English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Ask Your Neurons Again: Analysis of Deep Methods with Global Image Representation

Malinowski, M., Rohrbach, M., & Fritz, M. (2016). Ask Your Neurons Again: Analysis of Deep Methods with Global Image Representation. Poster presented at VQA Challenge Workshop, Las Vegas, NV, USA.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-002B-412A-F Version Permalink: https://hdl.handle.net/11858/00-001M-0000-002C-A1C0-1
Genre: Poster

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Malinowski, Mateusz1, Author           
Rohrbach, Marcus1, Author           
Fritz, Mario1, Author           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Content

show
hide
Free keywords: -
 Abstract: We are addressing an open-ended question answering task about real-world images. With the help of currently available methods developed in Computer Vision and Natural Language Processing, we would like to push an architecture with a global visual representation to its limits. In our contribution, we show how to achieve competitive performance on VQA with global visual features (Residual Net) together with a carefully desgined architecture.

Details

show
hide
Language(s): eng - English
 Dates: 2016
 Publication Status: Accepted / In Press
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: malinowski16vqa
 Degree: -

Event

show
hide
Title: VQA Challenge Workshop
Place of Event: Las Vegas, NV, USA
Start-/End Date: 2016-06-26 - 2016-06-26

Legal Case

show

Project information

show

Source 1

show
hide
Title: IEEE Conference on Computer Vision and Pattern Recognition Workshops
  Other : CVPR 2016
  Other : CVPRW 2016
  Abbreviation : VQA 2016
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -