{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:59:22Z","timestamp":1783439962246,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":54,"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":[{"name":"Tencent PCG","award":["ZGG9-P0043883"],"award-info":[{"award-number":["ZGG9-P0043883"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612434","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"6653-6664","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Toward Human Perception-Centric Video Thumbnail Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6943-2907","authenticated-orcid":false,"given":"Tao","family":"Yang","sequence":"first","affiliation":[{"name":"Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7928-2723","authenticated-orcid":false,"given":"Fan","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8717-8351","authenticated-orcid":false,"given":"Junfan","family":"Lin","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University & Sun Yat-sen University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8298-4063","authenticated-orcid":false,"given":"Zhongang","family":"Qi","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8010-6857","authenticated-orcid":false,"given":"Yang","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7932-2654","authenticated-orcid":false,"given":"Jing","family":"Xu","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7673-8325","authenticated-orcid":false,"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-234X","authenticated-orcid":false,"given":"Changwen","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01343"},{"key":"e_1_3_2_1_2_1","volume-title":"An actor-critic algorithm for sequence prediction. arXiv preprint arXiv:1607.07086","author":"Bahdanau Dzmitry","year":"2016","unstructured":"Dzmitry Bahdanau, Philemon Brakel, Kelvin Xu, Anirudh Goyal, Ryan Lowe, Joelle Pineau, Aaron Courville, and Yoshua Bengio. 2016. An actor-critic algorithm for sequence prediction. arXiv preprint arXiv:1607.07086 (2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2006.01.002"},{"key":"e_1_3_2_1_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"e_1_3_2_1_6_1","volume-title":"Deep reinforcement learning from human preferences. Advances in neural information processing systems 30","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_7_1","volume-title":"International conference on machine learning. PMLR, 1126--1135","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic metalearning for fast adaptation of deep networks. In International conference on machine learning. PMLR, 1126--1135."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00104"},{"key":"e_1_3_2_1_9_1","volume-title":"Conference on Robot Learning. PMLR","author":"Dorsa Sadigh Donald Joseph","year":"2023","unstructured":"Donald Joseph Hejna III and Dorsa Sadigh. 2023. Few-shot preference learning for human-in-the-loop RL. In Conference on Robot Learning. PMLR, 2014--2025."},{"key":"e_1_3_2_1_10_1","unstructured":"Gary B. Huang Manu Ramesh Tamara Berg and Erik Learned-Miller. 2007. Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments. Technical Report 07--49. University of Massachusetts Amherst."},{"key":"e_1_3_2_1_11_1","volume-title":"Reward learning from human preferences and demonstrations in atari. Advances in neural information processing systems 31","author":"Ibarz Borja","year":"2018","unstructured":"Borja Ibarz, Jan Leike, Tobias Pohlen, Geoffrey Irving, Shane Legg, and Dario Amodei. 2018. Reward learning from human preferences and demonstrations in atari. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_12_1","volume-title":"LayoutDM: Discrete Diffusion Model for Controllable Layout Generation. arXiv preprint arXiv:2303.08137","author":"Inoue Naoto","year":"2023","unstructured":"Naoto Inoue, Kotaro Kikuchi, Edgar Simo-Serra, Mayu Otani, and Kota Yamaguchi. 2023. LayoutDM: Discrete Diffusion Model for Controllable Layout Generation. arXiv preprint arXiv:2303.08137 (2023)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19994"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747465"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 3404--3413","author":"Kazemi Hadi","year":"2020","unstructured":"Hadi Kazemi, Fariborz Taherkhani, and Nasser Nasrabadi. 2020. Preferencebased image generation. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 3404--3413."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475497"},{"key":"e_1_3_2_1_17_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_18_1","volume-title":"Tel Aviv","author":"Kong Xiang","year":"2022","unstructured":"Xiang Kong, Lu Jiang, Huiwen Chang, Han Zhang, Yuan Hao, Haifeng Gong, and Irfan Essa. 2022. BLT: bidirectional layout transformer for controllable layout generation. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XVII. Springer, 474--490."},{"key":"e_1_3_2_1_19_1","volume-title":"Can neural machine translation be improved with user feedback? arXiv preprint arXiv:1804.05958","author":"Kreutzer Julia","year":"2018","unstructured":"Julia Kreutzer, Shahram Khadivi, Evgeny Matusov, and Stefan Riezler. 2018. Can neural machine translation be improved with user feedback? arXiv preprint arXiv:1804.05958 (2018)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2009.08.008"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_29"},{"key":"e_1_3_2_1_22_1","volume-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training. arXiv preprint arXiv:2106.05091","author":"Lee Kimin","year":"2021","unstructured":"Kimin Lee, Laura Smith, and Pieter Abbeel. 2021. Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training. arXiv preprint arXiv:2106.05091 (2021)."},{"key":"e_1_3_2_1_23_1","volume-title":"NewsThumbnail: Automatic Generation of News Video Thumbnail. In 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE, 1383--1388","author":"Li Jinyu","year":"2022","unstructured":"Jinyu Li, Shujin Lin, Fan Zhou, and Ruomei Wang. 2022. NewsThumbnail: Automatic Generation of News Video Thumbnail. In 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE, 1383--1388."},{"key":"e_1_3_2_1_24_1","volume-title":"Layoutgan: Generating graphic layouts with wireframe discriminators. arXiv preprint arXiv:1901.06767","author":"Li Jianan","year":"2019","unstructured":"Jianan Li, Jimei Yang, Aaron Hertzmann, Jianming Zhang, and Tingfa Xu. 2019. Layoutgan: Generating graphic layouts with wireframe discriminators. arXiv preprint arXiv:1901.06767 (2019)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.2999335"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1367497.1367501"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532401"},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Machine Learning. PMLR, 2285--2294","author":"MacGlashan James","year":"2017","unstructured":"James MacGlashan, Mark K Ho, Robert Loftin, Bei Peng, Guan Wang, David L Roberts, Matthew E Taylor, and Michael L Littman. 2017. Interactive learning from policy-dependent human feedback. In International Conference on Machine Learning. PMLR, 2285--2294."},{"key":"e_1_3_2_1_30_1","volume-title":"ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Task. arXiv preprint arXiv:2304.14177","author":"Mart\u00ednez-Cruz Roberto","year":"2023","unstructured":"Roberto Mart\u00ednez-Cruz, Alvaro J L\u00f3pez-L\u00f3pez, and Jos\u00e9 Portela. 2023. ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Task. arXiv preprint arXiv:2304.14177 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2009.2039841"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459418"},{"key":"e_1_3_2_1_33_1","volume-title":"Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332","author":"Nakano Reiichiro","year":"2021","unstructured":"Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, et al. 2021. Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332 (2021)."},{"key":"e_1_3_2_1_34_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 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1509\/jmkg.68.2.36.27794"},{"key":"e_1_3_2_1_36_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_37_1","volume-title":"Genetic Algorithms Data Structures= Evolution programs (3rd. J. Amer. Statist. Assoc. 95, 449","author":"Rocke DM","year":"2000","unstructured":"DM Rocke. 2000. Genetic Algorithms Data Structures= Evolution programs (3rd. J. Amer. Statist. Assoc. 95, 449 (2000), 347."},{"key":"e_1_3_2_1_38_1","volume-title":"Is ChatGPT A Good Keyphrase Generator? A Preliminary Study. arXiv preprint arXiv:2303.13001","author":"Song Mingyang","year":"2023","unstructured":"Mingyang Song, Haiyun Jiang, Shuming Shi, Songfang Yao, Shilong Lu, Yi Feng, Huafeng Liu, and Liping Jing. 2023. Is ChatGPT A Good Keyphrase Generator? A Preliminary Study. arXiv preprint arXiv:2303.13001 (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1519008"},{"key":"e_1_3_2_1_40_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_41_1","volume-title":"Unified Perceptual Parsing for Scene Understanding. In European Conference on Computer Vision. Springer.","author":"Xiao Tete","year":"2018","unstructured":"Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, and Jian Sun. 2018. Unified Perceptual Parsing for Scene Understanding. In European Conference on Computer Vision. Springer."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103382"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16416"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00543"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818709"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502116"},{"key":"e_1_3_2_1_47_1","volume-title":"Caiming Xiong, and Ran Xu.","author":"Yu Ning","year":"2022","unstructured":"Ning Yu, Chia-Chih Chen, Zeyuan Chen, Rui Meng, Gang Wu, Paul Josel, Juan Carlos Niebles, Caiming Xiong, and Ran Xu. 2022. LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer. arXiv preprint arXiv:2212.09877 (2022)."},{"key":"e_1_3_2_1_48_1","volume-title":"LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models. arXiv preprint arXiv:2303.11589","author":"Zhang Junyi","year":"2023","unstructured":"Junyi Zhang, Jiaqi Guo, Shizhao Sun, Jian-Guang Lou, and Dongmei Zhang. 2023. LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models. arXiv preprint arXiv:2303.11589 (2023)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126718"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDH51081.2020.00050"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Baoquan Zhao Shujin Lin Xin Qi Zhiquan Zhang Xiaonan Luo and Ruomei Wang. 2017. Automatic generation of visual-textual web video thumbnail. In SIGGRAPH Asia 2017 Posters. 1--2.","DOI":"10.1145\/3145690.3145712"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00320"},{"key":"e_1_3_2_1_53_1","volume-title":"Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs. arXiv preprint arXiv:2205.00303","author":"Zhou Min","year":"2022","unstructured":"Min Zhou, Chenchen Xu, Ye Ma, Tiezheng Ge, Yuning Jiang, and Weiwei Xu. 2022. Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs. arXiv preprint arXiv:2205.00303 (2022)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6521"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612434","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:05:34Z","timestamp":1755821134000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612434"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":54,"alternative-id":["10.1145\/3581783.3612434","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612434","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"}}]}}