AI Paper Atlas

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

Audio-Adaptive Activity Recognition Across Video Domains

Yunhua Zhang, Hazel Doughty, Ling Shao, Cees G. M. Snoek

CVPR 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 32 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 audio-based attention to the visual encoder (ablation)Audio-adaptive encoder · EPIC-Kitchenstop-1 accuracy: 48.0 -> 51.2Improved
add audio-based attention to the visual encoder (ablation)Audio-adaptive encoder · CharadesEgomAP: 23.1 -> 23.5Improved
add absent-activity learning (ablation)Audio-adaptive encoder · EPIC-Kitchenstop-1 accuracy: 51.2 -> 53.7Improved
add absent-activity learning (ablation)Audio-adaptive encoder · CharadesEgomAP: 23.5 -> 24.4Improved
add audio-balanced learning (ablation)Audio-adaptive encoder · EPIC-Kitchenstop-1 accuracy: 53.7 -> 55.7Improved
add audio-balanced learning (ablation)Audio-adaptive encoder · CharadesEgomAP: 24.4 -> 25.0Improved
add a vanilla multi-modal transformer (ablation)Audio-adaptive encoder · EPIC-Kitchenstop-1 accuracy: 55.7 -> 56.1Improved
add a vanilla multi-modal transformer (ablation)Audio-adaptive encoder · CharadesEgomAP: 25.0 -> 25.0No clear effect
add a domain embedding (ablation)Vanilla multi-modal transformer · EPIC-Kitchenstop-1 accuracy: 56.1 -> 57.2Improved
add a domain embedding (ablation)Vanilla multi-modal transformer · CharadesEgomAP: 25.0 -> 25.4Improved
replace the plain audio features and learnable class token with an audio-adaptive class token (ablation)Multi-modal transformer with domain embedding · EPIC-Kitchenstop-1 accuracy: 57.2 -> 59.2Improved
replace the plain audio features and learnable class token with an audio-adaptive class token (ablation)Multi-modal transformer with domain embedding · CharadesEgomAP: 25.4 -> 26.3Improved

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