Timezone: »

Hierarchical Question-Image Co-Attention for Visual Question Answering
Jiasen Lu · Jianwei Yang · Dhruv Batra · Devi Parikh

Tue Dec 06 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #7 #None

A number of recent works have proposed attention models for Visual Question Answering (VQA) that generate spatial maps highlighting image regions relevant to answering the question. In this paper, we argue that in addition to modeling "where to look" or visual attention, it is equally important to model "what words to listen to" or question attention. We present a novel co-attention model for VQA that jointly reasons about image and question attention. In addition, our model reasons about the question (and consequently the image via the co-attention mechanism) in a hierarchical fashion via a novel 1-dimensional convolution neural networks (CNN). Our model improves the state-of-the-art on the VQA dataset from 60.3% to 60.5%, and from 61.6% to 63.3% on the COCO-QA dataset. By using ResNet, the performance is further improved to 62.1% for VQA and 65.4% for COCO-QA.

Author Information

Jiasen Lu (Virginia Tech)
Jianwei Yang (Virginia Tech)
Dhruv Batra (Georgia Tech / Facebook AI Research (FAIR))
Devi Parikh (Virginia Tech)

More from the Same Authors