FFNet: Video Fast-Forwarding via Reinforcement Learning

TL;DR

FFNet is a reinforcement learning-based method for efficient video fast-forwarding that selects representative frames on the fly, reducing processing needs while maintaining good video representation.

Contribution

Introduces FFNet, an online reinforcement learning framework for video fast-forwarding that does not require processing entire videos and adapts in real-time.

Findings

Outperforms existing methods in video representation quality.

Reduces computational requirements significantly.

Operates effectively in real-time scenarios.

Abstract

For many applications with limited computation, communication, storage and energy resources, there is an imperative need of computer vision methods that could select an informative subset of the input video for efficient processing at or near real time. In the literature, there are two relevant groups of approaches: generating a trailer for a video or fast-forwarding while watching/processing the video. The first group is supported by video summarization techniques, which require processing of the entire video to select an important subset for showing to users. In the second group, current fast-forwarding methods depend on either manual control or automatic adaptation of playback speed, which often do not present an accurate representation and may still require processing of every frame. In this paper, we introduce FastForwardNet (FFNet), a reinforcement learning agent that gets inspiration from video summarization and does fast-forwarding differently. It is an online framework that automatically fast-forwards a video and presents a representative subset of frames to users on the fly. It does not require processing the entire video, but just the portion that is selected by the fast-forward agent, which makes the process very computationally efficient. The online nature of our proposed method also enables the users to begin fast-forwarding at any point of the video. Experiments on two real-world datasets demonstrate that our method can provide better representation of the input video with much less processing requirement.