Research map / Vision-language and multimodal / Cross-modal learning
Cross-Modal Attention Network for Temporal Inconsistent Audio-Visual Event Localization
Read the paperCheck 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 |
|---|---|---|---|
| fuse audio and visual inputs vs single modality (ablation) | event localization model · AVE | accuracy: 59.5/56.5 -> 71.4/69.0 | Helped |
| add cross-modal adaptive co-attention (ablation) | CMAN · AVE | accuracy: 73.5/71.8 -> 77.1/75.7 | Helped |
| add spatial visual attention (ablation) | CMAN · AVE | accuracy: 74.8/73.4 -> 77.1/75.7 | Helped |
| add S-att module (ablation) | CMAN · AVE | accuracy: 75.6/73.9 -> 77.1/75.7 | Helped |
| add global context vector (ablation) | CMAN · AVE | accuracy: 75.7/74.3 -> 77.1/75.7 | Helped |
| add modality sentinel vector (ablation) | CMAN · AVE | accuracy: 76.1/74.9 -> 77.1/75.7 | Helped |
| weighted spatial attention vs strongest CAM response | visual localization · AVE | accuracy: 72.3/68.8 -> 77.1/75.7 | Helped |
Closest papers by meaning
- Dense Audio-Visual Event Localization Under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration (AAAI 2025 · similarity 0.90)
- Audio-Visual Semantic Graph Network for Audio-Visual Event Localization (CVPR 2025 · similarity 0.89)
- Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds (CVPR 2025 · similarity 0.89)
- Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization (NeurIPS 2025 · similarity 0.87)
- Towards Open-Vocabulary Audio-Visual Event Localization (CVPR 2025 · similarity 0.87)
- Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment (CVPR 2025 · similarity 0.87)
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.