{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:42:51Z","timestamp":1776386571731,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Scientific Research Leader Studio of Jinan","award":["2021GXRC081"],"award-info":[{"award-number":["2021GXRC081"]}]},{"name":"Joint Project for Smart Computing of Shandong Natural Science Foundation","award":["ZR2022LZH012"],"award-info":[{"award-number":["ZR2022LZH012"]}]},{"name":"Joint Project for Smart Computing of Shandong Natural Science Foundation","award":["ZR2020LZH015"],"award-info":[{"award-number":["ZR2020LZH015"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543873.3587649","type":"proceedings-article","created":{"date-parts":[[2023,4,28]],"date-time":"2023-04-28T11:36:14Z","timestamp":1682681774000},"page":"669-677","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Dual-grained Text-Image Olfactory Matching Model with Mutual Promotion Stages"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1728-9758","authenticated-orcid":false,"given":"Yi","family":"Shao","sequence":"first","affiliation":[{"name":"Shandong Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6157-2051","authenticated-orcid":false,"given":"Jiande","family":"Sun","sequence":"additional","affiliation":[{"name":"Shandong Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6683-0205","authenticated-orcid":false,"given":"Ye","family":"Jiang","sequence":"additional","affiliation":[{"name":"Qingdao University of Science and Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9132-6684","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong Management University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Multimodal machine learning: A survey and taxonomy","author":"Baltru\u0161aitis Tadas","year":"2018","unstructured":"Tadas Baltru\u0161aitis, Chaitanya Ahuja, and Louis-Philippe Morency. 2018. Multimodal machine learning: A survey and taxonomy. IEEE transactions on pattern analysis and machine intelligence 41, 2 (2018), 423\u2013443."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40494-016-0114-1"},{"key":"e_1_3_2_2_3_1","volume-title":"Towards olfactory information extraction from text: A case study on detecting smell experiences in novels. arXiv preprint arXiv:2011.08903","author":"Brate Ryan","year":"2020","unstructured":"Ryan Brate, Paul Groth, and Marieke van Erp. 2020. Towards olfactory information extraction from text: A case study on detecting smell experiences in novels. arXiv preprint arXiv:2011.08903 (2020)."},{"key":"e_1_3_2_2_4_1","volume-title":"Japan","author":"J Brooks","year":"2021","unstructured":"J Brooks [n. d.]. STT21: Smell, Taste, and Temperature Interfaces workshop. Yokohama, Japan (2021)."},{"key":"e_1_3_2_2_5_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_6_1","volume-title":"HanLP: Han language processing. URL: https:\/\/github. com\/hankcs\/HanLP","author":"Han He.","year":"2014","unstructured":"Han He. 2014. HanLP: Han language processing. URL: https:\/\/github. com\/hankcs\/HanLP (2014)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_8_1","unstructured":"Alexander Hermans Lucas Beyer and Bastian Leibe. 2017. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"David Howes. 2006. Charting the sensorial revolution.","DOI":"10.2752\/174589206778055673"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.2752\/174589314X14023847039917"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882225"},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of MediaEval 2022 CEUR Workshop.","author":"H\u00fcrriyeto\u011flu Ali","year":"2022","unstructured":"Ali H\u00fcrriyeto\u011flu, Teresa Paccosi, Stefano Menini, Mathias Zinnen, Pasquale Lisena, Kiymet Akdemir, Rapha\u00ebl Troncy, and Marieke van Erp. 2022. MUSTI-Multimodal Understanding of Smells in Texts and Images at MediaEval 2022. In Proceedings of MediaEval 2022 CEUR Workshop."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S19-2146"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4205"},{"key":"e_1_3_2_2_16_1","volume-title":"International Journal of Machine Learning and Cybernetics","author":"Jiang Ye","year":"2022","unstructured":"Ye Jiang and Yimin Wang. 2022. Topic-aware hierarchical multi-attention network for text classification. International Journal of Machine Learning and Cybernetics (2022), 1\u201313."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA200327"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"e_1_3_2_2_19_1","volume-title":"The inability to self-evaluate smell performance. How the vividness of mental images outweighs awareness of olfactory performance. Frontiers in psychology 6","author":"Kollndorfer Kathrin","year":"2015","unstructured":"Kathrin Kollndorfer, Ksenia Kowalczyk, Stefanie Nell, Jacqueline Krajnik, Christian\u00a0A Mueller, and Veronika Sch\u00f6pf. 2015. The inability to self-evaluate smell performance. How the vividness of mental images outweighs awareness of olfactory performance. Frontiers in psychology 6 (2015), 627."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Bodo Kubartz. 2014. Urban smellscapes: understanding and designing city smell environments. 99\u2013101\u00a0pages.","DOI":"10.1080\/2325548X.2014.919152"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00446"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"e_1_3_2_2_27_1","volume-title":"Smell as Self-identity: Capitalist Ideology and Olfactory Imagination in Das Parfum\u2019s Multimedia Storytelling. Ph.\u00a0D. Dissertation","author":"Liu Xinrong","unstructured":"Xinrong Liu. 2020. Smell as Self-identity: Capitalist Ideology and Olfactory Imagination in Das Parfum\u2019s Multimedia Storytelling. Ph.\u00a0D. Dissertation. Chapman University."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jns.2021.117433"},{"key":"e_1_3_2_2_29_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_2_30_1","volume-title":"Proceedings of MediaEval 2023 CEUR Workshop.","author":"Shao Yi","year":"2022","unstructured":"Yi Shao, Yang Zhang, Wenbo Wan, Jing Li, and Jiande Sun. 2022. Multilingual Text-Image Olfactory Object Matching Based on Object Detection. In Proceedings of MediaEval 2023 CEUR Workshop."},{"key":"e_1_3_2_2_31_1","volume-title":"IEEE International Conference on, Vol.\u00a03. IEEE Computer Society, 1470\u20131470","author":"Sivic Josef","year":"2003","unstructured":"Josef Sivic and Andrew Zisserman. 2003. Video Google: A text retrieval approach to object matching in videos. In Computer Vision, IEEE International Conference on, Vol.\u00a03. IEEE Computer Society, 1470\u20131470."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"e_1_3_2_2_33_1","volume-title":"Olfactory system and emotion: common substrates. European annals of otorhinolaryngology, head and neck diseases 128, 1","author":"Soudry Ya\u00ebl","year":"2011","unstructured":"Ya\u00ebl Soudry, C\u00e9dric Lemogne, David Malinvaud, S-M Consoli, and Pierre Bonfils. 2011. Olfactory system and emotion: common substrates. European annals of otorhinolaryngology, head and neck diseases 128, 1 (2011), 18\u201323."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.latechclfl-1.2"},{"key":"e_1_3_2_2_35_1","unstructured":"ultralytics. 2020. yolov5. https:\/\/github.com\/ultralytics\/yolov5."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1075\/arcl.4.09vel"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.2752\/174589313X13589681980696"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.035"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877127"},{"key":"e_1_3_2_2_40_1","volume-title":"Multimodal Fake News Detection via CLIP-Guided Learning. arXiv preprint arXiv:2205.14304","author":"Zhou Yangming","year":"2022","unstructured":"Yangming Zhou, Qichao Ying, Zhenxing Qian, Sheng Li, and Xinpeng Zhang. 2022. Multimodal Fake News Detection via CLIP-Guided Learning. arXiv preprint arXiv:2205.14304 (2022)."}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3587649","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543873.3587649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:48:57Z","timestamp":1755820137000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3587649"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":40,"alternative-id":["10.1145\/3543873.3587649","10.1145\/3543873"],"URL":"https:\/\/doi.org\/10.1145\/3543873.3587649","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}