VisKE: Visual knowledge extraction and question answering by visual verification of relation phrases

@article{Sadeghi2015VisKEVK,
  title={VisKE: Visual knowledge extraction and question answering by visual verification of relation phrases},
  author={Fereshteh Sadeghi and S. Divvala and Ali Farhadi},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={1456-1464}
}
How can we know whether a statement about our world is valid. For example, given a relationship between a pair of entities e.g., `eat(horse, hay)', how can we know whether this relationship is true or false in general. Gathering such knowledge about entities and their relationships is one of the fundamental challenges in knowledge extraction. Most previous works on knowledge extraction have focused purely on text-driven reasoning for verifying relation phrases. In this work, we introduce the… Expand
Ask Me Anything: Free-Form Visual Question Answering Based on Knowledge from External Sources
Verb Physics: Relative Physical Knowledge of Actions and Objects
Visual entity linking
Detecting Unseen Visual Relations Using Analogies
Visual Translation Embedding Network for Visual Relation Detection
Weakly-Supervised Learning of Visual Relations
Embedding Network for Visual Relation Detection
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 42 REFERENCES
Acquiring temporal constraints between relations
Open question answering over curated and extracted knowledge bases
Adopting Abstract Images for Semantic Scene Understanding
Semantic Parsing on Freebase from Question-Answer Pairs
Learning Everything about Anything: Webly-Supervised Visual Concept Learning
Learning Knowledge Graphs for Question Answering through Conversational Dialog
Identifying Relations for Open Information Extraction
Recognition using visual phrases
NEIL: Extracting Visual Knowledge from Web Data
A study of the knowledge base requirements for passing an elementary science test
...
1
2
3
4
5
...