Research map / Vision-language and multimodal / Cross-modal learning
TriBERT: Human-centric Audio-visual Representation Learning
Tanzila Rahman, Mengyu Yang, Leonid Sigal
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 |
|---|---|---|---|
| use transformer-based instead of pre-transformer embeddings (ablation) | TriBERT retrieval · Audio->Vision | top-1 accuracy: 1.43 -> 68.10 | Improved |
| use transformer-based instead of pre-transformer embeddings (ablation) | TriBERT retrieval · Vision->Audio | top-1 accuracy: 4.76 -> 59.52 | Improved |
| use transformer-based instead of pre-transformer embeddings (ablation) | TriBERT retrieval · Audio->Pose | top-1 accuracy: 2.38 -> 63.81 | Improved |
| use transformer-based instead of pre-transformer embeddings (ablation) | TriBERT retrieval · Pose->Audio | top-1 accuracy: 1.90 -> 54.29 | Improved |
| use transformer-based instead of pre-transformer embeddings (ablation) | TriBERT retrieval · Vision+Audio->Pose | top-1 accuracy: 3.33 -> 54.29 | Improved |
| query with vision+audio instead of audio alone | TriBERT retrieval · MUSIC21 pose retrieval | top-1 accuracy: 63.81 -> 54.29 | Mixed |
| TriBERT vs MUSIC-Gesture, single-source | TriBERT · MUSIC21 single-source | SDR: 8.08 -> 10.09 | Improved |
| TriBERT vs MUSIC-Gesture, multi-source | TriBERT · MUSIC21 multi-source | SDR: 6.72 -> 7.66 | Improved |
| TriBERT after fine-tuning vs best prior baseline | TriBERT · MUSIC | SDR: 9.29 -> 12.34 | Improved |
Closest papers by meaning
- From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation (ICML 2024 · similarity 0.90)
- Seeing Speech and Sound: Distinguishing and Locating Audio Sources in Visual Scenes (CVPR 2025 · similarity 0.89)
- Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation (CVPR 2025 · similarity 0.89)
- Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer (AAAI 2024 · similarity 0.88)
- Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment (CVPR 2025 · similarity 0.88)
- CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment (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.
