{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:07:07Z","timestamp":1765310827368,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755103","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"7776-7784","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Beauty is Easy to Find: A Large-Scale Composition-Aware Dataset and an End-to-End Framework for Video Reframing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4840-3968","authenticated-orcid":false,"given":"Sitian","family":"Gu","sequence":"first","affiliation":[{"name":"School of AIA, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5584-6669","authenticated-orcid":false,"given":"Zhiyu","family":"Pan","sequence":"additional","affiliation":[{"name":"School of AIA, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1306-6634","authenticated-orcid":false,"given":"Chaoyi","family":"Hong","sequence":"additional","affiliation":[{"name":"School of AIA, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4050-6324","authenticated-orcid":false,"given":"Chengxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9223-1863","authenticated-orcid":false,"given":"Zhiguo","family":"Cao","sequence":"additional","affiliation":[{"name":"School of AIA, Huazhong University of Science and Technology, Wuhan, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506390"},{"key":"e_1_3_2_2_2_1","first-page":"6833","article-title":"Zechen Bai, Tong He, Haiyang Mei, Pichao Wang, Ziteng Gao, Joya Chen, Zheng Zhang, and Mike Zheng Shou. 2024. One Token to Seg Them All: Language, Instructed Reasoning Segmentation in Videos","volume":"37","year":"2024","unstructured":"024)]% baiOneTokenSeg2024 , Zechen Bai, Tong He, Haiyang Mei, Pichao Wang, Ziteng Gao, Joya Chen, Zheng Zhang, and Mike Zheng Shou. 2024. One Token to Seg Them All: Language, Instructed Reasoning Segmentation in Videos. Advances in Neural Information Processing Systems, Vol. 37 (2024), 6833-6859.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_3_1","volume-title":"Reframe Anything: Llm, Agent for Open World Video Reframing. arXiv preprint arXiv:2403.06070","author":"Cao Jiawang","year":"2024","unstructured":"Jiawang Cao, Yongliang Wu, Weiheng Chi, Wenbo Zhu, Ziyue Su, and Jay Wu. 2024. Reframe Anything: Llm, Agent for Open World Video Reframing. arXiv preprint arXiv:2403.06070 (2024). arXiv:2403.06070"},{"key":"e_1_3_2_2_4_1","volume-title":"A Visual Attention Model for Adapting Images on Small Displays. Multimedia systems","author":"Chen Li-Qun","year":"2003","unstructured":"Li-Qun Chen, Xing Xie, Xin Fan, Wei-Ying Ma, Hong-Jiang Zhang, and He-Qin Zhou. 2003. A Visual Attention Model for Adapting Images on Small Displays. Multimedia systems, Vol. 9 (2003), 353-364."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123274"},{"key":"e_1_3_2_2_6_1","volume-title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. arXiv preprint arXiv:1412.3555","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. arXiv preprint arXiv:1412.3555 (2014). arXiv:1412.3555"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1988.10478639"},{"key":"e_1_3_2_2_8_1","volume-title":"Trained Automatic Video Cropping. In 2008 IEEE Conference, on Computer Vision, and Pattern Recognition. IEEE, 1-8.","author":"Deselaers Thomas","year":"2008","unstructured":"Thomas Deselaers, Philippe Dreuw, and Hermann Ney. 2008. Pan, Zoom, Scan--Time-Coherent, Trained Automatic Video Cropping. In 2008 IEEE Conference, on Computer Vision, and Pattern Recognition. IEEE, 1-8."},{"key":"e_1_3_2_2_9_1","volume-title":"Mamba: Linear-time, Sequence Modeling with Selective State Spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time, Sequence Modeling with Selective State Spaces. arXiv preprint arXiv:2312.00752 (2023). arXiv:2312.00752"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2794262"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Chaoyi Hong Shuaiyuan Du Ke Xian Hao Lu Zhiguo Cao and Weicai Zhong. 2021. Composing Photos like a Photographer. In 2021 IEEE \/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 7053-7062.","DOI":"10.1109\/CVPR46437.2021.00698"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"volume-title":"Subjective Portrait Region Cropping On Landscape Video Study. In 2024 IEEE International Conference, on Image Processing (ICIP). 48-54","author":"Lee Cheng-Han","key":"e_1_3_2_2_13_1","unstructured":"Cheng-Han Lee, Maniratnam Mandal, Neil Birkbeck, Yilin Wang, Balu Adsumilli, and Alan C. Bovik. 2024. Subjective Portrait Region Cropping On Landscape Video Study. In 2024 IEEE International Conference, on Image Processing (ICIP). 48-54."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01270"},{"key":"e_1_3_2_2_15_1","unstructured":"Xinhao Li Yi Wang Jiashuo Yu Xiangyu Zeng Yuhan Zhu Haian Huang Jianfei Gao Kunchang Li Yinan He Chenting Wang Yu Qiao Yali Wang and Limin Wang. 2025. VideoChat-Flash : Hierarchical Compression for Long-Context Video Modeling. arXiv:2501.00574 [cs]"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01268"},{"key":"e_1_3_2_2_18_1","volume-title":"Decoupled Weight Decay Regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. arXiv preprint arXiv:1711.05101 (2017). arXiv:1711.05101"},{"key":"e_1_3_2_2_19_1","first-page":"4198","article-title":"TransView, : Inside, Outside, and Across, the Cropping View Boundaries. In 2021 IEEE, \/CVF International Conference, on Computer Vision (ICCV, ). IEEE, Montreal, QC","author":"Pan Zhiyu","year":"2021","unstructured":"Zhiyu Pan, Zhiguo Cao, Kewei Wang, Hao Lu, and Weicai Zhong. 2021. TransView, : Inside, Outside, and Across, the Cropping View Boundaries. In 2021 IEEE, \/CVF International Conference, on Computer Vision (ICCV, ). IEEE, Montreal, QC, Canada, 4198-4207.","journal-title":"Canada"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25293"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3377125"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1124772.1124886"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28303"},{"key":"e_1_3_2_2_24_1","volume-title":"Advances in neural information processing systems","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, Vol. 30 (2017)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00969"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.240"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00514"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"e_1_3_2_2_29_1","volume-title":"21st International Workshop on Multimedia Signal Processing (MMSP, ). IEEE, 1-5.","author":"Wang Yilin","year":"2019","unstructured":"Yilin Wang, Sasi Inguva, and Balu Adsumilli. 2019a. YouTube UGC, Dataset for Video Compression Research. In 2019 IEEE, 21st International Workshop on Multimedia Signal Processing (MMSP, ). IEEE, 1-5."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00570"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00102"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the IEEE, \/CVF, Conference on Computer Vision and Pattern Recognition. 14019-14029","author":"Ying Zhenqiang","year":"2021","unstructured":"Zhenqiang Ying, Maniratnam Mandal, Deepti Ghadiyaram, and Alan Bovik. 2021. Patch-vq:'patching up'the Video Quality Problem. In Proceedings of the IEEE, \/CVF, Conference on Computer Vision and Pattern Recognition. 14019-14029."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3024207"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP56404.2022.10008849"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3013350"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3092202"}],"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\/3746027.3755103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:03:53Z","timestamp":1765310633000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755103"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":38,"alternative-id":["10.1145\/3746027.3755103","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755103","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"}}]}}