{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:20:55Z","timestamp":1725808855541},"reference-count":22,"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\/icassp48485.2024.10447148","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11446-11450","source":"Crossref","is-referenced-by-count":0,"title":["Cooking-Clip: Context-Aware Language-Image Pretraining for Zero-Shot Recipe Generation"],"prefix":"10.1109","author":[{"given":"Lin","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haithm M.","family":"Al-Gunid","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ammar","family":"Hawbani","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Xiong","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,School of Computer Science and Technology,Hefei,China,230027"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1166"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3258628"},{"article-title":"Malm: Mask augmentation based local matching for food-recipe retrieval","year":"2023","author":"Voutharoja","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00276"},{"article-title":"Vast: A vision-audio-subtitle-text omni-modality foundation model and dataset","year":"2023","author":"Chen","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"article-title":"Multimodal procedural planning via dual text-image prompting","year":"2023","author":"Lu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref13","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"article-title":"Bertscore: Evaluating text generation with bert","volume-title":"International Conference on Learning Representations","author":"Zhang","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01234"},{"article-title":"Decap: Decoding CLIP latents for zero-shot captioning via text-only training","volume-title":"The Eleventh International Conference on Learning Representations","author":"Li","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00356"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10447148.pdf?arnumber=10447148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:30:51Z","timestamp":1722576651000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447148\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447148","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}