Visual Madlibs: Fill in the Blank Description Generation and Question Answering

• Published in: 2015 IEEE International Conference on Computer Vision (ICCV) pp. 2461 - 2469
• Main Authors: Licheng Yu, Eunbyung Park, Berg, Alexander C., Berg, Tamara L.
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01-12-2015
• Subjects: Blanks; Computer vision; Conferences; Context; Explosions; Knowledge discovery; Learning; Natural language (computers); Natural languages; Tasks; Videos; Visual; Visualization
• ISSN: 2380-7504
• DOI: 10.1109/ICCV.2015.283

In this paper, we introduce a new dataset consisting of 360,001 focused natural language descriptions for 10,738 images. This dataset, the Visual Madlibs dataset, is collected using automatically produced fill-in-the-blank templates designed to gather targeted descriptions about: people and objects, their appearances, activities, and interactions, as well as inferences about the general scene or its broader context. We provide several analyses of the Visual Madlibs dataset and demonstrate its applicability to two new description generation tasks: focused description generation, and multiple-choice question-answering for images. Experiments using joint-embedding and deep learning methods show promising results on these tasks.