no code implementations • 9 Feb 2016 • Babak Saleh, Ahmed Elgammal, Jacob Feldman
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.
no code implementations • 31 Dec 2015 • Mohamed Elhoseiny, Ahmed Elgammal, Babak Saleh
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.
no code implementations • 4 Dec 2015 • Babak Saleh, Ahmed Elgammal, Jacob Feldman, Ali Farhadi
In this paper we study various types of atypicalities in images in a more comprehensive way than has been done before.
no code implementations • 29 Jun 2015 • Mohamed Elhoseiny, Ahmed Elgammal, Babak Saleh
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.
no code implementations • 2 Jun 2015 • Ahmed Elgammal, Babak Saleh
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.
1 code implementation • 5 May 2015 • Babak Saleh, Ahmed Elgammal
In the past few years, the number of fine-art collections that are digitized and publicly available has been growing rapidly.
no code implementations • 5 May 2015 • Babak Saleh, Mira Dontcheva, Aaron Hertzmann, Zhicheng Liu
Infographics are complex graphic designs integrating text, images, charts and sketches.
no code implementations • 9 Nov 2014 • Babak Saleh, Ali Farhadi, Ahmed Elgammal
When describing images, humans tend not to talk about the obvious, but rather mention what they find interesting.
no code implementations • 14 Aug 2014 • Babak Saleh, Kanako Abe, Ravneet Singh Arora, Ahmed Elgammal
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.
no code implementations • CVPR 2013 • Babak Saleh, Ali Farhadi, Ahmed Elgammal
When describing images, humans tend not to talk about the obvious, but rather mention what they find interesting.