Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

11-2012

Abstract

We demonstrate a multimedia-based question-answering system, named FashionAsk, by allowing users to ask questions referring to pictures snapped by mobile devices. Specifically, instead of asking verbose questions to depict visual instances, direct pictures are provided as part of questions. To answer these multi-modal questions, FashionAsk performs a large-scale instance search to infer the names of instances, and then matches with similar questions from communitycontributed QA websites as answers. The demonstration is conducted on a million-scale dataset of Web images and QA pairs in the domain of fashion products. Asking a multimedia question through FashionAsk can take as short as five seconds to retrieve the candidate answer as well as suggested questions.

Keywords

instance naming, multimedia question answering, question matching

Discipline

Data Storage Systems | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 20th ACM international conference on Multimedia, MM 2012, Nara, Japan, October 29 - November 2

First Page

1345

Last Page

1346

ISBN

9781450310895

Identifier

10.1145/2393347.2396476

Publisher

ACM

City or Country

Nara, Japan

Download

Share

COinS