Research map / Vision-language and multimodal / Cross-modal learning
How Do Optical Flow and Textual Prompts Collaborate to Assist in Audio-Visual Semantic Segmentation?
Yujian Lee, Peng Gao, Yongqi Xu, Wentao Fan
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 optical-flow pre-mask (ablation) | AAVS · AVSBench MS3 | mIoU: 67.3 -> 69.5 | Improved |
| add optical-flow pre-mask (ablation) | AAVS · AVSBench S4 | mIoU: 83.2 -> 84.1 | Improved |
| add optical-flow pre-mask (ablation) | AAVS · AVSBench AVSS | mIoU: 48.5 -> 49.2 | Improved |
| add post-mask loss on top of pre-mask (ablation) | AAVS + pre-mask · AVSBench MS3 | mIoU: 69.5 -> 70.2 | Improved |
| add post-mask loss to full model (ablation) | SSP · AVSBench MS3 | mIoU: 70.4 -> 72.3 | Improved |
| add textual prompts without VTA (ablation) | AAVS · AVSBench MS3 | mIoU: 67.3 -> 68.1 | Improved |
| add textual prompts without VTA (ablation) | AAVS · AVSBench AVSS | F-score: 53.2 -> 53.0 | No clear effect |
| add VTA to textual prompts (ablation) | AAVS + textual prompts · AVSBench MS3 | mIoU: 68.1 -> 69.8 | Improved |
| add VTA to textual prompts (ablation) | AAVS + textual prompts · AVSBench MS3 | F-score: 78.9 -> 83.3 | Improved |
| add textual prompts and VTA to pre-mask and post-mask (ablation) | SSP · AVSBench MS3 | mIoU: 70.2 -> 72.3 | Improved |
| replace simple cross-attention with VTA (ablation) | SSP · AVSBench | mIoU: +1.1% mIoU, +0.5% F-score | Improved |
| improve textual prompt quality (worst A to best D) (ablation) | SSP with VTA · AVSBench MS3 | mIoU: 2.3% and 1.2% in mIoU and F-score | Improved |
Closest papers by meaning
- 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 0.90)
- Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation (CVPR 2024 · similarity 0.90)
- TSAM: Temporal SAM Augmented with Multimodal Prompts for Referring Audio-Visual Segmentation (CVPR 2025 · similarity 0.89)
- Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment (CVPR 2025 · similarity 0.89)
- SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes (CVPR 2025 · similarity 0.88)
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.
