AI Paper Atlas

Research map / Video / Action recognition

Flip-Invariant Motion Representation

Takumi Kobayashi

ICCV 2017 · Video › Action recognition · approach: Disentangled action recognition · 8 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
estimate patch orientation from flow instead of image gradients (Flip by Flow) (ablation)HOF descriptor · HMDB51accuracy (%): 52.24 -> 52.81Improved
estimate patch flip from flow instead of image gradients (ablation)HOG descriptor · Hollywood2accuracy (%): 48.15 -> 50.37Improved
add flip augmentation of training and test samples (ablation)HOF descriptor · HMDB51accuracy (%): 50.00 -> 49.59No clear effect
add flip invariance by Flip by Flow (ablation)HOF descriptor · UCF101accuracy (%): 77.44 -> 79.27Improved
use learned eigen invariant form (5) instead of averaging (ablation)HOF descriptor · HMDB51accuracy (%): 52.24 -> 54.64Improved
use eigen invariant form instead of MI-SIFT (ablation)HOF descriptor · UCF101accuracy (%): 77.24 -> 80.09Improved
add orthonormality constraint to the learned invariant form (vs generalized eigenvalue problem) (ablation)temporal ConvNet layer4 · HMDB51accuracy (%): 56.45 -> 57.30Improved
use MI-SIFT on ConvNet descriptors (ablation)temporal ConvNet layer3 · Hollywood2accuracy (%): 62.72 -> 60.50Hurt
use max operator instead of average for invariance (ablation)temporal ConvNet layer4 · UCF101accuracy (%): 84.47 -> 85.14Improved
add learned invariant form (ablation)spatial ConvNet layer4 · HMDB51accuracy (%): 46.67 -> 46.41No clear effect
train invariant form on UCF101 and apply to other datasets (ablation)temporal ConvNet layer4 · HMDB51accuracy (%): 57.30 -> 56.80No clear effect
add Flip by Flow to descriptor combinationiDT+LMS+ConvNet · Hollywood2accuracy (%): 70.53 -> 72.49Improved

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