Visual Question Answering: Grounded Systems and Transformer Capsules

Visual Question Answering: Grounded Systems and Transformer Capsules

UCF CRCV via YouTube Direct link

Approach

7 of 19

7 of 19

Approach

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Visual Question Answering: Grounded Systems and Transformer Capsules

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

  1. 1 Intro
  2. 2 Grounded Visual Question Answering
  3. 3 Limitations of Existing VQA Systems
  4. 4 Grounded VQA Systems
  5. 5 Problem Setup
  6. 6 Transformers with Capsules
  7. 7 Approach
  8. 8 Capsule-based Tokens
  9. 9 Input to Intermediate Transformer layers
  10. 10 Text-based Residual Connection
  11. 11 Pre-training Tasks
  12. 12 Masked Language Modeling (MLM)
  13. 13 Image Text Matching
  14. 14 Pre-training Datasets
  15. 15 Fine-tuning on Downstream Task
  16. 16 Qualitative comparison - GQA
  17. 17 Evaluation Metrics
  18. 18 Results - GQA
  19. 19 Conclusion and Future Work

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.