{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:25:53Z","timestamp":1776889553977,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448486","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7300-7304","source":"Crossref","is-referenced-by-count":6,"title":["A Sound Approach: Using Large Language Models to Generate Audio Descriptions for Egocentric Text-Audio Retrieval"],"prefix":"10.1109","author":[{"given":"Andreea-Maria","family":"Oncescu","sequence":"first","affiliation":[{"name":"University of Oxford"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jo\u00e3o F.","family":"Henriques","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Albanie","sequence":"additional","affiliation":[{"name":"University of Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. Sophia","family":"Koepke","sequence":"additional","affiliation":[{"name":"University of Tübingen"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Chatgpt"},{"key":"ref2","article-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron","year":"2023"},{"key":"ref3","article-title":"A short note on the kinetics-700-2020 human action dataset","author":"Smaira","year":"2020"},{"key":"ref4","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"Proc. NACCL","author":"Kim"},{"key":"ref5","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"Damen","year":"2018","journal-title":"ECCV"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2227"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149712"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1004822"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tuffc.2012.2167\/mm1"},{"key":"ref12","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref13","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref14","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref15","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface","author":"Shen","year":"2023"},{"key":"ref16","article-title":"Multi-modal classifiers for open-vocabulary object detection","author":"Kaul","year":"2023","journal-title":"ICML"},{"key":"ref17","article-title":"Visual classification via description from large language models","author":"Menon","year":"2023","journal-title":"ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref19","article-title":"Learning state-aware visual representations from audible interactions","author":"Mittal","year":"2022","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00024"},{"key":"ref21","article-title":"Egocentric videolanguage pretraining","author":"Lin","year":"2022","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02209"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00487"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096198"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448486.pdf?arnumber=10448486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:54:36Z","timestamp":1722660876000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448486\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448486","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}