Hierarchical Semantic Enhanced Directional Graph Network for Visual Commonsense Reasoning
Abstract
References
Index Terms
- Hierarchical Semantic Enhanced Directional Graph Network for Visual Commonsense Reasoning
Recommendations
Deep Hierarchical Attention Flow for Visual Commonsense Reasoning
Natural Language Processing and Chinese ComputingAbstractVisual Commonsense Reasoning (VCR) requires a thoroughly understanding general information connecting language and vision, as well as the background world knowledge. In this paper, we introduce a novel yet powerful deep hierarchical attention flow ...
Efficient and self-adaptive rationale knowledge base for visual commonsense reasoning
AbstractVisual commonsense reasoning (VCR) task leads to a cognitive level of understanding between vision and linguistic domains. Three sub-tasks, i.e., , , and , require the ability to predict the correct answer and rational explanation ...
Heterogeneous graph learning for visual commonsense reasoning
NIPS'19: Proceedings of the 33rd International Conference on Neural Information Processing SystemsVisual commonsense reasoning task aims at leading the research field into solving cognition-level reasoning with the ability of predicting correct answers and meanwhile providing convincing reasoning paths, resulting in three sub-tasks i.e., Q→A, QA→R and ...
Comments
Information & Contributors
Information
Published In
- Program Chairs:
- Dr. Teddy Furon,
- Dr. Jingen Liu,
- Prof. Yogesh Rawat,
- Dr. Wei Zhang,
- Prof. Qi Zhao
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Natural Science Foundation of China
- Natural Science Foundation of Guangdong Province
- PINGAN-HITsz Intelligence Finance Research Center
- Ricoh-HITsz Joint Research Center
- GBase-HITsz Joint Research Center
- Shenzhen Foundational Research Funding Under Grant
Conference
Upcoming Conference
- Sponsor:
- sigmm
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 213Total Downloads
- Downloads (Last 12 months)23
- Downloads (Last 6 weeks)0
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in