Research map / Vision-language and multimodal / Cross-modal learning
Deep Multimodal Clustering for Unsupervised Audiovisual Learning
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 ImageNet-pretrained visual supervision and keep the visual network fixed during training (ablation) | DMC · ESC-50 | accuracy: 0.798 -> 0.826 | Helped |
| Use DMC audio representations instead of raw spectrum | MLP · DCASE 2017 evaluation dataset | Segment F1: 42.8 -> 52.14 | Helped |
| Use DMC audio representations instead of raw spectrum | MLP · DCASE 2017 evaluation dataset | Segment Error: 0.94 -> 0.83 | Helped |
| Use the related rather than unrelated visual cluster for localization | DMC · Sound source localization | cIoU(0.5): 10.4 -> 67.1 | Helped |
| Use the related rather than unrelated visual cluster for localization | DMC · Sound source localization | AUC: 21.1 -> 56.8 | Helped |
| Use elaborate component-level correspondence instead of global matching | Audiovisual audio representation · DCASE 2017 evaluation dataset | Segment F1: 43.24 -> 52.14 | Helped |
Closest papers by meaning
- Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment (CVPR 2025 · similarity 0.84)
- Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering (CVPR 2024 · similarity 0.83)
- Seeing Speech and Sound: Distinguishing and Locating Audio Sources in Visual Scenes (CVPR 2025 · similarity 0.83)
- Unsupervised Audio-Visual Segmentation with Modality Alignment (AAAI 2025 · similarity 0.83)
- Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation (CVPR 2024 · similarity 0.83)
- Dense Audio-Visual Event Localization Under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration (AAAI 2025 · similarity 0.83)
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.