Research map / Video / Video segmentation and tracking
Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing
Haoyue Cheng, Zhaoyang Liu, Hang Zhou, Chen Qian, Wayne Wu, Limin 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 |
|---|---|---|---|
| use estimated noise ratios instead of constant 0.5 (ablation) | JoMoLD · LLP segment-level | Visual F: 58.3 -> 63.8 | Improved |
| use estimated noise ratios instead of constant 0.5 (ablation) | JoMoLD · LLP segment-level | Type@AV F: 56.6 -> 60.8 | Improved |
| remove cross-modal attention from noise estimator (ablation) | JoMoLD · LLP segment-level | Visual F: 55.9 -> 63.8 | Improved |
| skip cross-modal attention when computing forward loss (ablation) | JoMoLD · LLP segment-level | Type@AV F: 58.9 -> 60.8 | Improved |
| use joint-modal instead of intra-modal label denoising (ablation) | JoMoLD · LLP segment-level | Visual F: 58.5 -> 63.8 | Improved |
| use joint-modal instead of intra-modal label denoising (ablation) | JoMoLD · LLP segment-level | Type@AV F: 56.6 -> 60.8 | Improved |
| denoise both modalities instead of audio only (ablation) | JoMoLD · LLP segment-level | Visual F: 53.2 -> 63.8 | Improved |
| denoise both modalities instead of visual only (ablation) | JoMoLD · LLP segment-level | Type@AV F: 60.0 -> 60.8 | Improved |
| add warm-up of noise ratios (0.9) (ablation) | JoMoLD · LLP segment-level | Type@AV F: 60.1 -> 60.8 | Improved |
| vary thresholds theta_a and theta_v within range (ablation) | JoMoLD · LLP segment-level | Type@AV F: 60.5 - 60.8 near optimum | No clear effect |
| batch size 128 instead of 32 (ablation) | JoMoLD · LLP segment-level | Type@AV F: 60.3 -> 60.8 | Improved |
| apply JoMoLD to AVSlowFast backbone | AVSlowFast · LLP segment-level | Visual F: 50.8 -> 60.1 | Improved |
Closest papers by meaning
- UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing (CVPR 2025 · similarity 0.91)
- Weakly-Supervised Audio-Visual Video Parsing with Prototype-based Pseudo-Labeling (CVPR 2024 · similarity 0.91)
- Multimodal Class-aware Semantic Enhancement Network for Audio-Visual Video Parsing (AAAI 2025 · similarity 0.88)
- Local-Global Multi-Modal Distillation for Weakly-Supervised Temporal Video Grounding (AAAI 2024 · similarity 0.88)
- LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos (CVPR 2025 · similarity 0.87)
- Dense Audio-Visual Event Localization Under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration (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.
