English(EN) Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation

新算法改进了用于语音保留的面部表情操控的视觉语言模型监督

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-28 06:02

研究人员开发了一种名为个性化跨模态情感相关性学习（PCMECL）的新算法，以改进语音保留的面部表情操控。该方法通过改进视觉语言模型（VLMs）的监督来解决配对数据有限的挑战。PCMECL通过学习基于个体视觉线索的情感个性化提示，并利用特征差分来弥合视觉和语义特征分布之间的差距来实现这一点。 AI

影响通过改进基于VLM的监督和个性化，增强了面部表情操控技术。

排序理由这是一篇详细介绍特定计算机视觉任务新算法的研究论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Tianshui Chen, Yujie Zhu, Jianman Lin, Zhijing Yang, Chunmei Qing, Feng Gao, Liang Lin · 2026-04-29 04:00

Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation

arXiv:2604.25255v1 Announce Type: new Abstract: Speech-preserving facial expression manipulation (SPFEM) aims to enhance human expressiveness without altering mouth movements tied to the original speech. A primary challenge in this domain is the scarcity of paired data, namely al…
arXiv cs.CV TIER_1 English(EN) · Liang Lin · 2026-04-28 06:02

Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation

Speech-preserving facial expression manipulation (SPFEM) aims to enhance human expressiveness without altering mouth movements tied to the original speech. A primary challenge in this domain is the scarcity of paired data, namely aligned frames of the same individual with identic…