AI Paper Atlas

Research map / Video / Video segmentation and tracking

Repetition Estimation

Tom F. H. Runia, Cees G. M. Snoek, Arnold W. M. Smeulders

IJCV 2019 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 25 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
add wavelet-power motion segmentation instead of full-frame pooling (ablation)wavelet repetition counter · QUVA RepetitionMAE: 60.8 -> 26.1Improved
use wavelet-derived segmentation instead of classical motion segmentation (ablation)wavelet repetition counter · YTSegmentsMAE: 13.1 -> 9.4Improved
use wavelet-derived segmentation instead of two-stream LSTM segmentation (ablation)wavelet repetition counter · QUVA RepetitionMAE: 38.9 -> 26.1Improved
combine all six motion maps (oracle selection) instead of one map (ablation)motion maps · QUVA RepetitionMAE: 42.0 -> 24.1Improved
use best single map vertical flow vs divergence (ablation)motion maps · QUVA RepetitionMAE: 77.8 -> 42.0Improved
replace FlowNet 2.0 with TV-L1 flow (ablation)wavelet repetition counter · YTSegmentsMAE: 9.4 -> 9.8No clear effect
replace FlowNet 2.0 with EpicFlow (ablation)wavelet repetition counter · QUVA RepetitionMAE: 26.1 -> 30.8Hurt
replace Fourier periodogram with wavelet scalogram (ablation)idealized signals · QUVA Repetitioncounting error: 83 out of 100Improved
add 2x midpoint acceleration to test videoswavelet repetition counter · YTSegmentsMAE: increase of 4.4Hurt
add 2x midpoint acceleration to test videosdeep learning counting baseline · YTSegmentsMAE: rises with 10.8 pointsHurt
sum wavelet power of vertical flow and divergence maps (ablation)bouncing ball with viewpoint change · synthetic Blender videospectral power continuityImproved
vary spatial sigma from 4 to 2, 8, 16 (ablation)motion maps · QUVA Repetition and YTSegmentscount performanceNo clear effect

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