Generation and Comprehension of Unambiguous Object Descriptions

November 07, 2015 · Entered Twilight · 🏛 Computer Vision and Pattern Recognition

"Last commit was 9.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, README.md, evaluation, external, google_refexp_eval_demo.ipynb, google_refexp_py_lib, google_refexp_visualization_demo.ipynb, setup.py

Authors Junhua Mao, Jonathan Huang, Alexander Toshev, Oana Camburu, Alan Yuille, Kevin Murphy arXiv ID 1511.02283 Category cs.CV: Computer Vision Cross-listed cs.CL, cs.LG, cs.RO Citations 1.6K Venue Computer Vision and Pattern Recognition Repository https://github.com/mjhucla/Google_Refexp_toolbox ⭐ 166 Last Checked 1 month ago

Abstract

We propose a method that can generate an unambiguous description (known as a referring expression) of a specific object or region in an image, and which can also comprehend or interpret such an expression to infer which object is being described. We show that our method outperforms previous methods that generate descriptions of objects without taking into account other potentially ambiguous objects in the scene. Our model is inspired by recent successes of deep learning methods for image captioning, but while image captioning is difficult to evaluate, our task allows for easy objective evaluation. We also present a new large-scale dataset for referring expressions, based on MS-COCO. We have released the dataset and a toolbox for visualization and evaluation, see https://github.com/mjhucla/Google_Refexp_toolbox