cs.CV（2024-05-22）
📊 共 3 篇论文
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | From CNNs to Transformers in Multimodal Human Action Recognition: A Survey | 综述多模态人体行为识别中CNN到Transformer的演变与融合策略 | multimodal | ||
| 2 | More Distinctively Black and Feminine Faces Lead to Increased Stereotyping in Vision-Language Models | 视觉语言模型中更具种族和性别特征的面孔导致更强的刻板印象 | large language model |
🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 3 | GS-ROR$^2$: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstruction | 提出GS-ROR$^2$，双向引导3DGS与SDF，实现反射物体的可重光照与高质量重建。 | 3D gaussian splatting 3DGS gaussian splatting |