{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T09:08:43Z","timestamp":1777972123997,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"name":"Beijing Natural Science Foundation","award":["L251032, 4242028"],"award-info":[{"award-number":["L251032, 4242028"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376021"],"award-info":[{"award-number":["62376021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"publisher","award":["F2025105036"],"award-info":[{"award-number":["F2025105036"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755096","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"3477-3486","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Differential Contrastive Training for Gaze Estimation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1824-2270","authenticated-orcid":false,"given":"Lin","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University, Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6054-7970","authenticated-orcid":false,"given":"Yi","family":"Tian","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2660-8749","authenticated-orcid":false,"given":"Xiyun","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2206-5051","authenticated-orcid":false,"given":"Wanru","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, School of Computer Science and Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8408-3816","authenticated-orcid":false,"given":"Yi","family":"Jin","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, School of Computer Science and Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4465-372X","authenticated-orcid":false,"given":"Yaping","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Manuel Montes y G\u00f3mez, and Fabio A. Gonz\u00e1lez","author":"Arevalo John","year":"2017","unstructured":"John Arevalo, Thamar Solorio, Manuel Montes y G\u00f3mez, and Fabio A. Gonz\u00e1lez. 2017. Gated Multimodal Units for Information Fusion. ArXiv, Vol. abs\/1702.01992 (2017). https:\/\/api.semanticscholar.org\/CorpusID:9401721"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00417"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00140"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376405"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01440"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20876-9_20"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19921"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6636"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956687"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2982828"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00154"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"e_1_3_2_1_13_1","volume-title":"Teach CLIP to Develop a Number Sense for Ordinal Regression. ArXiv","author":"Du Yao","year":"2024","unstructured":"Yao Du, Qiang Zhai, Weihang Dai, and Xiaomeng Li. 2024. Teach CLIP to Develop a Number Sense for Ordinal Regression. ArXiv, Vol. abs\/2408.03574 (2024). https:\/\/api.semanticscholar.org\/CorpusID:271744959"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_21"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2578153.2578190"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_20"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612390"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680927"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69541-5_18"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.139"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00701"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3361330"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.239"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3348528"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00381"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-80126-2"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00547"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"e_1_3_2_1_30_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning.","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. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01900"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"e_1_3_2_1_34_1","first-page":"2579","article-title":"Visualizing Data","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data, Using T-SNE. Journal of Machine Learning Research, Vol. 9, 86 (2008), 2579-2605. http:\/\/jmlr.org\/papers\/v9\/vandermaaten08a.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_35_1","volume-title":"Attention Is All You Need","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. In Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00314"},{"key":"e_1_3_2_1_37_1","volume-title":"GazeCLIP: Towards Enhancing Gaze Estimation via Text Guidance. ArXiv","author":"Wang Jun","year":"2023","unstructured":"Jun Wang, Hao Ruan, Mingjie Wang, Chuanghui Zhang, Huachun Li, and Jun Zhou. 2023. GazeCLIP: Towards Enhancing Gaze Estimation via Text Guidance. ArXiv, Vol. abs\/2401.00260 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266693788"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01218"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28368"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01877"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01877"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680582"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111244"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28452"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28496"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00927"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3549201"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358948"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_22"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299081"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.284"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2778103"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3364539"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:20:43Z","timestamp":1765308043000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755096"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":55,"alternative-id":["10.1145\/3746027.3755096","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755096","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}