V-JEPA: Revisiting Feature Prediction for Learning Visual Representations from Video

V-JEPA: Revisiting Feature Prediction for Learning Visual Representations from Video

Yannic Kilcher via YouTube Direct link

- Qualitative Evaluation via Decoding

8 of 8

8 of 8

- Qualitative Evaluation via Decoding

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

V-JEPA: Revisiting Feature Prediction for Learning Visual Representations from Video

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

  1. 1 - Intro
  2. 2 - Predictive Feature Principle
  3. 3 - Weights & Biases course on Structured LLM Outputs
  4. 4 - The original JEPA architecture
  5. 5 - V-JEPA Concept
  6. 6 - V-JEPA Architecture
  7. 7 - Experimental Results
  8. 8 - Qualitative Evaluation via Decoding

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.