Research map / Vision-language and multimodal / Cross-modal learning
Dual Perspective Network for Audio-Visual Event Localization
Varshanth Rao, Md Ibrahim Khalil, Haoda Li, Peng Dai, Juwei Lu
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 Replicate augmentation (ablation) | DPNet · O-AVE (SEL) | accuracy (%): 77.50 -> 78.08 | Improved |
| add Link on top of Replicate (ablation) | DPNet · O-AVE (SEL) | accuracy (%): 78.08 -> 78.93 | Improved |
| add Replicate augmentation (ablation) | DPNet · C-AVE (SEL) | accuracy (%): 78.08 -> 78.78 | Improved |
| add Link on top of Replicate (ablation) | DPNet · C-AVE (SEL) | accuracy (%): 78.78 -> 79.68 | Improved |
| use RGCT instead of RGAT in a graph-only network (ablation) | graph-only network · O-AVE (SEL) | accuracy (%): 60.47 -> 67.13 | Improved |
| add RGCT graph perspective to a TCN-only network sequentially (TCN -> RGCT) (ablation) | TCN Only · O-AVE (WSEL) | accuracy (%): 70.20 -> 59.40 | Hurt |
| combine TCN and RGCT in alternating DPBlocks (Graph First) instead of TCN only (ablation) | TCN Only · O-AVE (WSEL) | accuracy (%): 70.20 -> 74.50 | Improved |
| serial DPBlock instead of parallel PPBlock (ablation) | DPNet · O-AVE (WSEL) | accuracy (%): 71.42 -> 74.50 | Improved |
| serial DPBlock instead of parallel PPBlock (ablation) | DPNet · O-AVE (SEL) | accuracy (%): 77.36 -> 78.93 | Improved |
| put RGCT first instead of TCN first within DPBlock (ablation) | DPNet · O-AVE (SEL) | accuracy (%): 78.60 -> 78.93 | Improved |
| put RGCT first instead of TCN first within DPBlock (ablation) | DPNet · O-AVE (WSEL) | accuracy (%): 73.70 -> 74.50 | Improved |
| add Replicate and Link to weaker base networks (ablation) | RGAT Only · O-AVE (SEL) | accuracy (%): 56.11 -> 60.47 | Improved |
Closest papers by meaning
- Audio-Visual Semantic Graph Network for Audio-Visual Event Localization (CVPR 2025 · similarity 0.92)
- Towards Open-Vocabulary Audio-Visual Event Localization (CVPR 2025 · similarity 0.91)
- Dense Audio-Visual Event Localization Under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration (AAAI 2025 · similarity 0.91)
- Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds (CVPR 2025 · similarity 0.87)
- Multimodal Class-aware Semantic Enhancement Network for Audio-Visual Video Parsing (AAAI 2025 · similarity 0.87)
- Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding (AAAI 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.
