{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:38:39Z","timestamp":1770845919384,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11343454","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"876-883","source":"Crossref","is-referenced-by-count":0,"title":["Grounded Multi-modal Conversation for Zero-shot Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Mohammad Reza","family":"Zarei","sequence":"first","affiliation":[{"name":"Carleton University,School of Computer Science,Ottawa,Canada"}]},{"given":"Abbas","family":"Akkasi","sequence":"additional","affiliation":[{"name":"Carleton University,School of Computer Science,Ottawa,Canada"}]},{"given":"Majid","family":"Komeili","sequence":"additional","affiliation":[{"name":"Carleton University,School of Computer Science,Ottawa,Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC59896.2024.10556344"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-1092-9_7"},{"key":"ref3","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref4","article-title":"Pixtral 12b","author":"Agrawal","year":"2024"},{"key":"ref5","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Georgiev","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612389"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.755"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.189"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3643795.3648387"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.67"},{"key":"ref11","article-title":"Visual haystacks: Answering harder questions about sets of images","author":"Wu","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.375"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref14","article-title":"Prompt-cap: Prompt-guided task-aware image captioning","author":"Hu","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/169546"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref19","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref20","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref22","first-page":"19 730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICECAI62591.2024.10674838"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126991"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107563"},{"key":"ref26","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"International conference on machine learning","author":"Kim"},{"key":"ref27","article-title":"Toa: task-oriented active vqa","volume":"36","author":"Liang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.590"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref33","article-title":"Coco-text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28212"},{"key":"ref37","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Zheng"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.672"},{"key":"ref39","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11343454.pdf?arnumber=11343454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:52:04Z","timestamp":1770843124000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343454\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11343454","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}