Research map / Detection and segmentation / Open-set and few-shot detection
Class-Aware Sounding Objects Localization via Audiovisual Correspondence
Di Hu, Yake Wei, Rui Qian, Weiyao Lin, Ruihua Song, Ji-Rong Wen
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 silent-area suppression (Prod) (ablation) | Ours · MUSIC-Synthetic | CIoU@0.3: 2.6 -> 32.3 | Improved |
| add silent-area suppression (Prod) (ablation) | Ours · VGGSound-Synthetic | CIoU@0.3: 3.1 -> 13.4 | Improved |
| add audiovisual consistency loss L_c (ablation) | Ours · MUSIC-Synthetic | CIoU@0.3: 18.0 -> 32.3 | Improved |
| add audiovisual consistency loss L_c (ablation) | Ours · Realistic DailyLife | CIoU@0.3: 20.1 -> 22.6 | Improved |
| increase clusters from 100 to 5000 (ablation) | Ours · VGGSound-Synthetic | CIoU@0.3: 13.4 -> 0.8 | Hurt |
| use 98 clusters (true category number) instead of 100 (ablation) | Ours · VGGSound (single source) | IoU@0.5: 49.5 -> 50.1 | No clear effect |
| remove 3 categories from first-stage data (ablation) | Ours · MUSIC-Synthetic | CIoU@0.3: 32.3 -> 8.4 | Hurt |
| remove 3 categories from first-stage data (ablation) | Ours · MUSIC-solo | IoU@0.5: 51.4 -> 46.7 | Hurt |
| add 15% multi-source noise to first-stage videos (ablation) | Ours · MUSIC-Synthetic | CIoU@0.3: 32.3 -> 19.3 | Hurt |
| add alternative localization-classification optimization (ablation) | Ours · VGGSound, DailyLife, MUSIC | localization | Improved |
| use ground-truth object labels (Oracle-v) instead of pseudo categories | Ours · VGGSound-Synthetic | CIoU@0.3: 13.4 -> 21.4 | Improved |
| use ground-truth audio labels (Oracle-a) instead of pseudo categories | Ours · VGGSound-Synthetic | CIoU@0.3: 13.4 -> 13.7 | No clear effect |
Closest papers by meaning
- Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching (NeurIPS 2020 · similarity 0.94)
- Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer (AAAI 2024 · similarity 0.90)
- Object-aware Sound Source Localization via Audio-Visual Scene Understanding (CVPR 2025 · similarity 0.89)
- Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment (CVPR 2025 · similarity 0.89)
- Audio-Visual Segmentation via Unlabeled Frame Exploitation (CVPR 2024 · similarity 0.88)
- Sounding that Object: Interactive Object-Aware Image to Audio Generation (ICML 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.
