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 Santosh Kumar 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… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 83 CITATIONS

Learn How to Choose: Independent Detectors Versus Composite Visual Phrases

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Visual Question Answering and Beyond

VIEW 1 EXCERPT
CITES BACKGROUND

Human-Centered Artificial Intelligence and Machine Learning

VIEW 1 EXCERPT
CITES BACKGROUND

Learning to Detect Human-Object Interactions With Knowledge

VIEW 1 EXCERPT
CITES BACKGROUND

Multimodal Latent Factor Model with Language Constraint for Predicate Detection

VIEW 1 EXCERPT

Neural Sequential Phrase Grounding (SeqGROUND)

VIEW 1 EXCERPT
CITES BACKGROUND

FILTER CITATIONS BY YEAR

2015
2020

CITATION STATISTICS

  • 2 Highly Influenced Citations

  • Averaged 16 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 41 REFERENCES

Recognition using visual phrases

VIEW 5 EXCERPTS

Exploring web scale language models for search query processing

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

NEIL: Extracting Visual Knowledge from Web Data

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Object Detection with Discriminatively Trained Part Based Models

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Adopting Abstract Images for Semantic Scene Understanding

VIEW 1 EXCERPT