{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T16:21:49Z","timestamp":1759940509858,"version":"3.37.3"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005022","name":"Beijing Jiaotong University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005022","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446407","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10056-10060","source":"Crossref","is-referenced-by-count":6,"title":["Empowering Vision-Language Models for Reasoning Ability through Large Language Models"],"prefix":"10.1109","author":[{"given":"Yueting","family":"Yang","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University,Beijing,China"}]},{"given":"Xintong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,Beijing,China"}]},{"given":"Jinan","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,Beijing,China"}]},{"given":"Wenjuan","family":"Han","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","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"},{"article-title":"Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref2"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"16816","article-title":"Conditional prompt learning for visionlanguage models","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhou"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"article-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models","year":"2023","author":"Wu","key":"ref7"},{"article-title":"Mm-react: Prompting chatgpt for multimodal reasoning and action","year":"2023","author":"Yang","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.104"},{"article-title":"Video chatcaptioner: Towards the enriched spatiotemporal descriptions","year":"2023","author":"Chen","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.201"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.43"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"article-title":"Iconqa: A new benchmark for abstract diagram understanding and visual language reasoning","year":"2021","author":"Lu","key":"ref16"},{"key":"ref17","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","year":"2022","author":"Lu","key":"ref18"},{"article-title":"Glm-130b: An open bilingual pre-trained model","year":"2022","author":"Zeng","key":"ref19"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446407.pdf?arnumber=10446407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:14:41Z","timestamp":1722575681000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446407","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}