Video captioning is an automated collection of natural language phrases that explains the contents in video frames. Because of the incomparable performance of deep learning in the …
We present a system which can recognize the contents of your meal from a single image, and then predict its nutritional contents, such as calories. The simplest version assumes that …
Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use. In response, previous …
In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult …
J Raiman, O Raiman - Proceedings of the AAAI Conference on Artificial …, 2018 - ojs.aaai.org
The wealth of structured (eg Wikidata) and unstructured data about the world available today presents an incredible opportunity for tomorrow's Artificial Intelligence. So far, integration of …
S Guadarrama, N Krishnamoorthy… - Proceedings of the …, 2013 - cv-foundation.org
Despite a recent push towards large-scale object recognition, activity recognition remains limited to narrow domains and small vocabularies of actions. In this paper, we tackle the …
L Liu, J Deng - Proceedings of the AAAI Conference on Artificial …, 2018 - ojs.aaai.org
Abstract We introduce Dynamic Deep Neural Networks (D2NN), a new type of feed-forward deep neural network that allows selective execution. Given an input, only a subset of D2NN …
We present a new tree based approach to composing expressive image descriptions that makes use of naturally occuring web images with captions. We investigate two related tasks …
Y Zhu, A Fathi, L Fei-Fei - Computer Vision–ECCV 2014: 13th European …, 2014 - Springer
Abstract Reasoning about objects and their affordances is a fundamental problem for visual intelligence. Most of the previous work casts this problem as a classification task where …