{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:16:15Z","timestamp":1777655775813,"version":"3.51.4"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iccv51070.2023.01856","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T20:55:59Z","timestamp":1705352159000},"page":"20236-20246","source":"Crossref","is-referenced-by-count":8,"title":["OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?"],"prefix":"10.1109","author":[{"given":"Runjia","family":"Li","sequence":"first","affiliation":[{"name":"University of Oxford,Torr Vision Group"}]},{"given":"Shuyang","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Oxford,Torr Vision Group"}]},{"given":"Mohamed","family":"Elhoseiny","sequence":"additional","affiliation":[{"name":"KAUST"}]},{"given":"Philip","family":"Torr","sequence":"additional","affiliation":[{"name":"University of Oxford,Torr Vision Group"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01140"},{"key":"ref3","article-title":"Colbert: Using BERT sentence embedding for humor detection","author":"Annamoradnejad","year":"2020","journal-title":"CoRR"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"CoRR"},{"key":"ref5","article-title":"Manga OCR","author":"Budy\u015b","journal-title":"original-date: 2022-01-15T17:18:34Z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1207\/s1532785xmep0602_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2018"},{"key":"ref9","author":"Chen","year":"2015","journal-title":"Microsoft coco captions: Data collection and evaluation server"},{"key":"ref10","author":"Damodaran","year":"2021","journal-title":"Parrot: Paraphrase generation for nlu."},{"key":"ref11","journal-title":"DeepLcom\/deepl-python: Official python library for the DeepL language translation API"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref13","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/85076"},{"key":"ref15","volume-title":"Emotion english distilroberta-base","author":"Hartmann","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17534"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1172"},{"key":"ref18","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.41"},{"key":"ref20","journal-title":"Imgflip - create and share awesome images"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00212"},{"key":"ref22","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","author":"Kiela","year":"2020","journal-title":"CoRR"},{"key":"ref23","article-title":"Gant Laborde","journal-title":"Deep nn for nsfw detection"},{"key":"ref24","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref25","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref26","article-title":"Roberta: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_26"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16500-9_9"},{"key":"ref29","author":"Loria","journal-title":"TextBlob: Simplified text processing. originaldate: 2013-06-30T18:29:18Z"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1336"},{"key":"ref31","volume-title":"Romantic progression: The psychology of literary history.","author":"Martindale","year":"1975"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1177\/0956797610376073"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.31861\/gph2021.831-832.288-297"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/1220575.1220642"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.600"},{"key":"ref36","article-title":"Clipcap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"CoRR"},{"key":"ref37","volume-title":"Taking Laughter Seriously.","author":"Morreall","year":"1983"},{"key":"ref38","article-title":"Vilio: State-of-the-art visio-linguistic models applied to hateful memes","author":"Muennighoff","year":"2020","journal-title":"CoRR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00062"},{"key":"ref41","author":"Peirson V","journal-title":"Dank learning: Generating memes using deep neural networks"},{"key":"ref42","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"CoRR"},{"issue":"8","key":"ref43","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref46","article-title":"Cider: Consensus-based image description evaluation","author":"Vedantam","year":"2014","journal-title":"CoRR"},{"key":"ref47","article-title":"Show and tell: A neural image caption generator","author":"Vinyals","year":"2014","journal-title":"CoRR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.figlang-1.25"},{"key":"ref49","first-page":"6136","article-title":"The rJokes dataset: a large scale humor collection","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Weller"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1284"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref52","journal-title":"Bokete ogiri"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Paris, France","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376473\/10376477\/10378611.pdf?arnumber=10378611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:40:14Z","timestamp":1705542014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10378611\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51070.2023.01856","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}