AI Paper Atlas

Research map / Video / Video segmentation and tracking

Deep Hand: How to Train a CNN on 1 Million Hand Images When Your Data Is Continuous and Weakly Labelled

Oscar Koller, Hermann Ney, Richard Bowden

CVPR 2016 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 288 citations (OpenAlex)

Check 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 1-Million-Hands features to the [18] multimodal system[18] sign language recognition system · PHOENIX 2014 DevWER: 57.3 -> 47.1Improved
Add 1-Million-Hands features to the [18] multimodal system[18] sign language recognition system · PHOENIX 2014 TestWER: 55.6 -> 45.1Improved
Add 1-Million-Hands features to the [18] multimodal system[18] sign language recognition system · SIGNUM TestWER: 10.0 -> 7.6Improved
Replace HoG-3D features with 1-Million-Hands CNN featuresHand-only continuous sign language recognition · PHOENIX 2014 DevWER: 60.9 -> 51.6Improved
Replace HoG-3D features with 1-Million-Hands CNN featuresHand-only continuous sign language recognition · PHOENIX 2014 TestWER: 58.1 -> 50.2Improved
Replace HoG-3D features with 1-Million-Hands CNN featuresHand-only continuous sign language recognition · SIGNUM TestWER: 12.5 -> 12.0Improved
Add PHOENIX training data to the Danish and New Zealand data (ablation)CNN hand-shape classifier · PHOENIX 2014 manually annotated hand shapestop-1 accuracy: 59.6 -> 62.8; 59.5 -> 57.7Mixed
Train with Danish data only rather than adding New Zealand and PHOENIX data (ablation)CNN hand-shape classifier · PHOENIX 2014 manually annotated hand shapestop-1 accuracy: 50.6 -> 62.8Hurt
Train with Danish and New Zealand data rather than also adding PHOENIX data (ablation)CNN hand-shape classifier · PHOENIX 2014 manually annotated hand shapestop-1 accuracy: 59.6 -> 62.8; 59.5 -> 57.7Mixed

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