{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T20:05:33Z","timestamp":1773864333787,"version":"3.50.1"},"publisher-location":"Stroudsburg, PA, USA","reference-count":0,"publisher":"Association for Computational Linguistics","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.18653\/v1\/p19-1564","type":"proceedings-article","created":{"date-parts":[[2019,9,12]],"date-time":"2019-09-12T14:39:56Z","timestamp":1568299196000},"page":"5612-5623","source":"Crossref","is-referenced-by-count":53,"title":["Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems"],"prefix":"10.18653","author":[{"given":"Hung","family":"Le","sequence":"first","affiliation":[]},{"given":"Doyen","family":"Sahoo","sequence":"additional","affiliation":[]},{"given":"Nancy","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Steven","family":"Hoi","sequence":"additional","affiliation":[]}],"member":"1643","event":{"name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","location":"Florence, Italy","start":{"date-parts":[[2019,7]]},"end":{"date-parts":[[2019,7]]}},"container-title":["Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics"],"original-title":[],"deposited":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T21:53:14Z","timestamp":1769896394000},"score":1,"resource":{"primary":{"URL":"https:\/\/aclanthology.org\/P19-1564"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":0,"URL":"https:\/\/doi.org\/10.18653\/v1\/p19-1564","relation":{},"subject":[],"published":{"date-parts":[[2019]]}}}