2016 Poster Sessions : DenseCap: Fully Convolutional Localization Networks for Dense Captioning

Student Name : Justin Johnson
Advisor : Fei-Fei Li
Research Areas: Artificial Intelligence
We introduce the dense captioning task, which requires a computer vision system to both localize and describe salient regions in images in natural language. The dense captioning task generalizes object detection when the descriptions consist of a single word, and Image Captioning when one predicted region covers the full image. To address the localization and description task jointly we propose a Fully Convolutional Localization Network (FCLN) architecture that processes an image with a single, efficient forward pass, requires no external regions proposals, and can be trained end-to-end with a single round of optimization. The architecture is composed of a Convolutional Network, a novel dense localization layer, and Recurrent Neural Network language model that generates the label sequences. We evaluate our network on the Visual Genome dataset, which comprises 94,000 images and 4,100,000 region-grounded captions. We observe both speed and accuracy improvements over baselines based on current state of the art approaches in both generation and retrieval settings.

Justin is a PhD student the in the Computer Science Department at Stanford University, advised by Professor Fei-Fei Li. His research focuses on deep learning, especially as applied to computer vision tasks such as image classification, object detection, and applications of natural language to computer vision.