Research map / Vision-language and multimodal / Cross-modal learning
Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation
Jingqi Tian, Yiheng Du, Haoji Zhang, Yuji Wang, Isaac Ning Lee, Xulong Bai, Tianrui Zhu, Jingxuan Niu, Yansong Tang
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 Query Module (prototype-bank queries) (ablation) | baseline · AVS-MS3 | J&F: 69.71 -> 71.89 | Improved |
| add Audio Query Module (ablation) | baseline · AVSS | J&F: 48.63 -> 49.80 | Improved |
| add Contrastive Optimization Module (ablation) | baseline+AQM · AVS-MS3 | J&F: 71.89 -> 74.07 | Improved |
| add Contrastive Optimization Module (ablation) | baseline+AQM · AVSS | J&F: 49.80 -> 51.70 | Improved |
| add delayed bidirectional alignment module (AVAM) (ablation) | baseline · AVS-MS3 | J&F: 69.71 -> 73.16 | Improved |
| add AQM and COM on top of AVAM (ablation) | AVAM · AVS-MS3 | J&F: 73.16 -> 76.01 | Improved |
| add AQM and COM on top of AVAM (ablation) | AVAM · AVSS | J&F: 51.45 -> 52.94 | Improved |
| inject alignment only in blocks 3,4 instead of all blocks 1,2,3,4 (ablation) | DDAVS · AVS-MS3 | J&F: 72.57 -> 76.01 | Improved |
| inject alignment in blocks 3,4 instead of block 1 only (ablation) | DDAVS · AVS-MS3 | J&F: 68.37 -> 76.01 | Improved |
| inject in blocks 3,4 instead of block 3 only (ablation) | DDAVS · AVS-MS3 | J&F: 74.27 -> 76.01 | Improved |
| use HTSAT audio encoder instead of VGGish (ablation) | DDAVS (MiT-B5) · AVS-MS3 | J&F: 74.45 -> 76.01 | Improved |
| use MiT-B5 visual backbone instead of PVTv2-B5 (ablation) | DDAVS (HTSAT) · AVS-MS3 | J&F: 74.69 -> 76.01 | Improved |
Closest papers by meaning
- Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment (CVPR 2025 · similarity 0.93)
- Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation (CVPR 2024 · similarity 0.91)
- Improving Audio-Visual Segmentation with Bidirectional Generation (AAAI 2024 · similarity 0.91)
- Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics (CVPR 2025 · similarity 0.91)
- Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation (CVPR 2024 · similarity 0.90)
- Seeing Speech and Sound: Distinguishing and Locating Audio Sources in Visual Scenes (CVPR 2025 · similarity 0.90)
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.
