3 papers
cs.CV2026
HCL-FF: Hierarchical and Contrastive Learning for Forward-Forward Algorithm
Jie-En Yao, Hong-En Chen, C. -C. Jay Kuo
Deep neural networks trained with backpropagation have achieved outstanding performance in vision tasks but remain biologically implausible, computationally demanding, and difficul…
cs.CV2025
Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions
Jintang Xue, Ganning Zhao, Jie-En Yao +5
Understanding 3D scenes goes beyond simply recognizing objects; it requires reasoning about the spatial and semantic relationships between them. Current 3D scene-language models of…
cs.CV2024
TPA3D: Triplane Attention for Fast Text-to-3D Generation
Bin-Shih Wu, Hong-En Chen, Sheng-Yu Huang +1
Due to the lack of large-scale text-3D correspondence data, recent text-to-3D generation works mainly rely on utilizing 2D diffusion models for synthesizing 3D data. Since diffusio…