Research map / Vision-language and multimodal / Cross-modal learning
Contrastive Positive Sample Propagation Along the Audio-Visual Event Line
Jinxing Zhou, Dan Guo, Meng Wang
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 the PSP module (ablation) | localization network · AVE (fully supervised) | accuracy (%): 73.7 -> 77.8 | Improved |
| add the PSP module (ablation) | localization network · AVE (weakly supervised) | accuracy (%): 70.2 -> 73.5 | Improved |
| prune weak and negative connections instead of keeping all (tau) (ablation) | PSP · AVE (fully supervised) | accuracy (%): 75.9 -> 77.8 | Improved |
| prune weak and negative connections instead of keeping all (tau) (ablation) | PSP · AVE (weakly supervised) | accuracy (%): 71.2 -> 73.5 | Improved |
| also prune weak connections, not only negative ones (ablation) | PSP · AVE (fully supervised) | accuracy (%): 76.0 -> 77.8 | Improved |
| add self-attention before the Bi-LSTMs (ablation) | PSP · AVE (fully supervised) | accuracy (%): 77.8 -> 75.4 | Hurt |
| add self-attention before the Bi-LSTMs (ablation) | PSP · AVE (weakly supervised) | accuracy (%): 73.5 -> 70.8 | Hurt |
| add L_avpsp pair-level loss (ablation) | PSP · AVE (fully supervised) | accuracy (%): 76.6 -> 77.8 | Improved |
| add L_avpsp pair-level loss (ablation) | AVEL · AVE (fully supervised) | accuracy (%): 69.8 -> 71.3 | Improved |
| add weighting branch (extra FC) (ablation) | PSP · AVE (weakly supervised) | accuracy (%): 71.6 -> 73.5 | Improved |
| add weighting branch (extra FC) (ablation) | AVEL · AVE (weakly supervised) | accuracy (%): 66.9 -> 69.2 | Improved |
| add segment-level PSA_S contrastive loss (ablation) | PSP · VGGSound-AVEL100k (fully supervised) | accuracy (%): 58.3 -> 59.6 | Improved |
Closest papers by meaning
- Positive Sample Propagation Along the Audio-Visual Event Line (CVPR 2021 · similarity 0.94)
- Enhancing Sound Source Localization via False Negative Elimination (TPAMI 2024 · similarity 0.89)
- Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning (CVPR 2023 · similarity 0.88)
- Robust Audio-Visual Contrastive Learning for Proposal-Based Self-Supervised Sound Source Localization in Videos (TPAMI 2024 · similarity 0.88)
- Towards Open-Vocabulary Audio-Visual Event Localization (CVPR 2025 · similarity 0.86)
- Dense Audio-Visual Event Localization Under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration (AAAI 2025 · 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.
