DeepAI AI Chat
Log In Sign Up

Adversarially Robust Frame Sampling with Bounded Irregularities

by   Hanhan Li, et al.

In recent years, video analysis tools for automatically extracting meaningful information from videos are widely studied and deployed. Because most of them use deep neural networks which are computationally expensive, feeding only a subset of video frames into such algorithms is desired. Sampling the frames with fixed rate is always attractive for its simplicity, representativeness, and interpretability. For example, a popular cloud video API generated video and shot labels by processing only the first frame of every second in a video. However, one can easily attack such strategies by placing chosen frames at the sampled locations. In this paper, we present an elegant solution to this sampling problem that is provably robust against adversarial attacks and introduces bounded irregularities as well.


page 1

page 2

page 3

page 4


Attacking Automatic Video Analysis Algorithms: A Case Study of Google Cloud Video Intelligence API

Due to the growth of video data on Internet, automatic video analysis ha...

Deceiving Google's Cloud Video Intelligence API Built for Summarizing Videos

Despite the rapid progress of the techniques for image classification, v...

Appending Adversarial Frames for Universal Video Attack

There have been many efforts in attacking image classification models wi...

Video Summarization using Keyframe Extraction and Video Skimming

Video is one of the robust sources of information and the consumption of...

MGSampler: An Explainable Sampling Strategy for Video Action Recognition

Frame sampling is a fundamental problem in video action recognition due ...

RPCA-KFE: Key Frame Extraction for Consumer Video based Robust Principal Component Analysis

Key frame extraction algorithms consider the problem of selecting a subs...

EgoSampling: Fast-Forward and Stereo for Egocentric Videos

While egocentric cameras like GoPro are gaining popularity, the videos t...