{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:15:48Z","timestamp":1784178948768,"version":"3.55.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3236837","type":"journal-article","created":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T17:30:09Z","timestamp":1681493409000},"page":"8383-8395","source":"Crossref","is-referenced-by-count":39,"title":["Dynamic Contrastive Distillation for Image-Text Retrieval"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5804-1508","authenticated-orcid":false,"given":"Jun","family":"Rao","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8976-2084","authenticated-orcid":false,"given":"Liang","family":"Ding","sequence":"additional","affiliation":[{"name":"JD Explore Academy at JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6903-145X","authenticated-orcid":false,"given":"Shuhan","family":"Qi","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology Shenzhen, Peng Cheng Laboratory, and Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Fang","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2486-5765","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"JD Explore Academy at JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5979-578X","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"JD Explore Academy at JD.com, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01838"},{"key":"ref2","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2655422"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3044473"},{"key":"ref5","first-page":"1","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2022"},{"key":"ref6","first-page":"1","article-title":"Coarse-to-fine vision-language pre-training with fusion in the backbone","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dou","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2912714"},{"key":"ref8","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Zeng","year":"2022"},{"key":"ref9","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref13","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref14","first-page":"21271","article-title":"Bootstrap your own latent - A new approach to self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Grill","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref16","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hinton","year":"2015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298868"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00143"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"ref22","first-page":"1","article-title":"Understanding and improving lexical choice in non-autoregressive translation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ding","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.172"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref26","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref27","first-page":"1","article-title":"VSE++ : Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref29","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2558463"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531715"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref38","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Devlin","year":"2019"},{"key":"ref39","article-title":"Distilbert, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3321480"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5314"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.iwslt-1.22"},{"key":"ref44","first-page":"1","article-title":"Vega-MT: The JD explore academy translation system for WMT22","volume-title":"Proc. WMTed EMNLP","author":"Zan","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00146"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482194"},{"key":"ref47","article-title":"Zero-shot detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.31"},{"key":"ref49","first-page":"1","article-title":"Learning efficient detector with semi-supervised adaptive distillation","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Tang","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_39"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1063"},{"key":"ref52","article-title":"Panda: Prompt transfer meets knowledge distillation for efficient model adaptation","author":"Zhong","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref54","first-page":"1849","article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2016"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018577"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref59","article-title":"A contrastive cross-channel data augmentation framework for aspect-based sentiment analysis","author":"Wang","year":"2022"},{"key":"ref60","article-title":"E2s2: Encoding-enhanced sequence-to-sequence pretraining for language understanding and generation","author":"Zhong","year":"2022"},{"key":"ref61","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Gutmann","year":"2010"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/362"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_14"},{"key":"ref64","first-page":"1","article-title":"Contrastive learning with hard negative samples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Robinson","year":"2021"},{"key":"ref65","article-title":"Active learning literature survey","volume-title":"Univ. WisconsinMadison, Madison","author":"Settles","year":"2009"},{"key":"ref66","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gal","year":"2016"},{"key":"ref67","first-page":"6405","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lakshminarayanan","year":"2017"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.60"},{"key":"ref72","first-page":"1","article-title":"Rethinking soft labels for knowledge distillation: A bias-variance tradeoff perspective","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2021"},{"key":"ref73","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10102558.pdf?arnumber=10102558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:22:36Z","timestamp":1705018956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10102558\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3236837","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}