AI Paper Atlas

Research map / Video / Action recognition

Modality Distillation with Multiple Stream Networks for Action Recognition

Nuno C. Garcia, Pietro Morerio, Vittorio Murino

ECCV 2018 · Video › Action recognition · approach: Disentangled action recognition · 214 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 cross-stream multiplicative connections when training hallucination stream (ablation)hallucination network (step 3) · NTU RGB+D (cross-subject)accuracy: 70.64 -> 71.93Improved
add cross-stream connections (cross-subject, step 3) (ablation)hallucination network · NTU RGB+D (cross-subject)accuracy: 71.10 -> 71.93Improved
add cross-stream connections to the two-stream RGB+D teacher (ablation)step 2 model · NTU RGB+D (cross-subject)accuracy: 78.27 -> 79.73Improved
add cross-stream connections to the two-stream RGB+D teacher (ablation)step 2 model · NTU RGB+D (cross-view)accuracy: 82.11 -> 81.43Hurt
replace Euclidean loss with distillation loss L_GD in Hoffman pipeline (ablation)Hoffman et al. hallucination · NTU RGB+D (cross-subject)accuracy: 64.64 -> 68.60Improved
use combined loss L instead of L_GD in Hoffman pipeline (ablation)Hoffman et al. hallucination · NTU RGB+D (cross-subject)accuracy: 68.60 -> 70.70Improved
use proposed losses and staged training instead of original Hoffman setup (ablation)Hoffman et al. · NTU RGB+D (cross-subject)accuracy: 64.64 -> 70.70Improved
add staged training with fine-tuning (step 4) after hallucination learning (ablation)step 3 model · NTU RGB+D (cross-subject)accuracy: 71.93 -> 73.42Improved
add fine-tuning step 4 (ablation)step 3 model · NTU RGB+D (cross-view)accuracy: 74.10 -> 77.21Improved
hallucinate depth instead of training RGB-only (ablation)RGB stream · NTU RGB+D (cross-subject)accuracy: 66.52 -> 73.42Improved
use hallucination model instead of corrupted real depth inputtwo-stream model · NTU RGB+D (cross-view)accuracy: 76.85 -> 77.21Improved
increase depth noise variance from 10^-3 to 10^1two-stream RGB+D with real depth · NTU RGB+D (cross-view)accuracy: 81.34 -> 51.43Hurt

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