{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:33:31Z","timestamp":1778081611333,"version":"3.51.4"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3437288","type":"journal-article","created":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T17:22:42Z","timestamp":1722619362000},"page":"10284-10296","source":"Crossref","is-referenced-by-count":9,"title":["UNK-VQA: A Dataset and a Probe Into the Abstention Ability of Multi-Modal Large Models"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8691-5372","authenticated-orcid":false,"given":"Yangyang","family":"Guo","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0670-6990","authenticated-orcid":false,"given":"Fangkai","family":"Jiao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, I<sup>2<\/sup>R, A*STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqi","family":"Shen","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4846-2015","authenticated-orcid":false,"given":"Mohan","family":"Kankanhalli","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1116-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref7","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref8","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref9","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.551"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02303"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01431"},{"key":"ref14","article-title":"Otter: A multi-modal model with in-context instruction tuning","author":"Li","year":"2023"},{"key":"ref15","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00650"},{"key":"ref18","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"issue":"8","key":"ref20","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548100"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00205"},{"key":"ref24","first-page":"20346","article-title":"Human-adversarial visual question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sheng"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3128322"},{"key":"ref27","article-title":"Introducing MPT-7B: A new standard for open-source, commercially usable LLMs","author":"Team","year":"2023"},{"key":"ref28","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref29","article-title":"Multimodal C4: An open, billion-scale corpus of images interleaved with text","author":"Zhu","year":"2023"},{"key":"ref30","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","author":"Zheng","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29808"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.710"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.84"},{"key":"ref34","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-55560-2_5"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.217"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref43","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Malinowski"},{"key":"ref44","first-page":"2953","article-title":"Exploring models and data for image question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.283"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_23"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref49","first-page":"2296","article-title":"Are you talking to a machine? dataset and methods for multilingual image question answering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gao"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_34"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.82"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1241"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00266"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.79"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1484"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016529"},{"key":"ref61","article-title":"NeurQuRI: Neural question requirement inspector for answerability prediction in machine reading comprehension","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Back"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17705"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref66","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref67","article-title":"Vision-language intelligence: Tasks, representation learning, and large models","author":"Li","year":"2022"},{"key":"ref68","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":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1219"},{"key":"ref70","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gan"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref73","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref76","first-page":"5583","article-title":"VILT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref77","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10620618.pdf?arnumber=10620618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:12:36Z","timestamp":1732666356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10620618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":77,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3437288","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":[[2024,12]]}}}