{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:09:45Z","timestamp":1765544985870,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":37,"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"}],"funder":[{"name":"National science and technology council","award":["112-2221-E-006 -157 -MY3"],"award-info":[{"award-number":["112-2221-E-006 -157 -MY3"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3689000","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"11464-11469","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Revisiting Vision-Language Features Adaptation and Inconsistency for Social Media Popularity Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2083-4438","authenticated-orcid":false,"given":"Chih-Chung","family":"Hsu","sequence":"first","affiliation":[{"name":"Institute of Data Science, National Cheng Kung University, Tainan, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6027-3083","authenticated-orcid":false,"given":"Chia-Ming","family":"Lee","sequence":"additional","affiliation":[{"name":"Institute of Data Science, National Cheng Kung University, Tainan, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9459-701X","authenticated-orcid":false,"given":"Yu-Fan","family":"Lin","sequence":"additional","affiliation":[{"name":"Institute of Data Science, National Cheng Kung University, Tainan, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4741-6115","authenticated-orcid":false,"given":"Yi-Shiuan","family":"Chou","sequence":"additional","affiliation":[{"name":"Institute of Data Science, National Cheng Kung University, Tainan, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6014-5154","authenticated-orcid":false,"given":"Chih-Yu","family":"Jian","sequence":"additional","affiliation":[{"name":"Institute of Data Science, National Cheng Kung University, Tainan, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8298-3230","authenticated-orcid":false,"given":"Chi-Han","family":"Tsai","sequence":"additional","affiliation":[{"name":"Institute of Data Science, National Cheng Kung University, Tainan, Taiwan"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"e_1_3_2_1_4_1","volume-title":"Progressive Feature Alignment for Unsupervised Domain Adaptation. arxiv","author":"Chen Chaoqi","year":"1811","unstructured":"Chaoqi Chen, Weiping Xie, Wenbing Huang, Yu Rong, Xinghao Ding, Yue Huang, Tingyang Xu, and Junzhou Huang. 2019. Progressive Feature Alignment for Unsupervised Domain Adaptation. arxiv: 1811.08585"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_6_1","volume-title":"A Simple Framework for Contrastive Learning of Visual Representations. arxiv","author":"Chen Ting","year":"2002","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. arxiv: 2002.05709"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551568"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612845"},{"key":"e_1_3_2_1_9_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arxiv: 2305.06500 [cs.CV]"},{"key":"e_1_3_2_1_10_1","unstructured":"Peng Gao Shijie Geng Renrui Zhang Teli Ma Rongyao Fang Yongfeng Zhang Hongsheng Li and Yu Qiao. 2021. CLIP-Adapter: Better Vision-Language Models with Feature Adapters. arxiv: 2110.04544 [cs.CV]"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijin.2022.08.005"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/jtaer19010024"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356064"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612843"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3266443"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127894"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551593"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3417332"},{"key":"e_1_3_2_1_19_1","volume-title":"Lightgbm: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems. 3146--3154.","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems. 3146--3154."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416273"},{"key":"e_1_3_2_1_21_1","volume-title":"Shafiq Joty, Caiming Xiong, and Steven Hoi.","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath R. Selvaraju, Akhilesh Deepak Gotmare, Shafiq Joty, Caiming Xiong, and Steven Hoi. 2021. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. arxiv: 2107.07651"},{"key":"e_1_3_2_1_22_1","first-page":"18","article-title":"Classification and regression by randomForest","volume":"2","author":"Liaw Andy","year":"2002","unstructured":"Andy Liaw, Matthew Wiener, et al. 2002. Classification and regression by randomForest. R News, Vol. 2, 3 (2002), 18--22.","journal-title":"R News"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3107411.3110413"},{"key":"e_1_3_2_1_24_1","volume-title":"Anna Veronika Dorogush, and Andrey Gulin","author":"Prokhorenkova Liudmila","year":"2018","unstructured":"Liudmila Prokhorenkova, Gleb Gusev, Aleksandr Vorobev, Anna Veronika Dorogush, and Andrey Gulin. 2018. CatBoost: unbiased boosting with categorical features. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_25_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","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. arXiv:2103.00020 [cs.CV] (2021)."},{"key":"e_1_3_2_1_26_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019)."},{"key":"e_1_3_2_1_27_1","volume-title":"Breslin","author":"Ruder Sebastian","year":"2017","unstructured":"Sebastian Ruder, Parsa Ghaffari, and John G. Breslin. 2017. Knowledge Adaptation: Teaching to Adapt. arxiv: 1702.02052"},{"key":"e_1_3_2_1_28_1","volume-title":"TabNet: Attentive Interpretable Tabular Learning. arXiv:1908.07442","author":"Arik Tomas Pfister","year":"2019","unstructured":"Tomas Pfister Sercan O. Arik. 2019. TabNet: Attentive Interpretable Tabular Learning. arXiv:1908.07442 (2019)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551607"},{"key":"e_1_3_2_1_30_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","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_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356084"},{"key":"e_1_3_2_1_32_1","volume-title":"Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks. In International Joint Conference on Artificial Intelligence (IJCAI)","author":"Wu Bo","year":"2017","unstructured":"Bo Wu, Wen-Huang Cheng, Yongdong Zhang, Huang Qiushi, Li Jintao, and Tao Mei. 2017. Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks. In International Joint Conference on Artificial Intelligence (IJCAI) (Melbourne, Australia)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613853"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9970"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551576"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-1694(01)00594-7"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Zhizhen Zhang Xiaohui Xie Mengyu Yang Ye Tian Yong Jiang and Yong Cui. 2023. Improving Social Media Popularity Prediction with Multiple Post Dependencies. arxiv: 2307.15413 [cs.MM]","DOI":"10.21203\/rs.3.rs-4267015\/v1"}],"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\/3664647.3689000","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3689000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:29Z","timestamp":1750295849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3689000"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":37,"alternative-id":["10.1145\/3664647.3689000","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3689000","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"}}]}}