Scene classification with low-dimensional semantic spaces and weak supervision

@article{Rasiwasia2008SceneCW,
  title={Scene classification with low-dimensional semantic spaces and weak supervision},
  author={Nikhil Rasiwasia and Nuno Vasconcelos},
  journal={2008 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2008},
  pages={1-6}
}
A novel approach to scene categorization is proposed. Similar to previous works of [11, 15, 3, 12], we introduce an intermediate space, based on a low dimensional semantic ldquothemerdquo image representation. However, instead of learning the themes in an unsupervised manner, they are learned with weak supervision, from casual image annotations. Each theme induces a probability density on the space of low-level features, and images are represented as vectors of posterior theme probabilities… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 99 CITATIONS

Cross-Modality Bridging and Knowledge Transferring for Image Understanding

VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Beyond visual word ambiguity: Weighted local feature encoding with governing region

VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Beyond visual features: A weak semantic image representation using exemplar classifiers for classification

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Beyond local image features: Scene calssification using supervised semantic representation

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Boosting algorithms for simultaneous feature extraction and selection

VIEW 5 EXCERPTS
CITES METHODS

Scene Recognition on the Semantic Manifold

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS

Image Classification base on PCA of Multi-view Deep Representation

VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Structured Weak Semantic Space Construction for Visual Categorization

VIEW 7 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

Contextual Exemplar Classifier-Based Image Representation for Classification

VIEW 7 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Object categorization in sub-semantic space

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2009
2019

CITATION STATISTICS

  • 10 Highly Influenced Citations

  • Averaged 12 Citations per year from 2017 through 2019

  • 90% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 19 REFERENCES

Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

A Bayesian hierarchical model for learning natural scene categories

  • Fei-Fei Li, Pietro Perona
  • Computer Science
  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Modeling scenes with local descriptors and latent aspects

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Scene Modeling Using Co-Clustering

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Supervised Learning of Semantic Classes for Image Annotation and Retrieval

VIEW 5 EXCERPTS

Scene Classification Via pLSA

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Latent Dirichlet Allocation

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Visual categorization with bags of keypoints

VIEW 2 EXCERPTS