AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

ModDrop: Adaptive Multi-Modal Gesture Recognition

Natalia Neverova, Christian Wolf, Graham Taylor, Florian Nebout

TPAMI 2016 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 482 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 ModDrop to dropout training (ablation)tree-structured MNIST net · MNIST (1 segment covered)test error %: 10.74 -> 2.30Improved
add ModDrop to dropout training (ablation)tree-structured MNIST net · MNIST (3 segments covered)test error %: 68.03 -> 24.88Improved
add ModDrop (ablation)MNIST net with all segments visible · MNISTtest error %: 1.02 -> 1.02No clear effect
add ModDrop (ablation)MNIST net under 50% pepper noise on all segments · MNISTtest error %: 7.27 -> 6.42Improved
add modality-wise pretraining (ablation)MNIST multi-modal net · MNIST (4 quarters as modalities)test errors: 142 -> 118Improved
add dropout on inputs after pretraining (ablation)MNIST multi-modal net · MNIST (4 quarters as modalities)test errors: 118 -> 102Improved
add ModDrop on top of pretraining and dropout (ablation)MNIST multi-modal net · MNIST (4 quarters as modalities)test errors: 102 -> 102No clear effect
add ModDrop to pretraining, dropout and initialization (ablation)ModDrop network · ChaLearn 2014 LAP + audio (validation)accuracy %: 96.77 -> 96.81Improved
add shared-layer initialization with pretrained blocks (ablation)ModDrop network · ChaLearn 2014 LAP + audio (validation)accuracy %: 96.31 -> 96.77Improved
add modality pretraining (ablation)network without dropout · ChaLearn 2014 LAP + audio (validation)accuracy %: 91.94 -> 94.96Improved
add ModDrop when the mocap channel is missing (ablation)dropout network · ChaLearn 2014 LAP + audioaccuracy %: 38.41 -> 92.82Improved
add gesture localization module (ablation)ModDrop improved · ChaLearn 2014 LAP visualJaccard index: 0.821 -> 0.868Improved

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