{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:50:50Z","timestamp":1761094250419,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746266.3762160","type":"proceedings-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:19:13Z","timestamp":1761059953000},"page":"47-51","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Prospective Analysis of Semantic Image Retrieval: Comparing Scene Graph, Visual Features, and Captions"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3041-4330","authenticated-orcid":false,"given":"Takahiro","family":"Komamizu","sequence":"first","affiliation":[{"name":"Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,26]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2711011"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1348246.1348248"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/S10044-008-0141-Y"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475619"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.105"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-68312-1_18"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR59079.2023.00021"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/S11263-016-0981--7"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3504274"},{"key":"e_1_3_2_1_13_1","volume-title":"Proc. International Conference on Machine Learning. 19730--19742","author":"Li Junnan","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven C. H. Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In Proc. International Conference on Machine Learning. 19730--19742. https:\/\/proceedings.mlr.press\/v202\/li23q.html"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01888"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.PATCOG.2006.04.045"},{"key":"e_1_3_2_1_16_1","unstructured":"OpenAI. 2023. GPT-4 with vision. https:\/\/openai.com\/research\/gpt-4."},{"key":"e_1_3_2_1_17_1","volume-title":"DINOv2: Learning Robust Visual Features without Supervision. Trans. Mach. Learn. Res. 2024","author":"Oquab Maxime","year":"2024","unstructured":"Maxime Oquab, Timoth\u00e9e Darcet, Th\u00e9o Moutakanni, Huy V. Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mido Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Herv\u00e9 J\u00e9gou, Julien Mairal, Patrick Labatut, Armand Joulin, and Piotr Bojanowski. 2024. DINOv2: Learning Robust Visual Features without Supervision. Trans. Mach. Learn. Res. 2024 (2024). https:\/\/openreview.net\/forum?id=a68SUt6zFt"},{"key":"e_1_3_2_1_18_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. (2021), 8748--8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01013"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01189"},{"key":"e_1_3_2_1_21_1","volume-title":"Proc. 4th International Conference on Learning Representations. http:\/\/arxiv.org\/abs\/1511","author":"Tolias Giorgos","year":"2016","unstructured":"Giorgos Tolias, Ronan Sicre, and Herv\u00e9 J\u00e9gou. 2016. Particular object retrieval with integral max-pooling of CNN activations. In Proc. 4th International Conference on Learning Representations. http:\/\/arxiv.org\/abs\/1511.05879"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1859891"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Liang Wang Nan Yang Xiaolong Huang Binxing Jiao Linjun Yang Daxin Jiang Rangan Majumder and Furu Wei. 2022. Text Embeddings by Weakly-Supervised Contrastive Pre-training. doi:10.48550\/ARXIV.2212.03533 arXiv:2212.03533","DOI":"10.48550\/ARXIV.2212.03533"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Yang Fan Kai Dang Mengfei Du Xuancheng Ren Rui Men Dayiheng Liu Chang Zhou Jingren Zhou and Junyang Lin. 2024. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. doi:10.48550\/ARXIV.2409.12191 arXiv:2409.12191","DOI":"10.48550\/ARXIV.2409.12191"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783417"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019087"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030-01246--5_41"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01156"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"}],"event":{"name":"MM '25:The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 3rd International Workshop on Deep Multimodal Generation and Retrieval"],"original-title":[],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:20:10Z","timestamp":1761060010000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746266.3762160"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":30,"alternative-id":["10.1145\/3746266.3762160","10.1145\/3746266"],"URL":"https:\/\/doi.org\/10.1145\/3746266.3762160","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]},"assertion":[{"value":"2025-10-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}