{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:25:45Z","timestamp":1774419945991,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887841","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["EventLens: Enhancing Visual Commonsense Reasoning by Leveraging Event-Aware Pretraining and Cross-modal Linking"],"prefix":"10.1109","author":[{"given":"Mingjie","family":"Ma","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology,School of Computer Science and Technology,Wuhan,China"}]},{"given":"Zhihuan","family":"Yu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Computer Science and Technology,Wuhan,China"}]},{"given":"Yichao","family":"Ma","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Computer Science and Technology,Wuhan,China"}]},{"given":"Guohui","family":"Li","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Software Engineering,Wuhan,China"}]},{"given":"Zhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Computer Science and Technology,Wuhan,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref2","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref6","article-title":"TAB-VCR: Tags and attributes based visual commonsense reasoning baselines","volume":"32","author":"Lin","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","article-title":"Connective cognition network for directional visual commonsense reasoning","volume":"32","author":"Wu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Heterogeneous graph learning for visual commonsense reasoning","volume":"32","author":"Yu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20536"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3091882"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475328"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.763"},{"key":"ref15","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","volume-title":"International Conference on Learning Representations","author":"Su"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1219"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107408"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01973"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2020.2991866"},{"key":"ref21","first-page":"1877","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref23","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref24","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref25","first-page":"23 716","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"},{"key":"ref26","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref27","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref28","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref29","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612395"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_30"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref35","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref36","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems 32. Curran Associates"},{"key":"ref37","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887841.pdf?arnumber=10887841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:34Z","timestamp":1774416334000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887841","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}