{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:29:49Z","timestamp":1764588589291,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681636","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"1092-1100","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["AlignCLIP: Align Multi Domains of Texts Input for CLIP models with Object-IoU Loss"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9532-5219","authenticated-orcid":false,"given":"Lu","family":"Zhang","sequence":"first","affiliation":[{"name":"Tencent Youtu Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3424-4866","authenticated-orcid":false,"given":"Ke","family":"Yan","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3175-3553","authenticated-orcid":false,"given":"Shouhong","family":"Ding","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International conference on machine learning. PMLR, 1463--1472","author":"Chang Nadine","year":"2021","unstructured":"Nadine Chang, Zhiding Yu, Yu-Xiong Wang, Animashree Anandkumar, Sanja Fidler, and Jose M Alvarez. 2021. Image-level or object-level? a tale of two resampling strategies for long-tailed detection. In International conference on machine learning. PMLR, 1463--1472."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01766"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_1_5_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Fan Lijie","year":"2024","unstructured":"Lijie Fan, Dilip Krishnan, Phillip Isola, Dina Katabi, and Yonglong Tian. 2024. Improving clip training with language rewrites. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27955"},{"key":"e_1_3_2_1_9_1","volume-title":"Pyramidclip: Hierarchical feature alignment for vision-language model pretraining. Advances in neural information processing systems","author":"Gao Yuting","year":"2022","unstructured":"Yuting Gao, Jinfeng Liu, Zihan Xu, Jun Zhang, Ke Li, Rongrong Ji, and Chunhua Shen. 2022. Pyramidclip: Hierarchical feature alignment for vision-language model pretraining. Advances in neural information processing systems, Vol. 35 (2022), 35959--35970."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_11_1","volume-title":"Unicoder: A universal language encoder by pre-training with multiple cross-lingual tasks. arXiv preprint arXiv:1909.00964","author":"Huang Haoyang","year":"2019","unstructured":"Haoyang Huang, Yaobo Liang, Nan Duan, Ming Gong, Linjun Shou, Daxin Jiang, and Ming Zhou. 2019. Unicoder: A universal language encoder by pre-training with multiple cross-lingual tasks. arXiv preprint arXiv:1909.00964 (2019)."},{"key":"e_1_3_2_1_12_1","volume-title":"International conference on machine learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904--4916."},{"key":"e_1_3_2_1_13_1","volume-title":"Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings, Part XXX 16","author":"Li Xiujun","year":"2020","unstructured":"Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, et al. 2020. Oscar: Object-semantics aligned pre-training for vision-language tasks. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXX 16. Springer, 121--137."},{"key":"e_1_3_2_1_16_1","volume-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm. arXiv preprint arXiv:2110.05208","author":"Li Yangguang","year":"2021","unstructured":"Yangguang Li, Feng Liang, Lichen Zhao, Yufeng Cui, Wanli Ouyang, Jing Shao, Fengwei Yu, and Junjie Yan. 2021. Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm. arXiv preprint arXiv:2110.05208 (2021)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00034"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00500"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00681"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00640"},{"key":"e_1_3_2_1_22_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","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, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00667"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_1_25_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Shi Jiang-Xin","year":"2023","unstructured":"Jiang-Xin Shi, Tong Wei, Yuke Xiang, and Yu-Feng Li. 2023. How Re-sampling Helps for Long-Tail Learning? Advances in Neural Information Processing Systems, Vol. 36 (2023)."},{"key":"e_1_3_2_1_26_1","unstructured":"Gemma Team Thomas Mesnard Cassidy Hardin Robert Dadashi Surya Bhupatiraju Shreya Pathak Laurent Sifre Morgane Rivi\u00e8re Mihir Sanjay Kale Juliette Love Pouya Tafti L\u00e9onard Hussenot Pier Giuseppe Sessa Aakanksha Chowdhery Adam Roberts Aditya Barua Alex Botev Alex Castro-Ros Ambrose Slone Am\u00e9lie H\u00e9liou Andrea Tacchetti Anna Bulanova Antonia Paterson Beth Tsai Bobak Shahriari Charline Le Lan Christopher A. Choquette-Choo Cl\u00e9ment Crepy Daniel Cer Daphne Ippolito David Reid"},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Machine Learning. PMLR, 23615--23630","author":"Wei Hongxin","year":"2022","unstructured":"Hongxin Wei, Lue Tao, Renchunzi Xie, Lei Feng, and Bo An. 2022. Open-sampling: Exploring out-of-distribution data for re-balancing long-tailed datasets. In International Conference on Machine Learning. PMLR, 23615--23630."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"e_1_3_2_1_29_1","volume-title":"GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition? arXiv preprint arXiv:2311.15732","author":"Wu Wenhao","year":"2023","unstructured":"Wenhao Wu, Huanjin Yao, Mengxi Zhang, Yuxin Song, Wanli Ouyang, and Jingdong Wang. 2023. GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition? arXiv preprint arXiv:2311.15732 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00239"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450086"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681636","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681636"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":33,"alternative-id":["10.1145\/3664647.3681636","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681636","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}