.png){kind=icon}
.png){kind=icon}
Return
Combining Multiple Cues for Visual Madlibs Question Answering
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-018-1096-0.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper presents an approach for answering fill-in-the-blank multiple choice questions from the Visual Madlibs dataset. Instead of generic and commonly used representations trained on the ImageNet classification task, our approach employs a combination of networks trained for specialized tasks such as scene recognition, person activity classification, and attribute prediction. We also present a method for localizing phrases from candidate answers in order to provide spatial support for feature extraction. We map each of these features, together with candidate answers, to a joint embedding space through normalized canonical correlation analysis (nCCA). Finally, we solve an optimization problem to learn to combine scores from nCCA models trained on multiple cues to select the best answer. Extensive experimental results show a significant improvement over the previous state of the art and confirm that answering questions from a wide range of types benefits from examining a variety of image cues and carefully choosing the spatial support for feature extraction.
Keywords:
Visual question answering
Cue integration
Region phrase correspondence
Computer vision
Language
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.3
Papers:
3.9K
Citations:
2.8W
View more organizations