Stating the Obvious: Extracting Visual Common Sense Knowledge

@inproceedings{Yatskar2016StatingTO,
  title={Stating the Obvious: Extracting Visual Common Sense Knowledge},
  author={Mark Yatskar and Vicente Ordonez and Ali Farhadi},
  booktitle={HLT-NAACL},
  year={2016}
}
Obtaining common sense knowledge using current information extraction techniques is extremely challenging. In this work, we instead propose to derive simple common sense statements from fully annotated object detection corpora such as the Microsoft Common Objects in Context dataset. We show that many thousands of common sense facts can be extracted from such corpora at high quality. Furthermore, using WordNet and a novel submodular k-coverage formulation, we are able to generalize our initial… Expand
32 Citations
Automatic Extraction of Commonsense LocatedNear Knowledge
  • 17
  • PDF
Commonsense LocatedNear Relation Extraction
  • 1
  • PDF
Machine Common Sense Concept Paper
  • 14
  • PDF
iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering
  • 2
  • PDF
Weakly-Supervised Learning of Visual Relations
  • 119
  • PDF
...
1
2
3
4
...

References

SHOWING 1-10 OF 27 REFERENCES
VisKE: Visual knowledge extraction and question answering by visual verification of relation phrases
  • 102
  • PDF
Recognizing textual entailment: Rational, evaluation and approaches
  • 196
  • PDF
DIRT @SBT@discovery of inference rules from text
  • 557
  • PDF
ConceptNet — A Practical Commonsense Reasoning Tool-Kit
  • 1,420
  • PDF
Volunteers Created the Web
  • Lucy Vanderwende
  • Computer Science
  • AAAI Spring Symposium: Knowledge Collection from Volunteer Contributors
  • 2005
  • 12
  • PDF
NEIL: Extracting Visual Knowledge from Web Data
  • 406
  • PDF
ConceptNet 5: A Large Semantic Network for Relational Knowledge
  • 193
  • PDF
Learning Everything about Anything: Webly-Supervised Visual Concept Learning
  • 268
  • PDF
...
1
2
3
...