cs.CV(2023-11-08)
📊 共 12 篇论文 | 🔗 3 篇有代码
🎯 兴趣领域导航
支柱二:RL算法与架构 (RL & Architecture) (5 🔗2)
支柱三:空间感知与语义 (Perception & Semantics) (3)
支柱九:具身大模型 (Embodied Foundation Models) (3 🔗1)
支柱五:交互与反应 (Interaction & Reaction) (1)
🔬 支柱二:RL算法与架构 (RL & Architecture) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Social Motion Prediction with Cognitive Hierarchies | 提出认知层次框架以解决社会运动预测问题 | reinforcement learning imitation learning motion prediction | ✅ | |
| 2 | SS-MAE: Spatial-Spectral Masked Auto-Encoder for Multi-Source Remote Sensing Image Classification | 提出SS-MAE以解决多源遥感图像分类中的空间与光谱特征建模问题 | MAE HSI | ✅ | |
| 3 | Lightweight Diffusion Models with Distillation-Based Block Neural Architecture Search | 提出DiffNAS以解决扩散模型高计算成本问题 | distillation | ||
| 4 | CLearViD: Curriculum Learning for Video Description | 提出CLearViD以解决视频描述生成中的挑战 | curriculum learning | ||
| 5 | Towards Few-Annotation Learning in Computer Vision: Application to Image Classification and Object Detection tasks | 提出少标注学习方法以解决计算机视觉中的图像分类与目标检测问题 | representation learning contrastive learning |
🔬 支柱三:空间感知与语义 (Perception & Semantics) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | LRM: Large Reconstruction Model for Single Image to 3D | 提出大型重建模型LRM以实现单图像到3D模型的快速重建 | 3D reconstruction NeRF neural radiance field | ||
| 7 | Learning Robust Multi-Scale Representation for Neural Radiance Fields from Unposed Images | 提出一种改进方案以解决无姿态图像的神经辐射场问题 | neural radiance field | ||
| 8 | Exploiting Inductive Biases in Video Modeling through Neural CDEs | 提出基于控制微分方程的视频建模方法以解决插值和掩码传播问题 | optical flow |
🔬 支柱九:具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 9 | Are foundation models efficient for medical image segmentation? | 比较基础模型与自监督学习在医学图像分割中的效率 | foundation model | ||
| 10 | NExT-Chat: An LMM for Chat, Detection and Segmentation | 提出pix2emb方法以提升多模态理解能力 | large language model multimodal visual grounding | ✅ | |
| 11 | GCS-ICHNet: Assessment of Intracerebral Hemorrhage Prognosis using Self-Attention with Domain Knowledge Integration | 提出GCS-ICHNet以解决脑出血预后评估问题 | multimodal |
🔬 支柱五:交互与反应 (Interaction & Reaction) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 12 | General Framework to Evaluate Unlinkability in Biometric Template Protection Systems | 提出通用框架以评估生物特征模板保护系统的不可链接性 | OMOMO |