{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T16:28:33Z","timestamp":1788625713315,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,12,13]],"date-time":"2022-12-13T00:00:00Z","timestamp":1670889600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["110-2634-F-006-022, 110-2221-E-006-127-MY3, 108-2221-E-006-227-MY3, 107-2923-E-006 -009 -MY3"],"award-info":[{"award-number":["110-2634-F-006-022, 110-2221-E-006-127-MY3, 108-2221-E-006-227-MY3, 107-2923-E-006 -009 -MY3"]}],"id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,12,13]]},"DOI":"10.1145\/3551626.3564960","type":"proceedings-article","created":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T00:55:45Z","timestamp":1670374545000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Multimodal Fusion with Cross-Modal Attention for Action Recognition in Still Images"],"prefix":"10.1145","author":[{"given":"Jia-Hua","family":"Tsai","sequence":"first","affiliation":[{"name":"National Cheng Kung University, Taiwan, Tainan, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Ta","family":"Chu","sequence":"additional","affiliation":[{"name":"National Cheng Kung University, Taiwan, Tainan, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,12,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_12"},{"key":"e_1_3_2_1_3_1","volume-title":"Chris Williams, John Winn, and Andrew Zisserman.","author":"Everingham Mark","year":"2012","unstructured":"Mark Everingham , Luc Van Gool , Chris Williams, John Winn, and Andrew Zisserman. 2012 . The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results . http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html. Mark Everingham, Luc Van Gool, Chris Williams, John Winn, and Andrew Zisserman. 2012. The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of IEEE International Conference on Computer Vision.","author":"Fang Hao-Shu","year":"2017","unstructured":"Hao-Shu Fang , Shuqin Xie , Yu-Wing Tai , and Cewu Lu . 2017 . RMPE: Regional Multi-Person Pose Estimation . In Proceedings of IEEE International Conference on Computer Vision. Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, and Cewu Lu. 2017. RMPE: Regional Multi-Person Pose Estimation. In Proceedings of IEEE International Conference on Computer Vision."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.284"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.129"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of British Machine Vision Conference.","author":"Iashin Vladimir","year":"2020","unstructured":"Vladimir Iashin and Esa Rahtu . 2020 . A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer . In Proceedings of British Machine Vision Conference. Vladimir Iashin and Esa Rahtu. 2020. A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer. In Proceedings of British Machine Vision Conference."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01330"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of Neural Information Processing Systems.","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017 . Attention is All you Need . In Proceedings of Neural Information Processing Systems. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Proceedings of Neural Information Processing Systems."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_13"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2605305"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2016.08.020"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.367"}],"event":{"name":"MMAsia '22: ACM Multimedia Asia","location":"Tokyo Japan","acronym":"MMAsia '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 4th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3551626.3564960","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3551626.3564960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:26Z","timestamp":1750186826000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3551626.3564960"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,13]]},"references-count":15,"alternative-id":["10.1145\/3551626.3564960","10.1145\/3551626"],"URL":"https:\/\/doi.org\/10.1145\/3551626.3564960","relation":{},"subject":[],"published":{"date-parts":[[2022,12,13]]},"assertion":[{"value":"2022-12-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}