{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T02:07:03Z","timestamp":1769825223368,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094821","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video Retrieval"],"prefix":"10.1109","author":[{"given":"Andrew","family":"Rouditchenko","sequence":"first","affiliation":[{"name":"MIT"}]},{"given":"Yung-Sung","family":"Chuang","sequence":"additional","affiliation":[{"name":"MIT"}]},{"given":"Nina","family":"Shvetsova","sequence":"additional","affiliation":[{"name":"Goethe University Frankfurt"}]},{"given":"Samuel","family":"Thomas","sequence":"additional","affiliation":[{"name":"IBM Research AI"}]},{"given":"Rogerio","family":"Feris","sequence":"additional","affiliation":[{"name":"IBM Research AI"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[{"name":"IBM Research AI"}]},{"given":"Leonid","family":"Karlinsky","sequence":"additional","affiliation":[{"name":"IBM Research AI"}]},{"given":"David","family":"Harwath","sequence":"additional","affiliation":[{"name":"UT Austin"}]},{"given":"Hilde","family":"Kuehne","sequence":"additional","affiliation":[{"name":"Goethe University Frankfurt"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[{"name":"MIT"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2018.8547629"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.195"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479913"},{"key":"ref4","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.62"},{"issue":"7","key":"ref9","article-title":"Distilling the knowledge in a neural network","volume-title":"NIPS Deep Learning Workshop","volume":"2","author":"Hinton"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref13","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Gutmann"},{"key":"ref14","article-title":"Exploring the limits of language modeling","author":"Jozefowicz","year":"2016"},{"key":"ref15","article-title":"Representation learning with contrastive predictive coding","author":"den Oord","year":"2018"},{"key":"ref16","article-title":"Learning video representations using contrastive bidirectional transformer","author":"Sun","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1312"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref20","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref22","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094821.pdf?arnumber=10094821","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:21:34Z","timestamp":1705026094000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094821\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094821","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}