{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:40:45Z","timestamp":1765309245077,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473307,62495084"],"award-info":[{"award-number":["62473307,62495084"]}],"id":[{"id":"10.13039\/501100001809","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\/3746027.3755701","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"4982-4991","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Image Captioning with Multimodal Guidance and Search Space Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2203-5422","authenticated-orcid":false,"given":"Yimou","family":"Guo","sequence":"first","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5741-5280","authenticated-orcid":false,"given":"Yaochen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3479-9871","authenticated-orcid":false,"given":"Jingze","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2780-9190","authenticated-orcid":false,"given":"Jiahui","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7172-3507","authenticated-orcid":false,"given":"Haoyi","family":"Lou","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8526-7124","authenticated-orcid":false,"given":"Zhimin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1673-7829","authenticated-orcid":false,"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7520-7020","authenticated-orcid":false,"given":"Yuanqi","family":"Su","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30080"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3202690"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00282"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01657"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_18"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19940"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681161"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00277"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107567"},{"key":"e_1_3_2_1_15_1","volume-title":"Image Captioning: Analyzing CNN-LSTM and Vision-GPT Models. In 2024 IEEE 9th International Conference for Convergence in Technology (I2CT). IEEE, 1-6.","author":"Karthik Abburi Sai","year":"2024","unstructured":"Abburi Sai Karthik, Maddala HSM Krishna Karthik, Samudrala Yashwanth, and T Anjali. 2024. Image Captioning: Analyzing CNN-LSTM and Vision-GPT Models. In 2024 IEEE 9th International Conference for Convergence in Technology (I2CT). IEEE, 1-6."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.254"},{"key":"e_1_3_2_1_17_1","volume-title":"HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, 11039-11049","author":"Kuo Chia-Wen","year":"2023","unstructured":"Chia-Wen Kuo and Zsolt Kira. 2023. HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, 11039-11049."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/151"},{"key":"e_1_3_2_1_19_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_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110941"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01278"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/InCACCT61598.2024.10551257"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"e_1_3_2_1_28_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_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00281"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00668"},{"key":"e_1_3_2_1_31_1","volume-title":"Memorial gan with joint semantic optimization for unpaired image captioning","author":"Song Peipei","year":"2022","unstructured":"Peipei Song, Dan Guo, Jinxing Zhou, Mingliang Xu, and Meng Wang. 2022. Memorial gan with joint semantic optimization for unpaired image captioning. IEEE transactions on cybernetics, Vol. 53, 7 (2022), 4388-4399."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26189"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01287"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00061"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 1353-1361","author":"Wang Bo","year":"2024","unstructured":"Bo Wang, Zhao Zhang, Mingbo Zhao, Xiaojie Jin, Mingliang Xu, and Meng Wang. 2024. OSIC: a new one-stage image captioner coined. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 1353-1361."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25359"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25360"},{"key":"e_1_3_2_1_39_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. 2022a. 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_40_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wen Yuxin","year":"2024","unstructured":"Yuxin Wen, Neel Jain, John Kirchenbauer, Micah Goldblum, Jonas Geiping, and Tom Goldstein. 2024. Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 32nd International Conference on International Conference on Machine Learning-Volume 37","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Lei Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard S Zemel, and Yoshua Bengio. 2015. Show, attend and tell: neural image caption generation with visual attention. In Proceedings of the 32nd International Conference on International Conference on Machine Learning-Volume 37. 2048-2057."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.157"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.559"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548024"},{"key":"e_1_3_2_1_48_1","volume-title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. In International Conference on Machine Learning. PMLR, 25994-26009","author":"Zeng Yan","year":"2022","unstructured":"Yan Zeng, Xinsong Zhang, and Hang Li. 2022a. Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. In International Conference on Machine Learning. PMLR, 25994-26009."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3528216"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755701","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:36:28Z","timestamp":1765308988000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755701"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":51,"alternative-id":["10.1145\/3746027.3755701","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755701","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"}}]}}