Search Results for author:
Found 10 papers, 1 papers with code
The Role of Typicality in Object Classification: Improving The Generalization Capacity of Convolutional Neural Networks
We focus on Convolutional Neural Networks (CNN) as the state-of-the-art models in object recognition and classification; investigate this problem in more detail, and hypothesize that training CNN models suffer from unstructured loss minimization.
Write a Classifier: Predicting Visual Classifiers from Unstructured Text
Then, we propose a new constrained optimization formulation that combines a regression function and a knowledge transfer function with additional constraints to predict the parameters of a linear classifier.
Toward a Taxonomy and Computational Models of Abnormalities in Images
In this paper we study various types of atypicalities in images in a more comprehensive way than has been done before.
Tell and Predict: Kernel Classifier Prediction for Unseen Visual Classes from Unstructured Text Descriptions
In this paper we propose a framework for predicting kernelized classifiers in the visual domain for categories with no training images where the knowledge comes from textual description about these categories.
Quantifying Creativity in Art Networks
The proposed computational framework is based on constructing a network between creative products and using this network to infer about the originality and influence of its nodes.
Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature
In the past few years, the number of fine-art collections that are digitized and publicly available has been growing rapidly.
Learning Style Similarity for Searching Infographics
Infographics are complex graphic designs integrating text, images, charts and sketches.
Abnormal Object Recognition: A Comprehensive Study
When describing images, humans tend not to talk about the obvious, but rather mention what they find interesting.
Toward Automated Discovery of Artistic Influence
The contribution of this paper is in exploring the problem of computer-automated suggestion of influences between artists, a problem that was not addressed before in a general setting.
Object-Centric Anomaly Detection by Attribute-Based Reasoning
When describing images, humans tend not to talk about the obvious, but rather mention what they find interesting.
