Plug-and-Adapt: Multimodal Coreference Resolution at First Sight With a Pretrained Alignment Model
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 13936-13948
Abstract
No abstract availableAll Related Versions
Funding Information
- National Research Foundation, Singapore
- National Large Language Models Funding Initiative
- AISG (AISG-NMLP-2024-003)
- National Natural Science Foundation of China (62403372)
- Science and Technology Project of China Huaneng Group Co., Ltd. (HNKJ23-HF67)
- National Postdoctoral Innovative Talents Support Program (BX20230283)
- Sanqin Bochuang Talent Support Plan of Shaanxi Province (2024SQBC005)
- China Scholarship Council (202406280309)
This publication has 42 references indexed in Scilit:
- GPT-4 in a Cancer Center — Institute-Wide Deployment Challenges and Lessons LearnedNEJM AI, 2024
- A brief survey on recent advances in coreference resolutionArtificial Intelligence Review, 2023
- Grounded Situation Recognition2020
- Connecting Vision and Language with Localized Narratives2020
- UNITER: UNiversal Image-TExt Representation Learning2020
- Generalization of Dempster–Shafer theory: A complex mass functionApplied Intelligence, 2020
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image AnnotationsInternational Journal of Computer Vision, 2017
- Subjective Logic2016
- What Are You Talking About? Text-to-Image Coreference2014
- Bipartite Graphs and their Applications1998