# Knowing Where to Look? Analysis on Attention of Visual Question Answering System

Source: [Knowing Where to Look? Analysis on Attention of Visual Question Answering System](<https://www.sota2.com/research/paper/68fa64e21e209131cea070e1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:13:58.604Z

Authors: Wei Li, Zehuan Yuan, Xiangzhong Fang, Changhu Wang

Published: 2018-10-09T05:51:08.000Z

## Abstract

Attention mechanisms have been widely used in Visual Question Answering (VQA) solutions due to their capacity to model deep cross-domain interactions. Analyzing attention maps offers us a perspective to find out limitations of current VQA systems and an opportunity to further improve them. In this paper, we select two state-of-the-art VQA approaches with attention mechanisms to study their robustness and disadvantages by visualizing and analyzing their estimated attention maps. We find that both methods are sensitive to features, and simultaneously, they perform badly for counting and multi-object related questions. We believe that the findings and analytical method will help researchers identify crucial challenges on the way to improve their own VQA systems.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1810.03821>)

[PDF](<https://arxiv.org/pdf/1810.03821.pdf>)