AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning Image Matching by Simply Watching Video

Gucan Long, Laurent Kneip, Jose M. Alvarez, Hongdong Li, Xiaohu Zhang, Qifeng Yu

ECCV 2016 · Video › Video segmentation and tracking · approach: Video frame interpolation · 199 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
initialize DeepFlow with MIND matches instead of no matchesDeepFlow · KITTI 2012 flow trainingAPE: 3.55 -> 2.89Improved
initialize DeepFlow with MIND matches instead of no matchesDeepFlow · MPI-Sintel flow trainingAPE: 6.63 -> 5.78Improved
initialize DeepFlow with DeepMatching instead of MIND matchesDeepFlow · KITTI 2012 flow trainingAPE: 2.89 -> 2.63Improved
initialize DeepFlow with MIND matches instead of HoGDeepFlow · MPI-Sintel flow trainingAPE: 5.46 -> 5.78Hurt
initialize DeepFlow with MIND matches instead of HoGDeepFlow · KITTI 2012 flow trainingAPE: 3.06 -> 2.89Improved
use MIND matches instead of KLT matchingmatching · KITTI 2012 flow training (matching)Accuracy@10: 0.826 -> 0.915Improved
use MIND matches instead of HoG matchingmatching · KITTI 2012 flow training (matching)Accuracy@10: 0.805 -> 0.915Improved
use MIND matches instead of KLT matchingmatching · MPI-Sintel training Final (matching)Accuracy@5: 0.808 -> 0.719Hurt
use MIND matches instead of HoG matchingmatching · MPI-Sintel training Final (matching)Accuracy@10: 0.875 -> 0.876No clear effect
use DeepMatching instead of MINDmatching · MPI-Sintel training Final (matching)APE: 5.838 -> 3.240Improved
use Charbonnier loss instead of L2 loss (ablation)MIND frame interpolation network · KITTI/Sintel traininginterpolation qualityImproved
use MIND instead of DeepFlow for interpolationframe interpolation · KITTImean interpolation error: 33.30 -> 30.99Improved

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