all AI news
Unsupervised Audio-Visual Segmentation with Modality Alignment
March 22, 2024, 4:45 a.m. | Swapnil Bhosale, Haosen Yang, Diptesh Kanojia, Jiangkang Deng, Xiatian Zhu
cs.CV updates on arXiv.org arxiv.org
Abstract: Audio-Visual Segmentation (AVS) aims to identify, at the pixel level, the object in a visual scene that produces a given sound. Current AVS methods rely on costly fine-grained annotations of mask-audio pairs, making them impractical for scalability. To address this, we introduce unsupervised AVS, eliminating the need for such expensive annotation. To tackle this more challenging problem, we propose an unsupervised learning method, named Modality Correspondence Alignment (MoCA), which seamlessly integrates off-the-shelf foundation models like …
abstract alignment annotations arxiv audio avs cs.ai cs.cv current fine-grained identify making object pixel scalability segmentation sound them type unsupervised visual
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote