networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3076\u20133086 (2017)","DOI":"10.1109\/CVPR.2017.352"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Zhou, B., Shi, J., Zhang, C., Wang, X.: Factorizable net: an efficient subgraph-based framework for scene graph generation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 335\u2013351 (2018)","DOI":"10.1007\/978-3-030-01246-5_21"},{"key":"32_CR25","unstructured":"Liao, W., Lan, C., Zeng, W., Yang, M.Y., Rosenhahn, B.: Exploring the semantics for visual relationship detection. arXiv preprint arXiv:1904.02104 (2019)"},{"key":"32_CR26","unstructured":"Fasola, J., Mataric, M.: Using spatial language to guide and instruct robots in household environments. In: 2012 AAAI Fall Symposium Series (2012)"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Kim, J., Rohrbach, A., Darrell, T., Canny, J., Akata, Z.: Textual explanations for self-driving vehicles. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 563\u2013578 (2018)","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Ghanimifard, M., Dobnik, S.: What goes into a word: generating image descriptions with top-down spatial knowledge. In: Proceedings of the 12th International Conference on Natural Language Generation, pp. 540\u2013551 (2019)","DOI":"10.18653\/v1\/W19-8668"},{"issue":"1","key":"32_CR29","first-page":"1","volume":"19","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Pan, Y., Yao, T., Huang, R., Mei, T., Chen, C.W.: Boosting scene graph generation with visual relation saliency. ACM Trans. Multimed. Comput. Commun. Appl. 19(1), 1\u201317 (2023)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"32_CR30","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"32_CR31","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":"32_CR32","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"32_CR33","unstructured":"Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.: Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 (2015)"},{"key":"32_CR34","doi-asserted-by":"crossref","unstructured":"Yang, K., Russakovsky, O., Deng, J.: Spatialsense: An adversarially crowdsourced benchmark for spatial relation recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2051\u20132060 (2019)","DOI":"10.1109\/ICCV.2019.00214"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Japkowicz, N., Shah, M.: Evaluating learning algorithms: a classification perspective. Cambridge University Press (2011)","DOI":"10.1017\/CBO9780511921803"},{"key":"32_CR36","doi-asserted-by":"crossref","unstructured":"Peyre, J., Sivic, J., Laptev, I., Schmid, C.: Weakly-supervised learning of visual relations. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5179\u20135188 (2017)","DOI":"10.1109\/ICCV.2017.554"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from rgbd images. In: ECCV (5) 7576, 746\u2013760 (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"32_CR38","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Liu, L., Shen, C., Reid, I.: Towards context-aware interaction recognition for visual relationship detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 589\u2013598 (2017)","DOI":"10.1109\/ICCV.2017.71"},{"key":"32_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S.F., Chua, T.S.: Visual translation embedding network for visual relation detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5532\u20135540 (2017)","DOI":"10.1109\/CVPR.2017.331"},{"key":"32_CR40","doi-asserted-by":"crossref","unstructured":"Ding, X., Li, Y., Pan, Y., Zeng, D., Yao, T.: Exploring depth information for spatial relation recognition. In: 2020 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), pp. 279\u2013284. IEEE (2020)","DOI":"10.1109\/MIPR49039.2020.00065"}],"container-title":["IFIP Advances in Information and Communication Technology","Artificial Intelligence Applications and Innovations"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-34111-3_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T08:18:47Z","timestamp":1685521127000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-34111-3_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031341106","9783031341113"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-34111-3_32","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"type":"print","value":"1868-4238"},{"type":"electronic","value":"1868-422X"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 June 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Artificial Intelligence Applications and Innovations","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Le\u00f3n","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"14 June 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 June 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ifipaiai.org\/2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"185","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":"75","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":"17","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":"2,8","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":"3,1","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)"}},{"value":"This event was held in hybrid mode.","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)"}}]}}