{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T22:45:44Z","timestamp":1784069144713,"version":"3.55.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Fundamental Research Funds for the Central Universities, SCUT","award":["x2rjD2220050"],"award-info":[{"award-number":["x2rjD2220050"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076100"],"award-info":[{"award-number":["62076100"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3379900","type":"journal-article","created":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T19:10:43Z","timestamp":1711653043000},"page":"2652-2664","source":"Crossref","is-referenced-by-count":18,"title":["Knowledge-Augmented Visual Question Answering With Natural Language Explanation"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-7879","authenticated-orcid":false,"given":"Jiayuan","family":"Xie","sequence":"first","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1767-789X","authenticated-orcid":false,"given":"Yi","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiali","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruohang","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7064-6507","authenticated-orcid":false,"given":"Jiexin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software Engineering and the Key Laboratory of Big Data and Intelligent Robot, Ministry of Education, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10151-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097180"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00814"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548284"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.06.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3145158"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3051476"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2969330"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028651"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1037\/a0031026"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","volume":"139","author":"Radford"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.551"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547870"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"ref21","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. ICML","volume":"162","author":"Li"},{"key":"ref22","article-title":"Generating rationales in visual question answering","author":"Ayyubi","year":"2020","journal-title":"arXiv:2004.02032"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4812"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.253"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00128"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.440"},{"key":"ref27","first-page":"1801","article-title":"Interpretable neural-symbolic concept reasoning","volume-title":"Proc. ICML","volume":"202","author":"Barbiero"},{"key":"ref28","first-page":"1","article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","volume-title":"Proc. ICLR","author":"Mao"},{"key":"ref29","first-page":"1039","article-title":"Neural-symbolic VQA: Disentangling reasoning from vision and language understanding","volume-title":"Proc. NeurIPS","author":"Yi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.201"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"issue":"8","key":"ref34","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref35","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. NeurIPS","author":"Ren"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v3i1.13979"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3189242"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806502"},{"key":"ref41","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3138706"},{"key":"ref43","article-title":"Pythia v0.1: The winning entry to the VQA challenge 2018","author":"Jiang","year":"2018","journal-title":"arXiv:1807.09956"},{"key":"ref44","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"ref47","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref49","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref51","first-page":"1","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref52","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref53","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Browner"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref55","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. ACL Workshop","author":"Lin"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10981"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10480354.pdf?arnumber=10480354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:55:28Z","timestamp":1712692528000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10480354\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3379900","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}