{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T21:39:08Z","timestamp":1730237948640,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T00:00:00Z","timestamp":1696204800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T00:00:00Z","timestamp":1696204800000},"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":[[2023,10,2]]},"DOI":"10.1109\/iccvw60793.2023.00503","type":"proceedings-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:31:40Z","timestamp":1703532700000},"page":"4665-4670","source":"Crossref","is-referenced-by-count":0,"title":["Pointing out Human Answer Mistakes in a Goal-Oriented Visual Dialogue"],"prefix":"10.1109","author":[{"given":"Ryosuke","family":"Oshima","sequence":"first","affiliation":[{"name":"Waseda University"}]},{"given":"Seitaro","family":"Shinagawa","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology"}]},{"given":"Hideki","family":"Tsunashima","sequence":"additional","affiliation":[{"name":"Waseda University"}]},{"given":"Qi","family":"Feng","sequence":"additional","affiliation":[{"name":"Waseda University"}]},{"given":"Shigeo","family":"Morishima","sequence":"additional","affiliation":[{"name":"Waseda Research Institute for Science and Engineering"}]}],"member":"263","reference":[{"key":"ref1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume-title":"Advances in Neural Information Processing Systems","author":"Alayrac","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.320"},{"article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","year":"2023","author":"Dai","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.475"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.splurobonlp-1.3"},{"article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","year":"2023","author":"Fu","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref9","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proceedings of the 2015 International Conference on Learning Representations","author":"Kingma"},{"key":"ref10","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.169"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00191"},{"key":"ref13","first-page":"11054","article-title":"True few-shot learning with language models","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Perez","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1265"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00507"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.splu-1.4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00557"},{"article-title":"Enabling harmonious human-machine interaction with visual-context augmented dialogue system: A review","year":"2022","author":"Wang","key":"ref18"},{"key":"ref19","first-page":"12697","article-title":"Calibrate before use: Improving few-shot performance of language models","volume-title":"Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research","author":"Zhao"},{"article-title":"Multimodal C4: An open, billion-scale corpus of images interleaved with text","year":"2023","author":"Zhu","key":"ref20"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","start":{"date-parts":[[2023,10,2]]},"location":"Paris, France","end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10350357\/10350360\/10350676.pdf?arnumber=10350676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T03:00:14Z","timestamp":1705028414000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10350676\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,2]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iccvw60793.2023.00503","relation":{},"subject":[],"published":{"date-parts":[[2023,10,2]]}}}