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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add audio-based attention to the visual encoder (ablation) | Audio-adaptive encoder · EPIC-Kitchens | top-1 accuracy: 48.0 -> 51.2 | Improved |
| add audio-based attention to the visual encoder (ablation) | Audio-adaptive encoder · CharadesEgo | mAP: 23.1 -> 23.5 | Improved |
| add absent-activity learning (ablation) | Audio-adaptive encoder · EPIC-Kitchens | top-1 accuracy: 51.2 -> 53.7 | Improved |
| add absent-activity learning (ablation) | Audio-adaptive encoder · CharadesEgo | mAP: 23.5 -> 24.4 | Improved |
| add audio-balanced learning (ablation) | Audio-adaptive encoder · EPIC-Kitchens | top-1 accuracy: 53.7 -> 55.7 | Improved |
| add audio-balanced learning (ablation) | Audio-adaptive encoder · CharadesEgo | mAP: 24.4 -> 25.0 | Improved |
| add a vanilla multi-modal transformer (ablation) | Audio-adaptive encoder · EPIC-Kitchens | top-1 accuracy: 55.7 -> 56.1 | Improved |
| add a vanilla multi-modal transformer (ablation) | Audio-adaptive encoder · CharadesEgo | mAP: 25.0 -> 25.0 | No clear effect |
| add a domain embedding (ablation) | Vanilla multi-modal transformer · EPIC-Kitchens | top-1 accuracy: 56.1 -> 57.2 | Improved |
| add a domain embedding (ablation) | Vanilla multi-modal transformer · CharadesEgo | mAP: 25.0 -> 25.4 | Improved |
| replace the plain audio features and learnable class token with an audio-adaptive class token (ablation) | Multi-modal transformer with domain embedding · EPIC-Kitchens | top-1 accuracy: 57.2 -> 59.2 | Improved |
| replace the plain audio features and learnable class token with an audio-adaptive class token (ablation) | Multi-modal transformer with domain embedding · CharadesEgo | mAP: 25.4 -> 26.3 | Improved |
Closest papers by meaning
- Interact Before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition (CVPR 2022 · similarity 0.87)
- Learning State-Aware Visual Representations from Audible Interactions (NeurIPS 2022 · similarity 0.86)
- TIM: A Time Interval Machine for Audio-Visual Action Recognition (CVPR 2024 · similarity 0.85)
- Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds (CVPR 2025 · similarity 0.85)
- Language-Guided Audio-Visual Learning for Long-Term Sports Assessment (CVPR 2025 · similarity 0.85)
- SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos (CVPR 2024 · similarity 0.85)
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.
