Learning Everything about Anything: Webly-Supervised Visual Concept Learning

@article{Divvala2014LearningEA,
  title={Learning Everything about Anything: Webly-Supervised Visual Concept Learning},
  author={Santosh Kumar Divvala and Ali Farhadi and Carlos Guestrin},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={3270-3277}
}
Recognition is graduating from labs to real-world applications. While it is encouraging to see its potential being tapped, it brings forth a fundamental challenge to the vision researcher: scalability. How can we learn a model for any concept that exhaustively covers all its appearance variations, while requiring minimal or no human supervision for compiling the vocabulary of visual variance, gathering the training images and annotations, and learning the models? In this paper, we introduce a… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 216 CITATIONS

Learning Semantic Part-Based Models from Google Images

VIEW 19 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

A new web-supervised method for image dataset constructions

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Advances in detecting object classes and their semantic parts

VIEW 10 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Towards Automatic Construction of Diverse, High-quality Image Dataset

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A Domain Robust Approach For Image Dataset Construction

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Commonsense knowledge acquisition and applications

VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Extracting Visual Knowledge from the Internet: Making Sense of Image Data

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

From Visual Attributes to Adjectives through Decompositional Distributional Semantics

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2013
2020

CITATION STATISTICS

  • 22 Highly Influenced Citations

  • Averaged 36 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 53 REFERENCES

LIBSVM: A library for support vector machines

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

The Pascal Visual Object Classes (VOC) Challenge

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Learning object class detectors from weakly annotated video

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Measuring the Objectness of Image Windows

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Recognition using visual phrases

VIEW 5 EXCERPTS

Scene recognition and weakly supervised object localization with deformable part-based models

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Weakly supervised object detector learning with model drift detection

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Describing objects by their attributes

VIEW 5 EXCERPTS

Learning to detect unseen object classes by between-class attribute transfer

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL