Research map / Vision-language and multimodal / Cross-modal learning
Audio-Visual Event Localization in Unconstrained Videos
Yapeng Tian, Jing Shi, Bochen Li, Zhiyao Duan, Chenliang Xu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add audio features to visual-only model (ablation) | visual LSTM model · AVE event localization | accuracy (%): 55.3 -> 71.4 | Improved |
| add visual features to audio-only model (ablation) | audio LSTM model · AVE event localization | accuracy (%): 59.5 -> 71.4 | Improved |
| add audio-guided visual attention to visual model (ablation) | V model · AVE event localization | accuracy (%): 55.3 -> 58.6 | Improved |
| add audio-guided visual attention to audio-visual model (ablation) | A+V model · AVE event localization | accuracy (%): 71.4 -> 72.7 | Improved |
| add audio-guided visual attention to weakly supervised audio-visual model (ablation) | W-A+V · AVE event localization (weakly supervised) | accuracy (%): 63.7 -> 66.7 | Improved |
| use fusion after LSTM (late) instead of before (early) (ablation) | Concat fusion · AVE event localization | accuracy (%): 61.0 -> 72.7 | Improved |
| use late fusion instead of decision fusion (ablation) | DMRN · AVE event localization | accuracy (%): 70.4 -> 73.1 | Improved |
| use DMRN instead of Concat in late fusion | fusion network · AVE event localization | accuracy (%): 72.7 -> 73.1 | Improved |
| use DMRN instead of MRN in late fusion | fusion network · AVE event localization | accuracy (%): 70.8 -> 73.1 | Improved |
| use DMRFE ensemble instead of DMRN | DMRN · AVE event localization | accuracy (%): 73.1 -> 73.3 | Improved |
| stack multiple residual blocks in fusion network (ablation) | MRN and DMRN · AVE event localization | accuracy (%) | No clear effect |
| add C3D temporal visual features (ablation) | visual features · AVE event localization | accuracy (%) | No clear effect |
Closest papers by meaning
- Dual Attention Matching for Audio-Visual Event Localization (ICCV 2019 · similarity 0.94)
- Dense Audio-Visual Event Localization Under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration (AAAI 2025 · similarity 0.94)
- Towards Open-Vocabulary Audio-Visual Event Localization (CVPR 2025 · similarity 0.92)
- Audio-Visual Semantic Graph Network for Audio-Visual Event Localization (CVPR 2025 · similarity 0.92)
- Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds (CVPR 2025 · similarity 0.91)
- Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding (AAAI 2025 · similarity 0.89)
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.
