2 papers
cs.CV2026
SIE3D: Single-Image Expressive 3D Avatar Generation via Semantic Embedding and Perceptual Expression Loss
Zhiqi Huang, Dulongkai Cui, Jinglu Hu
Generating high-fidelity 3D head avatars from a single image is challenging, as current methods lack fine-grained, intuitive control over expressions via text. This paper proposes…
cs.AI2025
Extensible Multi-Granularity Fusion Network and Transferable Curriculum Learning for Aspect-based Sentiment Analysis
Xinran Li, Xiaowei Zhao, Yubo Zhu +8
Aspect-based Sentiment Analysis (ABSA) aims to determine sentiment polarity toward specific aspects in text. Existing methods enrich semantic and syntactic representations through…