DeepVision 2019

Overview

Deep Learning has become the standard tool to approach almost any computer vision problem. In order to present an attractive workshop that brings a different perspective to the topic, we are focusing this edition on brave new ideas, theoretical discussions and, in general, imaginative approaches that may yield to the next family of deep learning algorithms.

We encourage researchers to formulate innovative learning theories, feature representations, and end-to-end vision systems based on deep learning. We also encourage new theories and processes for dealing with large scale image datasets through deep learning architectures.

TOPICS

We are soliciting original contributions that address a wide range of theoretical and practical issues including, but not limited to:

• Large scale image and video understanding with deep models
  • Video classification
  • Object recognition
  • Object tracking
• Industrial and medical applications
• Unsupervised feature learning and feature selection
• Learning with limited data, trends and training strategies
• Deep learning hardware architectures
• Deep learning in mobile platforms and embedded systems
• Advancements in deep learning
• Domain transfer using deep architectures
• Real time applications
• Mid-level representations with deep learning

SPONSORS