AI Paper Atlas

Research map / Video / Video segmentation and tracking

Real-World Repetition Estimation by Div, Grad and Curl

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

CVPR 2018 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 5 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 the proposed flow-signal and wavelet method instead of Pogalin et al.repetition counting · QUVA RepetitionMAE: 38.5 ± 37.6 -> 23.2 ± 34.4Improved
use the proposed flow-signal and wavelet method instead of Levy & Wolfrepetition counting · QUVA RepetitionMAE: 48.2 ± 61.5 -> 23.2 ± 34.4Improved
use the proposed method instead of Levy & Wolfrepetition counting · YTSegmentsMAE: 6.5 ± 9.2 -> 10.3 ± 19.8Hurt
use the proposed method instead of Pogalin et al.repetition counting · YTSegmentsMAE: 21.9 ± 30.1 -> 10.3 ± 19.8Improved
use time-localized wavelets rather than a global Fourier periodogramidealized cycle signals from QUVA Repetition · QUVA Repetitioncounting performance: nullImproved
add diverse flow-based signals with per-video signal selection instead of relying on one fixed signal (ablation)repetition counting · QUVA RepetitionMAE: 32.9 ± 31.4 -> 10.5 ± 15.7Improved
use only vertical flow instead of selecting among diverse signals (ablation)flow-based repetition counting · QUVA RepetitionMAE: 10.5 ± 15.7 -> 32.9 ± 31.4Hurt
use only horizontal flow instead of selecting among diverse signals (ablation)flow-based repetition counting · QUVA RepetitionMAE: 10.5 ± 15.7 -> 38.3 ± 31.4Hurt
use only the divergence signal instead of selecting among diverse signals (ablation)flow-based repetition counting · QUVA RepetitionMAE: 10.5 ± 15.7 -> 44.9 ± 34.8Hurt
use only the curl signal instead of selecting among diverse signals (ablation)flow-based repetition counting · QUVA RepetitionMAE: 10.5 ± 15.7 -> 44.9 ± 34.8Hurt
use only ∇x Fx instead of selecting among diverse signals (ablation)flow-based repetition counting · QUVA RepetitionMAE: 10.5 ± 15.7 -> 46.7 ± 30.8Hurt
use only ∇y Fy instead of selecting among diverse signals (ablation)flow-based repetition counting · QUVA RepetitionMAE: 10.5 ± 15.7 -> 42.7 ± 39.8Hurt

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