Research map / Video / Video segmentation and tracking
MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing
Langyu Wang, Bingke Zhu, Yingying Chen, Yiyuan Zhang, Ming Tang, Jinqiao 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 cross modality random combination (CMRC) augmentation (ablation) | MUG · LLP segment-level | Type@AV: 62.2 -> 63.9 | Improved |
| add CMRC augmentation (ablation) | MUG · LLP event-level | Type@AV: 57.4 -> 59.6 | Improved |
| add Mamba-based attention (MBA) (ablation) | MUG · LLP segment-level | Type@AV: 63.3 -> 63.9 | Improved |
| add adaptive mamba fusion (AMF) (ablation) | MUG · LLP segment-level | Type@AV: 63.4 -> 63.9 | Improved |
| add Mamba feature enhancement (MFE) (ablation) | MUG · LLP segment-level | Type@AV: 62.4 -> 63.9 | Improved |
| add pseudo-label semantic interaction module (PLSIM) (ablation) | MUG · LLP segment-level | Type@AV: 63.7 -> 63.9 | Improved |
| add CMRC to HAN | HAN · LLP segment-level | Type@AV: 54.0 -> 54.9 | Improved |
| add CMRC to MGN | MGN · LLP segment-level | Type@AV: 55.5 -> 57.3 | Improved |
| add CMRC to JoMoLD | JoMoLD · LLP segment-level | Type@AV: 60.8 -> 61.7 | Improved |
| increase CMRC data from 1585 (Batch1) to 6080 (Batch4) samples (ablation) | MUG · LLP segment-level | Type@AV: 62.7 -> 63.9 | Improved |
| double generated data again (Batch4 to Batch5) (ablation) | MUG · LLP segment-level | Event@AV: 64.7 -> 64.9 | Mixed |
| replace Mamba with Transformer attention (ablation) | MUG · LLP segment-level | Type@AV: 63.9 -> 62.7 | Hurt |
Closest papers by meaning
- Weakly-Supervised Audio-Visual Video Parsing with Prototype-based Pseudo-Labeling (CVPR 2024 · similarity 0.92)
- UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing (CVPR 2025 · similarity 0.92)
- Multimodal Class-aware Semantic Enhancement Network for Audio-Visual Video Parsing (AAAI 2025 · similarity 0.88)
- PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling (NeurIPS 2025 · similarity 0.87)
- Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding (AAAI 2025 · similarity 0.86)
- Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation (CVPR 2024 · similarity 0.86)
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.
