Research map / Vision-language and multimodal / Cross-modal learning
Audio—Visual Segmentation
Jinxing Zhou, Jianyuan Wang, Jiayi Zhang, Weixuan Sun, Jing Zhang, Stan Birchfield, Dan Guo, Lingpeng Kong, Meng Wang, Yiran Zhong
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 TPAVI module (ablation) | AVS (PVT-v2) · AVSBench S4 | M_J: .778 -> .787 | Improved |
| add TPAVI module (ablation) | AVS (ResNet50) · AVSBench S4 | M_J: .701 -> .728 | Improved |
| add TPAVI module (ablation) | AVS (PVT-v2) · AVSBench MS3 | M_J: .482 -> .531 | Improved |
| add TPAVI instead of simple A+V feature addition (ablation) | AVS (PVT-v2) · AVSBench S4 | M_J: .777 -> .787 | Improved |
| add L_AVM-AV loss to BCE (ablation) | AVS (ResNet50) · AVSBench MS3 | M_J: .466 -> .479 | Improved |
| add L_AVM-AV loss to BCE (ablation) | AVS (PVT-v2) · AVSBench MS3 | M_F: .626 -> .645 | Improved |
| add L_AVM-VV loss to BCE (ablation) | AVS (ResNet50) · AVSBench MS3 | M_J: .466 -> .467 | No clear effect |
| apply TPAVI at all four stages instead of only stage 4 (ablation) | AVS (PVT-v2) · AVSBench MS3 | M_J: 0.490 to 0.540 | Improved |
| apply TPAVI at stage 4 only instead of stage 3 only (ablation) | AVS (PVT-v2) · AVSBench S4 | M_J: .780 -> .777 | Hurt |
| pretrain on Single-source subset (ablation) | AVS (PVT-v2) with TPAVI · AVSBench MS3 | M_J: 0.540 to 0.573 | Improved |
| pretrain on Single-source subset (ablation) | AVS (ResNet50) with TPAVI · AVSBench MS3 | M_J: 0.479 to 0.543 | Improved |
| pretrain on Single-source subset (ablation) | AVS (PVT-v2) without TPAVI · AVSBench MS3 | M_J: 0.482 to 0.506 | Improved |
Closest papers by meaning
- Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation (CVPR 2024 · similarity 0.94)
- Improving Audio-Visual Segmentation with Bidirectional Generation (AAAI 2024 · similarity 0.93)
- Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics (CVPR 2025 · similarity 0.92)
- AVSegFormer: Audio-Visual Segmentation with Transformer (AAAI 2024 · similarity 0.92)
- Audio-Visual Instance Segmentation (CVPR 2025 · similarity 0.92)
- Revisiting Audio-Visual Segmentation with Vision-Centric Transformer (CVPR 2025 · similarity 0.91)
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.
