{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:16:15Z","timestamp":1750220175249,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3552365","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"7220-7222","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Overview of the Multimedia Grand Challenges 2022"],"prefix":"10.1145","author":[{"given":"Miriam","family":"Redi","sequence":"first","affiliation":[{"name":"King's College London, San Francisco, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georges","family":"Quenot","sequence":"additional","affiliation":[{"name":"Univ. Grenoble Alpes, Grenoble, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458305.3479968"},{"key":"e_1_3_2_1_2_1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski , Yuhao Zhou , Abdelrahman Mohamed , and Michael Auli . 2020 . wav2vec 2.0: A framework for self-supervised learning of speech representations . Advances in Neural Information Processing Systems , Vol. 33 (2020), 12449 -- 12460 . Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems, Vol. 33 (2020), 12449--12460.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356072"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416275"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356062"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356054"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356064"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3266443"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3417332"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3266439"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416273"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3266438"},{"key":"e_1_3_2_1_13_1","volume-title":"Auto-captions on GIF: A Large-scale Video-sentence Dataset for Vision-language Pre-training. arXiv preprint arXiv:2007.02375","author":"Pan Yingwei","year":"2020","unstructured":"Yingwei Pan , Yehao Li , Jianjie Luo , Jun Xu , Ting Yao , and Tao Mei . 2020. Auto-captions on GIF: A Large-scale Video-sentence Dataset for Vision-language Pre-training. arXiv preprint arXiv:2007.02375 ( 2020 ). Yingwei Pan, Yehao Li, Jianjie Luo, Jun Xu, Ting Yao, and Tao Mei. 2020. Auto-captions on GIF: A Large-scale Video-sentence Dataset for Vision-language Pre-training. arXiv preprint arXiv:2007.02375 (2020)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416294"},{"key":"e_1_3_2_1_15_1","volume-title":"Towards Real-World Blind Face Restoration with Generative Facial Prior. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Wang Xintao","year":"2021","unstructured":"Xintao Wang , Yu Li , Honglun Zhang , and Ying Shan . 2021 . Towards Real-World Blind Face Restoration with Generative Facial Prior. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Xintao Wang, Yu Li, Honglun Zhang, and Ying Shan. 2021. Towards Real-World Blind Face Restoration with Generative Facial Prior. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356084"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964335"},{"key":"e_1_3_2_1_18_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). 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_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9970"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416274"},{"key":"e_1_3_2_1_21_1","volume-title":"Responsive Listening Head Generation: A Benchmark Dataset and Baseline. arXiv preprint arXiv:2112.13548","author":"Zhou Mohan","year":"2021","unstructured":"Mohan Zhou , Yalong Bai , Wei Zhang , Tiejun Zhao , and Tao Mei . 2021. Responsive Listening Head Generation: A Benchmark Dataset and Baseline. arXiv preprint arXiv:2112.13548 ( 2021 ). Mohan Zhou, Yalong Bai, Wei Zhang, Tiejun Zhao, and Tao Mei. 2021. Responsive Listening Head Generation: A Benchmark Dataset and Baseline. arXiv preprint arXiv:2112.13548 (2021)."}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Lisboa Portugal","acronym":"MM '22"},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3552365","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3552365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:48Z","timestamp":1750186848000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3552365"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":21,"alternative-id":["10.1145\/3503161.3552365","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3552365","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}