• Publications
  • Influence
Measuring the Objectness of Image Windows
TLDR
A generic objectness measure, quantifying how likely it is for an image window to contain an object of any class, and uses objectness as a complementary score in addition to the class-specific model, which leads to fewer false positives.
What is an object?
TLDR
A generic objectness measure, quantifying how likely it is for an image window to contain an object of any class, is presented, combining in a Bayesian framework several image cues measuring characteristics of objects, such as appearing different from their surroundings and having a closed boundary.
Weakly Supervised Localization and Learning with Generic Knowledge
TLDR
A conditional random field that starts from generic knowledge and then progressively adapts to the new class is proposed that allows training any state-of-the-art object detector in a weakly supervised fashion, although it would normally require object location annotations.
The IAPR TC-12 Benchmark: A New Evaluation Resource for Visual Information Systems
TLDR
An image collection created for the CLEF cross-language image retrieval track (ImageCLEF), including its associated text captions which are expressed in multiple languages, making the collection well-suited for evaluating the effectiveness of both textbased and visual retrieval methods.
Features for image retrieval: an experimental comparison
TLDR
An experimental comparison of a large number of different image descriptors for content-based image retrieval is presented and the often used, but very simple, color histogram performs well in the comparison and thus can be recommended as a simple baseline for many applications.
Deformation Models for Image Recognition
TLDR
It is shown experimentally that the proposed nonlinear image deformation models performs very well for four different handwritten digit recognition tasks and for the classification of medical images, thus showing high generalization capacity.
The 2005 PASCAL Visual Object Classes Challenge
TLDR
This chapter provides details of the datasets, algorithms used by the teams, evaluation criteria, and results achieved in the PASCAL Visual Object Classes Challenge.
Localizing Objects While Learning Their Appearance
TLDR
This work proposes a conditional random field that starts from generic knowledge and then progressively adapts to the new class to enable any state-of-the-art object detector in a weakly supervised fashion, although it would normally require object location annotations.
Global and efficient self-similarity for object classification and detection
TLDR
This paper proposes computationally efficient algorithms to extract GSS descriptors for classification and demonstrates that GSS outperforms LSS for both classification and detection, and that G SS descriptors are complementary to conventional descriptors such as gradients or color.
Visual and semantic similarity in ImageNet
TLDR
The insights gained from analysis enable building a novel distance function between images assessing whether they are from the same basic-level category, which goes beyond direct visual distance as it also exploits semantic similarity measured through ImageNet.
...
1
2
3
4
5
...