{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:21:16Z","timestamp":1764400876819,"version":"3.46.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249307","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"1497-1502","source":"Crossref","is-referenced-by-count":0,"title":["Lyric-Aware Karaoke Background Video Selection Using Large Language Models and Moment Retrieval"],"prefix":"10.1109","author":[{"given":"Tomoki","family":"Ariga","sequence":"first","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Taniguchi","sequence":"additional","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yosuke","family":"Higuchi","sequence":"additional","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sayaka","family":"Toma","sequence":"additional","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunihiro","family":"Abe","sequence":"additional","affiliation":[{"name":"DAIICHIKOSHO CO., LTD.,Tokyo,JAPAN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rie","family":"Shigyo","sequence":"additional","affiliation":[{"name":"DAIICHIKOSHO CO., LTD.,Tokyo,JAPAN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuji","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref3","first-page":"11846","article-title":"QVHIGHLIGHTS: Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref5","first-page":"65948","article-title":"Momentdiff: Generative video moment retrieval from random to real","volume":"36","author":"Li","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250518"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02208"},{"key":"ref9","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1986"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"journal-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge","year":"2024","author":"Liu","key":"ref12"},{"journal-title":"LLaVA-NeXT: A strong zero-shot video understanding model","year":"2024","author":"Zhang","key":"ref13"},{"key":"ref14","article-title":"Charades-Ego: A large-scale dataset of paired third and first person videos","author":"Sigurdsson","year":"2018","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref19","article-title":"A technique for the measurement of attitudes","author":"Likert","year":"1932","journal-title":"Archives of Psychology"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF02310555"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249307.pdf?arnumber=11249307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:17:24Z","timestamp":1764400644000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249307","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}