Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs with Language Structures via Dependency Relationships
Author:
Affiliation:
1. Beijing Institute for General Artificial Intelligence (BIGAI),Beijing,China
2. Tsinghua Unversity,Beijing,China
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9878378/9878366/09880111.pdf?arnumber=9880111
Reference50 articles.
1. Learning Hierarchical Space Tiling for Scene Modeling, Parsing and Attribute Tagging
2. Maf: Multimodal alignment framework for weakly-supervised phrase grounding;qinxin;Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP),0
3. Energy-Based Learning for Scene Graph Generation
4. A Simple Baseline for Weakly-Supervised Scene Graph Generation
5. Visually Grounded Neural Syntax Acquisition
Cited by 5 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. IntentQA: Context-aware Video Intent Reasoning;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01
2. Empowering MultiModal Models’ In-Context Learning Ability through Large Language Models;Proceedings of the ACM Turing Award Celebration Conference - China 2023;2023-07-28
3. Scene Graph based Fusion Network for Image-Text Retrieval;2023 IEEE International Conference on Multimedia and Expo (ICME);2023-07
4. Skew Class-Balanced Re-Weighting for Unbiased Scene Graph Generation;Machine Learning and Knowledge Extraction;2023-03-10
5. Graph Strategy for Interpretable Visual Question Answering;Artificial General Intelligence;2023
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3