Главная
Study mode:
on
1
Intro
2
Paper details
3
Problem Formulation
4
Method: Overview
5
Method: Motion-Excited Sampler
6
Method: Motion Excited Sampling
7
Method: Motion Calculation
8
Method: Gradient Estimation - Formulation
9
Method: Gradient Estimation - Big Idea
10
Method: Gradient Estimation - Algorithm
11
(Method) Adversarial Optimization
12
(Method) loss function
13
(Results) Model Accuracy
14
(Results) Effectiveness of using motion
15
(Results) Visualizing Motion Vectors
16
(Results) Main Results
17
(Results) Ablation study
18
Summary
19
Against
Description:
Explore a lecture on video adversarial attacks using the Motion-Excited Sampler technique. Delve into the problem formulation, methodology, and key components such as motion-excited sampling, motion calculation, and gradient estimation. Examine the adversarial optimization process, loss function, and results, including model accuracy and the effectiveness of using motion. Visualize motion vectors and analyze main findings through an ablation study. Gain insights into this innovative approach for generating adversarial examples in videos, presented as part of the CAP6412 course at the University of Central Florida.

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

University of Central Florida
Add to list