AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition

Masashi Hatano, Ryo Hachiuma, Ryo Fujii, Hideo Saito

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 19 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 source cross-entropy classification loss to VideoMAE reconstruction pretraining (ablation)MM-CDFSL · EPIC-Kitchens 5-shottop-1 accuracy: 49.82 -> 58.70Improved
add target-domain reconstruction loss in pretraining (ablation)MM-CDFSL · EPIC-Kitchens 5-shottop-1 accuracy: 56.43 -> 58.70Improved
add multimodal distillation (optical flow and hand pose) to the RGB student (ablation)MM-CDFSL · WEAR 5-shottop-1 accuracy: 67.19 -> 69.57Improved
add optical flow distillation on top of RGB+Pose (ablation)MM-CDFSL · WEAR 1-shottop-1 accuracy: 49.39 -> 51.25Improved
set pretraining cross-entropy weight to 0.05 rather than 1 or 0.01 (ablation)MM-CDFSL RGB only · EPIC-Kitchens 5-shottop-1 accuracy: 54.58 / 52.40 -> 57.07Improved
apply ensemble masked inference (mask 0.75, P=2) instead of full-token inferenceMM-CDFSL · Inference costruntime (ms): 22.1 -> 9.64Improved
use most accurate setting (no masking, P=1) versus CDFSL-VMM-CDFSL · EPIC-Kitchensaccuracy: +5.23 pointsImproved
use MM-CDFSL instead of Dynamic Distillation++ on MECCANO 5-shotMECCANO · MECCANO 5-shottop-1 accuracy: 37.87 -> 37.80No clear effect
use MM-CDFSL instead of CDFSL-V on WEAR 5-shotWEAR · WEAR 5-shottop-1 accuracy: 58.28 -> 69.57Improved

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