Neural-Symbolic VQA - Disentangling Reasoning from Vision and Language Understanding

Neural-Symbolic VQA - Disentangling Reasoning from Vision and Language Understanding

UCF CRCV via YouTube Direct link

Quantitative results on CLEVR

8 of 11

8 of 11

Quantitative results on CLEVR

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Neural-Symbolic VQA - Disentangling Reasoning from Vision and Language Understanding

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Visual Question Answering
  3. 3 Task Breakdown
  4. 4 Architecture Overview
  5. 5 Question Parsing
  6. 6 Program Execution
  7. 7 Training
  8. 8 Quantitative results on CLEVR
  9. 9 CLEVR-Humans & Results
  10. 10 New Scenes: Minecraft
  11. 11 Summary

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.