cs.CV(2024-07-01)
📊 共 3 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱九:具身大模型 (Embodied Foundation Models) (1)
支柱五:交互与反应 (Interaction & Reaction) (1)
支柱二:RL算法与架构 (RL & Architecture) (1 🔗1)
🔬 支柱九:具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context Learning | 多模态上下文学习:通过模态分析指导演示策略,提升模型性能 | large language model multimodal |
🔬 支柱五:交互与反应 (Interaction & Reaction) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 2 | From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos | CATS框架:端到端视频多人HOI识别,融合几何与视觉特征建模场景交互。 | human-object interaction HOI |
🔬 支柱二:RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 3 | Learning Robust 3D Representation from CLIP via Dual Denoising | 提出Dual Denoising框架,提升CLIP在3D表示学习中的鲁棒性和泛化性 | representation learning distillation | ✅ |