@inproceedings{f6cfce86567b492c992d9bf54dd2b34f,
title = "Visual Classifier Prediction by Distributional Semantic Embedding of Text Descriptions",
abstract = "One of the main challenges for scaling up object recognition systems is the lack of annotated images for real-world categories. It is estimated that humans can recognize and discriminate among about 30,000 categories (Biederman and others, 1987). Typically there are few images available for training classifiers form most of these categories. This is reflected in the number of images per category available for training in most object categorization datasets, which, as pointed out in (Salakhutdinov et al., 2011), shows a Zipf distribution.",
author = "Mohamed Elhoseiny and Ahmed Elgammal",
note = "Publisher Copyright: {\textcopyright} 2015 Association for Computational Linguistics.; 4th Workshop on Vision and Language, VL 2015, as part of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 ; Conference date: 18-09-2015",
year = "2015",
language = "English (US)",
series = "A Workshop of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Workshop on Vision and Language 2015, VL 2015: Vision and Language Meet Cognitive Systems - Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "48--50",
booktitle = "A Workshop of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Workshop on Vision and Language 2015, VL 2015",
address = "United States",
}