2015/10/30 by Fereshteh Sadeghi, C. Lawrence Zitnick, Sadeghi, Fereshteh +3 · 2 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Video Analysis and Summarization #cs.CV
paper · pdf · doi:10.48550/arxiv.1510.08973
To appear in NIPS 2015
arxiv created 2015/10/30 · openalex publication_date 2015/10/30 · arxiv updated 2015/11/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper, we study the problem of answering visual analogy questions. These questions take the form of image A is to image B as image C is to what. Answering these questions entails discovering the mapping from image A to image B and then extending the mapping to image C and searching for the image D such that the relation from A to B holds for C to D. We pose this problem as learning an embedding that encourages pairs of analogous images with similar transformations to be close together using convolutional neural networks with a quadruple Siamese architecture. We introduce a dataset of visual analogy questions in natural images, and show first results of its kind on solving analogy questions on natural images.