曖昧性のない物体記述の生成と理解
Generation and Comprehension of Unambiguous Object Descriptions
画像中の特定物体を一意に指す参照表現を生成し、また与えられた表現から対象物体を推論する手法を提案。MS-COCOベースの大規模データセットも公開した。
著者: Junhua Mao, Jonathan Huang, Alexander Toshev, Oana Camburu, Alan Yuille, Kevin Murphy
分類: cs.CV, cs.CL, cs.LG, cs.RO
原文アブストラクト
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
