{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T03:34:16Z","timestamp":1764646456517,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2043, 62102419, 62102416"],"award-info":[{"award-number":["U21B2043, 62102419, 62102416"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["No. 2020AAA0106400"],"award-info":[{"award-number":["No. 2020AAA0106400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612388","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"5120-5131","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8947-7053","authenticated-orcid":false,"given":"Zikang","family":"Liu","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3539-8085","authenticated-orcid":false,"given":"Sihan","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4340-4000","authenticated-orcid":false,"given":"Longteng","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2473-2561","authenticated-orcid":false,"given":"Handong","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5396-6253","authenticated-orcid":false,"given":"Xingjian","family":"He","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0903-9131","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.164"},{"key":"e_1_3_2_1_2_1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 23716--23736.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"e_1_3_2_1_5_1","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais Khan Mohammed, Kriti Aggarwal, Subhojit Som, Songhao Piao, and Furu Wei. 2022. Vlmo: Unified vision-language pre-training with mixture-of-modality-experts. Advances in Neural Information Processing Systems, Vol. 35 (2022), 32897--32912.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.142"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"e_1_3_2_1_8_1","volume-title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset. arXiv preprint arXiv:2304.08345","author":"Chen Sihan","year":"2023","unstructured":"Sihan Chen, Xingjian He, Longteng Guo, Xinxin Zhu, Weining Wang, Jinhui Tang, and Jing Liu. 2023. VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset. arXiv preprint arXiv:2304.08345 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325","author":"Chen Xinlei","year":"2015","unstructured":"Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2015. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)."},{"key":"e_1_3_2_1_10_1","volume-title":"UK","author":"Chen Yen-Chun","year":"2020","unstructured":"Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu. 2020. Uniter: Universal image-text representation learning. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXX. Springer, 104--120."},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Cho Jaemin","year":"2021","unstructured":"Jaemin Cho, Jie Lei, Hao Tan, and Mohit Bansal. 2021. Unifying vision-and-language tasks via text generation. In International Conference on Machine Learning. PMLR, 1931--1942."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"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 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_14_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 17980--17989","author":"Hu Xiaowei","year":"2022","unstructured":"Xiaowei Hu, Zhe Gan, Jianfeng Wang, Zhengyuan Yang, Zicheng Liu, Yumao Lu, and Lijuan Wang. 2022. Scaling up vision-language pre-training for image captioning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 17980--17989."},{"key":"e_1_3_2_1_15_1","volume-title":"Pixel-bert: Aligning image pixels with text by deep multi-modal transformers. arXiv preprint arXiv:2004.00849","author":"Huang Zhicheng","year":"2020","unstructured":"Zhicheng Huang, Zhaoyang Zeng, Bei Liu, Dongmei Fu, and Jianlong Fu. 2020. Pixel-bert: Aligning image pixels with text by deep multi-modal transformers. arXiv preprint arXiv:2004.00849 (2020)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_1_17_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_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3529"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of NAACL-HLT. 4171--4186","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.512"},{"key":"e_1_3_2_1_23_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 Vol. 123 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Hao Li Jinguo Zhu Xiaohu Jiang Xizhou Zhu Hongsheng Li Chun Yuan Xiaohua Wang Yu Qiao Xiaogang Wang Wenhai Wang et al. 2022c. Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks. arXiv preprint arXiv:2211.09808 (2022).","DOI":"10.1109\/CVPR52729.2023.00264"},{"key":"e_1_3_2_1_25_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"International Conference on Machine Learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022b. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_27_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, Vol. 34 (2021), 9694--9705."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018650"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00640"},{"key":"e_1_3_2_1_30_1","volume-title":"Scaling Language-Image Pre-training via Masking. arXiv preprint arXiv:2212.00794","author":"Li Yanghao","year":"2022","unstructured":"Yanghao Li, Haoqi Fan, Ronghang Hu, Christoph Feichtenhofer, and Kaiming He. 2022a. Scaling Language-Image Pre-training via Masking. arXiv preprint arXiv:2212.00794 (2022)."},{"volume-title":"InEuropean conference on computer vision 2014 Sep 6 (pp. 740--755)","author":"Lin TY","key":"e_1_3_2_1_31_1","unstructured":"TY Lin, M Maire, S Belongie, J Hays, P Perona, D Ramanan, P Doll\u00e1r, CL Zitnick, et al. [n.,d.]. Microsoft coco: Common objects in context. InEuropean conference on computer vision 2014 Sep 6 (pp. 740--755)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_33_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_34_1","volume-title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge. In Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Marino Kenneth","year":"2019","unstructured":"Kenneth Marino, Mohammad Rastegari, Ali Farhadi, and Roozbeh Mottaghi. 2019. OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1170"},{"key":"e_1_3_2_1_36_1","volume-title":"Im2text: Describing images using 1 million captioned photographs. Advances in neural information processing systems","author":"Ordonez Vicente","year":"2011","unstructured":"Vicente Ordonez, Girish Kulkarni, and Tamara Berg. 2011. Im2text: Describing images using 1 million captioned photographs. Advances in neural information processing systems, Vol. 24 (2011)."},{"key":"e_1_3_2_1_37_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, Vol. 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","volume-title":"Minh-Thang Luong, Mingxing Tan, and Quoc V Le.","author":"Pham Hieu","year":"2021","unstructured":"Hieu Pham, Zihang Dai, Golnaz Ghiasi, Hanxiao Liu, Adams Wei Yu, Minh-Thang Luong, Mingxing Tan, and Quoc V Le. 2021. Combined scaling for zero-shot transfer learning. arXiv preprint arXiv:2111.10050 (2021)."},{"key":"e_1_3_2_1_39_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_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"e_1_3_2_1_41_1","volume-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114","author":"Schuhmann Christoph","year":"2021","unstructured":"Christoph Schuhmann, Richard Vencu, Romain Beaumont, Robert Kaczmarczyk, Clayton Mullis, Aarush Katta, Theo Coombes, Jenia Jitsev, and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00681"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152990"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_48_1","volume-title":"Git: A generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100","author":"Wang Jianfeng","year":"2022","unstructured":"Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu, Linjie Li, Kevin Lin, Zhe Gan, Zicheng Liu, Ce Liu, and Lijuan Wang. 2022b. Git: A generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100 (2022)."},{"key":"e_1_3_2_1_49_1","volume-title":"International Conference on Machine Learning. PMLR, 23318--23340","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022c. Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In International Conference on Machine Learning. PMLR, 23318--23340."},{"key":"e_1_3_2_1_50_1","volume-title":"Saksham Singhal, Subhojit Som, et al.","author":"Wang Wenhui","year":"2022","unstructured":"Wenhui Wang, Hangbo Bao, Li Dong, Johan Bjorck, Zhiliang Peng, Qiang Liu, Kriti Aggarwal, Owais Khan Mohammed, Saksham Singhal, Subhojit Som, et al. 2022a. Image as a foreign language: Beit pretraining for all vision and vision-language tasks. arXiv preprint arXiv:2208.10442 (2022)."},{"key":"e_1_3_2_1_51_1","volume-title":"Zihang Dai, Yulia Tsvetkov, and Yuan Cao.","author":"Wang Zirui","year":"2021","unstructured":"Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, and Yuan Cao. 2021. Simvlm: Simple visual language model pretraining with weak supervision. arXiv preprint arXiv:2108.10904 (2021)."},{"key":"e_1_3_2_1_52_1","volume-title":"GRiT: A Generative Region-to-text Transformer for Object Understanding. arXiv preprint arXiv:2212.00280","author":"Wu Jialian","year":"2022","unstructured":"Jialian Wu, Jianfeng Wang, Zhengyuan Yang, Zhe Gan, Zicheng Liu, Junsong Yuan, and Lijuan Wang. 2022. GRiT: A Generative Region-to-text Transformer for Object Understanding. arXiv preprint arXiv:2212.00280 (2022)."},{"key":"e_1_3_2_1_53_1","volume-title":"Radial graph convolutional network for visual question generation","author":"Xu Xing","year":"2020","unstructured":"Xing Xu, Tan Wang, Yang Yang, Alan Hanjalic, and Heng Tao Shen. 2020. Radial graph convolutional network for visual question generation. IEEE transactions on neural networks and learning systems, Vol. 32, 4 (2020), 1654--1667."},{"key":"e_1_3_2_1_54_1","volume-title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions. In International Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Xue Hongwei","year":"2022","unstructured":"Hongwei Xue, Tiankai Hang, Yanhong Zeng, Yuchong Sun, Bei Liu, Huan Yang, Jianlong Fu, and Baining Guo. 2022. Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions. In International Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.214"},{"volume-title":"FILIP: Fine-grained Interactive Language-Image Pre-Training. In International Conference on Learning Representations.","author":"Yao Lewei","key":"e_1_3_2_1_56_1","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. [n.,d.]. FILIP: Fine-grained Interactive Language-Image Pre-Training. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00640"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_59_1","volume-title":"Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)."},{"key":"e_1_3_2_1_60_1","volume-title":"Florence: A new foundation model for computer vision. arXiv preprint arXiv:2111.11432","author":"Yuan Lu","year":"2021","unstructured":"Lu Yuan, Dongdong Chen, Yi-Ling Chen, Noel Codella, Xiyang Dai, Jianfeng Gao, Houdong Hu, Xuedong Huang, Boxin Li, Chunyuan Li, et al. 2021. Florence: A new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612388","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:55:17Z","timestamp":1755820517000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612388"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":61,"alternative-id":["10.1145\/3581783.3612388","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612388","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}