Publications
Detailed Information
Video-based Visual Question Answering with Spatio-Temporal Reasoning Tasks : 시·공간 추론에 기반한 동영상 질의 응답
Cited 0 time in
Web of Science
Cited 0 time in Scopus
- Authors
- Advisor
- 김건희
- Major
- 공과대학 컴퓨터공학부
- Issue Date
- 2018-02
- Publisher
- 서울대학교 대학원
- Keywords
- Neural Network ; Deep Learning ; Computer Vision ; Natual Lan- guage Processing ; Visual Question Answering ; Visual Understanding ; Visual Reasoning
- Description
- 학위논문 (석사)-- 서울대학교 대학원 : 공과대학 컴퓨터공학부, 2018. 2. 김건희.
- Abstract
- Vision and language understanding has emerged as a subject undergoing intense study in Artificial Intelligence. Among many tasks in this line of research, visual question answering (VQA) has been one of the most successful ones, where the goal is to learn a model that understands visual content at region-level details and finds their associations with pairs of questions and answers in the natural language form. Despite the rapid progress in the past few years, most existing work in VQA have focused primarily on images. In this paper, we focus on extending VQA to the video domain and contribute to the literature in three important ways. First, we propose three new tasks designed specifically for video VQA, which require spatio-temporal reasoning from videos to answer questions correctly. Next, we introduce a new large-scale dataset for video VQA named TGIF-QA that extends existing VQA work with our new tasks. Finally, we propose a dual-LSTM based approach with both spatial and temporal attention, and show its effectiveness over conventional VQA techniques through empirical evaluations. Code and the dataset are available on our project page: http://vision.snu.ac.kr/projects/tgif-qa
- Language
- English
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.