cs.CV（2024-08-11）
📊 共 7 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱三：空间感知与语义 (Perception & Semantics) (3)
支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1)
支柱二：RL算法与架构 (RL & Architecture) (2)
🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | An analysis of HOI: using a training-free method with multimodal visual foundation models when only the test set is available, without the training set | 提出无训练集情况下的多模态视觉模型用于人-物交互识别 | open-vocabulary open vocabulary human-object interaction | ||
| 2 | Egocentric Vision Language Planning | EgoPlan：利用自中心视觉语言规划提升具身智能体长时任务能力 | optical flow egocentric egocentric vision | ||
| 3 | Efficient and Versatile Robust Fine-Tuning of Zero-shot Models | 提出R-Adapter，高效且泛化性强地微调零样本模型，提升OOD鲁棒性。 | open-vocabulary open vocabulary |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Advancing Re-Ranking with Multimodal Fusion and Target-Oriented Auxiliary Tasks in E-Commerce Search | 提出ARMMT模型，利用多模态融合和目标导向辅助任务提升电商搜索重排序效果。 | multimodal | ||
| 5 | A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot | 提出OneShotLP，一种免训练的视频车牌跟踪与识别框架，仅需单样本。 | large language model multimodal | ✅ |
🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Neural Architecture Search based Global-local Vision Mamba for Palm-Vein Recognition | 提出基于神经架构搜索的全局-局部Vision Mamba用于掌纹识别 | Mamba | ||
| 7 | Contrastive masked auto-encoders based self-supervised hashing for 2D image and 3D point cloud cross-modal retrieval | 提出基于对比掩码自编码器的自监督哈希方法，用于2D图像和3D点云跨模态检索 | masked autoencoder contrastive learning |