热点
关于我们
xx
xx
"
视听同步
" 相关文章
SyncLipMAE: Contrastive Masked Pretraining for Audio-Visual Talking-Face Representation
cs.AI updates on arXiv.org
2025-10-14T04:08:31.000000Z
AI learns how vision and sound are connected, without human intervention
MIT News - Computer Science and Artificial Intelligence Laboratory
2025-09-25T10:00:59.000000Z
Controllable Video-to-Music Generation with Multiple Time-Varying Conditions
cs.AI updates on arXiv.org
2025-07-29T04:21:56.000000Z
Google DeepMind Introduces Video-to-Audio V2A Technology: Synchronizing Audiovisual Generation
MarkTechPost@AI
2024-06-23T23:01:39.000000Z