{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T01:34:57Z","timestamp":1769823297014,"version":"3.49.0"},"reference-count":40,"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\/icassp48485.2024.10446193","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"3025-3029","source":"Crossref","is-referenced-by-count":3,"title":["WAVER: Writing-Style Agnostic Text-Video Retrieval Via Distilling Vision-Language Models Through Open-Vocabulary Knowledge"],"prefix":"10.1109","author":[{"given":"Huy","family":"Le","sequence":"first","affiliation":[{"name":"FPT Software AI Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tung","family":"Kieu","sequence":"additional","affiliation":[{"name":"RMIT University,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Liverpool,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngan","family":"Le","sequence":"additional","affiliation":[{"name":"University of Arkansas,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref2","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"ACL","author":"Chen"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref5","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref6","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li"},{"key":"ref7","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li"},{"key":"ref8","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"ICML","author":"Jia"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_17"},{"key":"ref11","article-title":"Simple open-vocabulary object detection with vision transformers","volume-title":"ECCV","author":"Minderer"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref15","article-title":"Clip2video: Mastering video-text retrieval via image CLIP","author":"Fang","year":"2021","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref19","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3589316"},{"key":"ref22","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref24","article-title":"Disentangled representation learning for text-video retrieval","author":"Wang","year":"2022","journal-title":"CoRR"},{"key":"ref25","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"CoRR"},{"key":"ref26","article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"BMVC","author":"Liu"},{"key":"ref27","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"ICLR","author":"Patrick"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref29","article-title":"Text-adaptive multiple visual prototype matching for video-text retrieval","author":"Lin","year":"2022","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01427"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00635"},{"key":"ref33","article-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss","author":"Cheng","year":"2021","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"ref36","article-title":"CLIP2TV: an empirical study on transformer-based methods for video-text retrieval","author":"Gao","year":"2021","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3227973"},{"key":"ref40","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS"}],"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\/10446193.pdf?arnumber=10446193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:43:56Z","timestamp":1722573836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446193","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}