{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:15:26Z","timestamp":1755839726565,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China (NSFC)","award":["62072459,62172421"],"award-info":[{"award-number":["62072459,62172421"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658024","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"915-924","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["STDG: Semi-Teacher-Student Training Paradigm for Depth-guided One-stage Scene Graph Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5478-1791","authenticated-orcid":false,"given":"Xukun","family":"Zhou","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5020-4277","authenticated-orcid":false,"given":"Zhenbo","family":"Song","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1511-7554","authenticated-orcid":false,"given":"Jun","family":"He","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4902-1078","authenticated-orcid":false,"given":"Hongyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6324-1712","authenticated-orcid":false,"given":"Zhaoxin","family":"Fan","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00014"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3157567"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3230590"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00167"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2621673"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00632"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475297"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR49039.2020.00065"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01882"},{"key":"e_1_3_2_1_13_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv:2010.11929 [cs.CV]"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2021"},{"key":"e_1_3_2_1_16_1","volume-title":"Object localization based on structural SVM using privileged information. Advances in Neural Information Processing Systems 27","author":"Feyereisl Jan","year":"2014","unstructured":"Jan Feyereisl, Suha Kwak, Jeany Son, and Bohyung Han. 2014. Object localization based on structural SVM using privileged information. Advances in Neural Information Processing Systems 27 (2014)."},{"key":"e_1_3_2_1_17_1","volume-title":"Olivier Le Meur, and Christine Guillemot","author":"Gautier Josselin","year":"2011","unstructured":"Josselin Gautier, Olivier Le Meur, and Christine Guillemot. 2011. Depth-based image completion for view synthesis. In 2011 3DTV Conference: The True Vision-Capture, Transmission and Display of 3D Video (3DTV-CON). IEEE, 1--4."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_23"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_22_1","volume-title":"Scene graph reasoning for visual question answering. arXiv preprint arXiv:2007.01072","author":"Hildebrandt Marcel","year":"2020","unstructured":"Marcel Hildebrandt, Hang Li, Rajat Koner, Volker Tresp, and Stephan G\u00fcnnemann. 2020. Scene graph reasoning for visual question answering. arXiv preprint arXiv:2007.01072 (2020)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/app10186497"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision 123 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3139000"},{"key":"e_1_3_2_1_28_1","volume-title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer. CoRR abs\/1907.01341","author":"Lasinger Katrin","year":"2019","unstructured":"Katrin Lasinger, Ren\u00e9 Ranftl, Konrad Schindler, and Vladlen Koltun. 2019. Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer. CoRR abs\/1907.01341 (2019). arXiv:1907.01341 http: \/\/arxiv.org\/abs\/1907.01341"},{"key":"e_1_3_2_1_29_1","volume-title":"Spigan: Privileged adversarial learning from simulation. arXiv preprint arXiv:1810.03756","author":"Lee Kuan-Hui","year":"2018","unstructured":"Kuan-Hui Lee, German Ros, Jie Li, and Adrien Gaidon. 2018. Spigan: Privileged adversarial learning from simulation. arXiv preprint arXiv:1810.03756 (2018)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01830"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01884"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.142"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01887"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01138"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_39_1","volume-title":"International Challenge on Activity Recognition (ActivityNet) CVPR 2021 Workshop","volume":"3","author":"Lu Yichao","year":"2021","unstructured":"Yichao Lu, Cheng Chang, Himanshu Rai, Guangwei Yu, and Maksims Volkovs. 2021. Multi-view scene graph generation in videos. In International Challenge on Activity Recognition (ActivityNet) CVPR 2021 Workshop, Vol. 3. 2."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01563"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3141044"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2494266.2494296"},{"key":"e_1_3_2_1_43_1","volume-title":"Revisiting multi-task learning with rock: a deep residual auxiliary block for visual detection. Advances in neural information processing systems 31","author":"Mordan Taylor","year":"2018","unstructured":"Taylor Mordan, Nicolas Thome, Gilles Henaff, and Matthieu Cord. 2018. Revisiting multi-task learning with rock: a deep residual auxiliary block for visual detection. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_44_1","volume-title":"Pixels to graphs by associative embedding. Advances in neural information processing systems 30","author":"Newell Alejandro","year":"2017","unstructured":"Alejandro Newell and Jia Deng. 2017. Pixels to graphs by associative embedding. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_45_1","volume-title":"Scene graph refinement network for visual question answering","author":"Qian Tianwen","year":"2022","unstructured":"Tianwen Qian, Jingjing Chen, Shaoxiang Chen, Bo Wu, and Yu-Gang Jiang. 2022. Scene graph refinement network for visual question answering. IEEE Transactions on Multimedia (2022)."},{"key":"e_1_3_2_1_46_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01343"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.06.042"},{"key":"e_1_3_2_1_50_1","unstructured":"Jingdong Wang Ke Sun Tianheng Cheng Borui Jiang Chaorui Deng Yang Zhao Dong Liu Yadong Mu Mingkui Tan Xinggang Wang Wenyu Liu and Bin Xiao. 2020. Deep High-Resolution Representation Learning for Visual Recognition. arXiv:1908.07919 [cs.CV]"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_11"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3074854"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01125"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1582-8"},{"key":"e_1_3_2_1_59_1","volume-title":"Syed Afaq Ali Shah, et al","author":"Zhu Guangming","year":"2022","unstructured":"Guangming Zhu, Liang Zhang, Youliang Jiang, Yixuan Dang, Haoran Hou, Peiyi Shen, Mingtao Feng, Xia Zhao, Qiguang Miao, Syed Afaq Ali Shah, et al. 2022. Scene graph generation: A comprehensive survey. arXiv preprint arXiv:2201.00443 (2022)."}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Phuket Thailand","acronym":"ICMR '24"},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658024","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658024","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:49:25Z","timestamp":1755766165000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658024"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":59,"alternative-id":["10.1145\/3652583.3658024","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658024","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}