Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior - Spring 2021

Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior - Spring 2021

UCF CRCV via YouTube Direct link

(Method) loss function

12 of 19

12 of 19

(Method) loss function

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior - Spring 2021

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

  1. 1 Intro
  2. 2 Paper details
  3. 3 Problem Formulation
  4. 4 Method: Overview
  5. 5 Method: Motion-Excited Sampler
  6. 6 Method: Motion Excited Sampling
  7. 7 Method: Motion Calculation
  8. 8 Method: Gradient Estimation - Formulation
  9. 9 Method: Gradient Estimation - Big Idea
  10. 10 Method: Gradient Estimation - Algorithm
  11. 11 (Method) Adversarial Optimization
  12. 12 (Method) loss function
  13. 13 (Results) Model Accuracy
  14. 14 (Results) Effectiveness of using motion
  15. 15 (Results) Visualizing Motion Vectors
  16. 16 (Results) Main Results
  17. 17 (Results) Ablation study
  18. 18 Summary
  19. 19 Against

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.