{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T16:40:31Z","timestamp":1774975231641,"version":"3.50.1"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Grants Council of the Hong Kong Special Administrative Region","award":["CityU 11212518"],"award-info":[{"award-number":["CityU 11212518"]}]},{"name":"Research Grants Council of the Hong Kong Special Administrative Region","award":["CityU 11215820"],"award-info":[{"award-number":["CityU 11215820"]}]},{"name":"City University of Hong Kong Strategic Research","award":["7005218"],"award-info":[{"award-number":["7005218"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,2,1]]},"DOI":"10.1109\/tpami.2022.3159811","type":"journal-article","created":{"date-parts":[[2022,3,16]],"date-time":"2022-03-16T19:45:43Z","timestamp":1647459943000},"page":"2088-2103","source":"Crossref","is-referenced-by-count":25,"title":["On Distinctive Image Captioning via Comparing and Reweighting"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6113-0066","authenticated-orcid":false,"given":"Jiuniu","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1425-4162","authenticated-orcid":false,"given":"Wenjia","family":"Xu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1562-8098","authenticated-orcid":false,"given":"Qingzhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2886-2513","authenticated-orcid":false,"given":"Antoni B.","family":"Chan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref3","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mao"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref7","article-title":"CNN+CNN: Convolutional decoders for image captioning","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit. Workshop","author":"Wang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2824816"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00899"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref11","article-title":"Overview of the imageclef 2018 caption prediction tasks","volume-title":"Proc. CEUR Workshop","author":"De Herrera"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00434"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018142"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00486"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_21"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref17","first-page":"898","article-title":"Contrastive learning for image captioning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00432"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01168"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/584091.584093"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref26","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","first-page":"91","article-title":"Faster r-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"8","key":"ref33","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref34","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Devlin"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00146"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.445"},{"key":"ref39","article-title":"Generating diverse and accurate visual captions by comparative adversarial learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Li"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00436"},{"key":"ref41","first-page":"3613","article-title":"Diverse image captioning with context-object split latent spaces","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mahajan"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.681"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.120"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00350"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_10"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref49","first-page":"1917","article-title":"Meta-weight-Net: Learning an explicit mapping for sample weighting","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shu"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00344"},{"key":"ref52","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mao"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013834"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.276"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-018-9581-x"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref57","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Assoc. Comput. Linguistics Workshop","author":"Lin"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01095"},{"key":"ref59","article-title":"Towards diverse and accurate image captions via reinforcing determinantal point process","author":"Wang","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1428"},{"key":"ref61","first-page":"1730","article-title":"Measuring the diversity of automatic image descriptions","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Van Miltenburg"},{"key":"ref62","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref64","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"},{"key":"ref65","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref68","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10008914\/09736453.pdf?arnumber=9736453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:37:25Z","timestamp":1705534645000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9736453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,1]]},"references-count":68,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3159811","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,1]]}}}