VQA Challenge Workshop
at CVPR 2016, June 26, Las Vegas, USA

Home Program SubmissionAccepted Abstracts




The VQA Challenge Winners and Honorable Mentions will be revealed at this workshop where they will be awarded GPUs sponsored by NVIDIA!

Introduction

The primary purpose of this workshop is to hold a challenge on Visual Question Answering on the VQA dataset. VQA is a new dataset containing open-ended and multiple-choice questions about images. These questions require an understanding of vision, language, and commonsense knowledge to answer. This workshop will provide an opportunity to benchmark algorithms on the VQA dataset and to identify state-of-the-art algorithms.

A secondary goal of this workshop is to bring together researchers interested in Visual Question Answering to share state-of-the-art approaches, best practices, and perspectives on future directions in multi-modal AI. We invite submissions of extended abstracts of at most 2 pages describing work in areas such as: Visual Question Answering, (Textual) Question Answering, Commonsense Knowledge, Video Question Answering, Image/Video Captioning and other problems at the intersection of vision and language. Accepted abstracts will be presented as posters at the workshop. The workshop will be held on June 26th, 2016 at the IEEE Conference on Computer Vision and Pattern Recognition, 2016.


Invited Speakers


Alex Berg
UNC Chapel Hill


Trevor Darrell
UC Berkeley


Ali Farhadi
University of Washington


Mario Fritz
Max-Planck-Institut für Informatik


Jitendra Malik
UC Berkeley


Margaret Mitchell
Microsoft Research


Kevin Murphy
Google Research


Yuandong Tian
Facebook AI Research


Program (Venue: Palace III)

9:00 AM - 9:10 AM
Welcome
9:10 AM - 9:35 AM
A Simple Baseline for Visual Question Answering
Invited Talk: Yuandong Tian (Facebook AI Research)
9:35 AM - 10:00 AM
See While You Say: Generating Human-like Language from Visual Input
Invited Talk: Margaret Mitchell (Microsoft Research)
10:00 AM - 10:25 AM
Consistent questions in Visual Madlibs, and detecting objects for visual question answering
Invited Talk: Alex Berg (UNC Chapel Hill)
10:25 AM - 10:45 AM
Morning Break
10:45 AM - 11:10 AM
Embodied Cognition: Linking vision, motor control and language
Invited Talk: Jitendra Malik (UC Berkeley)
11:10 AM - 11:40 AM
Overview of challenge, winner announcements, analysis of results
Aishwarya Agrawal
11:40 AM - 11:55 AM

Challenge Winner Talk (Abstract Scenes)
Andrew Shin, Kuniaki Saito, Tatsuya Harada and Yoshitaka Ushiku
11:55 AM - 12:00 PM

Honorable Mention Spotlight (Real Images)
Aaditya Prakash
12:00 PM - 12:15 PM

Challenge Runner-Up Talk (Real Images)
Hyeonseob Nam and Jeonghee Kim
12:15 PM - 12:30 PM


Challenge Winner Talk (Real Images)
Akira Fukui, Dong Huk Park, Daylen Yang, Anna Rohrbach, Trevor Darrell and Marcus Rohrbach
12:30 PM - 2:00 PM
Lunch (On your own)
2:00 PM - 2:25 PM
Towards vision and language aids for the blind
Invited Talk: Kevin Murphy (Google Research)
2:25 PM - 2:50 PM
Invited Talk
Trevor Darrell (UC Berkeley)
2:50 PM - 4:00 PM

Poster session and Afternoon break
4:00 PM - 4:25 PM
Invited Talk
Ali Farhadi (University of Washington)
4:25 PM - 4:50 PM
Invited Talk
Mario Fritz (Max-Planck-Institut für Informatik)
4:50 PM - 6:00 PM
Panel: Future Directions
6:00 PM
Closing Remarks

Poster Presentation Instructions

1. Poster stands will be 8 feet wide by 4 feet high. Please review the CVPR16 poster template for more details on how to prepare your poster. You do not need to use this template, but please read the instructions carefully and prepare your posters accordingly.

2. Poster presenters are asked to install their posters between 12:25 PM and 2:00 PM. Push pins will be provided for attaching posters to the boards.


Submission Instructions

We invite submissions of extended abstracts of at most 2 pages describing work in areas such as: Visual Question Answering, (Textual) Question Answering, Commonsense Knowledge, Video Question Answering, Image/Video Captioning and other problems at the intersection of vision and language. Accepted submissions will be presented as posters at the workshop. The extended abstract should follow the CVPR formatting guidelines and be emailed as single PDF to the email id mentioned below. Please use the following LaTeX/Word templates.

  • LaTeX/Word Templates (tar): cvpr2016AuthorKit.tgz
  • LaTeX/Word Templates (zip): cvpr2016AuthorKit.zip

  • Dual Submissions

    We encourage submissions of relevant work that has been previously published, or is to be presented at the main conference. The accepted abstracts will be posted on the workshop website and will not appear in the official IEEE proceedings.


    Dates

    May 08, 2016 Extended Submission Deadline
    May 15, 2016 Decision to Authors

    In case you need a decision before the CVPR early registration deadline (May 15), please let us know.


    Where to Submit?

    Please send your abstracts to visualqa.workshop@gmail.com


    Organizers


    Aishwarya Agrawal
    Virginia Tech


    Jiasen Lu
    Virginia Tech


    Yash Goyal
    Virginia Tech


    Peng Zhang
    Virginia Tech


    Larry Zitnick
    Facebook AI Research


    Dhruv Batra
    Virginia Tech


    Devi Parikh
    Virginia Tech


    Webmaster


    Akrit Mohapatra
    Virginia Tech


    Sponsors




    Contact: visualqa@gmail.com