Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908728505139200 |
|---|---|
| author | Vyas, Apoorv Chang, Heng-Jui Yang, Cheng-Fu Huang, Po-Yao Gao, Luya Richter, Julius Chen, Sanyuan Le, Matt Dollár, Piotr Feichtenhofer, Christoph Lee, Ann Hsu, Wei-Ning |
| author_facet | Vyas, Apoorv Chang, Heng-Jui Yang, Cheng-Fu Huang, Po-Yao Gao, Luya Richter, Julius Chen, Sanyuan Le, Matt Dollár, Piotr Feichtenhofer, Christoph Lee, Ann Hsu, Wei-Ning |
| contents | We introduce Perception Encoder Audiovisual, PE-AV, a new family of encoders for audio and video understanding trained with scaled contrastive learning. Built on PE, PE-AV makes several key contributions to extend representations to audio, and natively support joint embeddings across audio-video, audio-text, and video-text modalities. PE-AV's unified cross-modal embeddings enable novel tasks such as speech retrieval, and set a new state of the art across standard audio and video benchmarks. We unlock this by building a strong audiovisual data engine that synthesizes high-quality captions for O(100M) audio-video pairs, enabling large-scale supervision consistent across modalities. Our audio data includes speech, music, and general sound effects-avoiding single-domain limitations common in prior work. We exploit ten pairwise contrastive objectives, showing that scaling cross-modality and caption-type pairs strengthens alignment and improves zero-shot performance. We further develop PE-A-Frame by fine-tuning PE-AV with frame-level contrastive objectives, enabling fine-grained audio-frame-to-text alignment for tasks such as sound event detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_19687 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning Vyas, Apoorv Chang, Heng-Jui Yang, Cheng-Fu Huang, Po-Yao Gao, Luya Richter, Julius Chen, Sanyuan Le, Matt Dollár, Piotr Feichtenhofer, Christoph Lee, Ann Hsu, Wei-Ning Sound Computer Vision and Pattern Recognition Machine Learning We introduce Perception Encoder Audiovisual, PE-AV, a new family of encoders for audio and video understanding trained with scaled contrastive learning. Built on PE, PE-AV makes several key contributions to extend representations to audio, and natively support joint embeddings across audio-video, audio-text, and video-text modalities. PE-AV's unified cross-modal embeddings enable novel tasks such as speech retrieval, and set a new state of the art across standard audio and video benchmarks. We unlock this by building a strong audiovisual data engine that synthesizes high-quality captions for O(100M) audio-video pairs, enabling large-scale supervision consistent across modalities. Our audio data includes speech, music, and general sound effects-avoiding single-domain limitations common in prior work. We exploit ten pairwise contrastive objectives, showing that scaling cross-modality and caption-type pairs strengthens alignment and improves zero-shot performance. We further develop PE-A-Frame by fine-tuning PE-AV with frame-level contrastive objectives, enabling fine-grained audio-frame-to-text alignment for tasks such as sound event detection. |
| title | Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning |
| topic | Sound Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2512.19687 |