Research map / Vision-language and multimodal / Cross-modal learning
Cross-Modal Background Suppression for Audio-Visual Event Localization
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use cross-modal background suppression and gated attention | AVE localization · AVE supervised, VGG-like + VGG-19 | accuracy: 77.8 -> 79.3 | Helped |
| use cross-modal background suppression and gated attention | AVE localization · AVE supervised, VGG-like + Res-151 | accuracy: 78.3 -> 79.7 | Helped |
| use cross-modal background suppression and gated attention | AVE localization · AVE weakly supervised, VGG-like + VGG-19 | accuracy: 73.5 -> 74.2 | Helped |
| use cross-modal background suppression and gated attention | AVE localization · AVE weakly supervised, VGG-like + Res-151 | accuracy: 75.3 -> 76.0 | Helped |
| add cross-modal gated attention (ablation) | CMBS · AVE supervised and weakly supervised | accuracy: 78.07 -> 79.30; 71.91 -> 74.22 | Helped |
| add self-attention (ablation) | CMBS · AVE supervised and weakly supervised | accuracy: 77.62 -> 79.30; 71.29 -> 74.22 | Helped |
| add time-level background suppression (ablation) | CMBS · AVE supervised and weakly supervised | accuracy: 77.93 -> 79.30; 73.45 -> 74.22 | Helped |
| add cross-attention (ablation) | CMBS · AVE supervised and weakly supervised | accuracy: 78.10 -> 79.30; 72.03 -> 74.22 | Helped |
| add event-level background suppression (ablation) | CMBS · AVE supervised and weakly supervised | accuracy: 78.30 -> 79.30; 73.57 -> 74.22 | Helped |
| use TBS gate loss without applying feature suppression (α = 0) (ablation) | CMBS · AVE supervised | accuracy: 77.93 -> 78.37 | Helped |
| increase TBS suppression strength from α = 0.2 to α = 0.3 (ablation) | CMBS · AVE supervised | accuracy: 79.30 -> 78.45 | Hurt |
| add the audio EBS gate (ablation) | CMBS · AVE supervised and weakly supervised | accuracy: 79.05 -> 79.30; 73.83 -> 74.22 | Helped |
Closest papers by meaning
- Towards Open-Vocabulary Audio-Visual Event Localization (CVPR 2025 · similarity 0.89)
- Audio-Visual Semantic Graph Network for Audio-Visual Event Localization (CVPR 2025 · similarity 0.89)
- Dense Audio-Visual Event Localization Under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration (AAAI 2025 · similarity 0.88)
- Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds (CVPR 2025 · similarity 0.88)
- LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos (CVPR 2025 · similarity 0.86)
- CrossMAE: Cross-Modality Masked Autoencoders for Region-Aware Audio-Visual Pre-Training (CVPR 2024 · similarity 0.86)
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.