Modified densely connected convolutional network for content generation in automatic image description generation system
S R Sreela, Sumam Mary Idicula · 2017 IEEE Region 10 Symposium (TENSYMP) · 2017
Automatic image description generation is a challenging task in computer vision and computational linguistics. It helps people to get access to social media images easily. Content generation and surface realization are two important phases of this task. Deep learning techniques have a major role in content generation phase. The important scenario in content generation is object recognition. Deep learning algorithms produce better results compared to classical machine learning techniques. In this paper, we will explain a modified densely connected convolution network(Densenet) for object classification.