AI Paper Atlas

Research map / Video / Video segmentation and tracking

FFNet: Video Fast-Forwarding via Reinforcement Learning

Shuyue Lan, Rameswar Panda, Qi Zhu, Amit K. Roy-Chowdhury

CVPR 2018 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 55 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use FFNet's reinforcement-learning fast-forward policy instead of the supervised baselinevideo fast-forwarding · Tour20, hit number 10segment-level coverage: 0.685 -> 0.893Improved
Use FFNet's reinforcement-learning fast-forward policy instead of the supervised baselinevideo fast-forwarding · TVSum, hit number 10segment-level coverage: 0.526 -> 0.941Improved
Select frames with FFNet rather than the compared baselinesvideo fast-forwarding · Tour20human rating: 8.49 -> 8.70Improved
Select frames with FFNet rather than the compared baselinesvideo fast-forwarding · TVSumhuman rating: 8.10 -> 8.95Improved
Process only selected frames with FFNet rather than processing every video framevideo fast-forwarding · All tested videosframes processed: 100% -> 18.67%Improved
Use online Q-learning fast-forwarding instead of Spectral Clusteringvideo fast-forwarding · TVSum random subset, hit number 10coverage: 58% -> 97%Improved
Vary the reward's Gaussian window size among 2, 3, and 4 (ablation)FFNet · TVSumsegment-level coverageNo clear effect

Later papers that compared with this method

2 later accepted papers report FFNet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy