Hierarchical Question-Image Co-Attention for Visual Question Answering

Code

• github.com/jiasenlu/HieCoAttenVQA
  OfficialIn papertorch★ 351
• github.com/WillSuen/VQA
  tf★ 0
• github.com/phisad/keras-hicoatt
  tf★ 0
• github.com/ritvikshrivastava/ADL_VQA_Tensorflow2
  tf★ 0
• github.com/miohana/vqa
  tf★ 0
• github.com/SkyOL5/VQA-CoAttention
  pytorch★ 0
• github.com/arya46/VQA_HieCoAtt
  tf★ 0
• github.com/karunraju/VQA
  pytorch★ 0
• github.com/Rabahjamal/Visual-Question-Answering
  tf★ 0

Abstract

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.

Tasks

Benchmark Results

Reproductions