DeepAI AI Chat
Log In Sign Up

From Pixels to Objects: Cubic Visual Attention for Visual Question Answering

by   Jingkuan Song, et al.

Recently, attention-based Visual Question Answering (VQA) has achieved great success by utilizing question to selectively target different visual areas that are related to the answer. Existing visual attention models are generally planar, i.e., different channels of the last conv-layer feature map of an image share the same weight. This conflicts with the attention mechanism because CNN features are naturally spatial and channel-wise. Also, visual attention models are usually conducted on pixel-level, which may cause region discontinuous problems. In this paper, we propose a Cubic Visual Attention (CVA) model by successfully applying a novel channel and spatial attention on object regions to improve VQA task. Specifically, instead of attending to pixels, we first take advantage of the object proposal networks to generate a set of object candidates and extract their associated conv features. Then, we utilize the question to guide channel attention and spatial attention calculation based on the con-layer feature map. Finally, the attended visual features and the question are combined to infer the answer. We assess the performance of our proposed CVA on three public image QA datasets, including COCO-QA, VQA and Visual7W. Experimental results show that our proposed method significantly outperforms the state-of-the-arts.


page 1

page 6


Hierarchical Question-Image Co-Attention for Visual Question Answering

A number of recent works have proposed attention models for Visual Quest...

Task-driven Visual Saliency and Attention-based Visual Question Answering

Visual question answering (VQA) has witnessed great progress since May, ...

Question-Agnostic Attention for Visual Question Answering

Visual Question Answering (VQA) models employ attention mechanisms to di...

Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering

We address the problem of Visual Question Answering (VQA), which require...

Two-stream Spatiotemporal Feature for Video QA Task

Understanding the content of videos is one of the core techniques for de...

Revisiting Modulated Convolutions for Visual Counting and Beyond

This paper targets at visual counting, where the setup is to estimate th...