Show, Deconfound and Tell: Image Captioning with Causal Inference
Author:
Affiliation:
1. School of Computer Science and Technology, China University of Mining and Technology
2. School of Computer Science and Engineering, Southeast University
Funder
National Natural Science Foundation of China
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9878378/9878366/09880383.pdf?arnumber=9880383
Reference51 articles.
1. Show and tell: A neural image caption generator
2. CIDEr: Consensus-based image description evaluation
3. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
4. Two Causal Principles for Improving Visual Dialog
5. Glove: Global Vectors for Word Representation
Cited by 26 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. M3ixup: A multi-modal data augmentation approach for image captioning;Pattern Recognition;2025-02
2. Learning consistent representations with temporal and causal enhancement for knowledge tracing;Expert Systems with Applications;2024-07
3. GaitSCM: Causal representation learning for gait recognition;Computer Vision and Image Understanding;2024-06
4. A survey of neurosymbolic visual reasoning with scene graphs and common sense knowledge;Neurosymbolic Artificial Intelligence;2024-05-13
5. Background no more: Action recognition across domains by causal interventions;Computer Vision and Image Understanding;2024-05
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