cs.CV（2024-03-09）

📊 共 13 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (5 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱三：空间感知与语义 (Perception & Semantics) (3 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
1 Semi-Supervised Multimodal Multi-Instance Learning for Aortic Stenosis Diagnosis 提出半监督多模态多实例学习以解决主动脉狭窄诊断问题 multimodal
2 General surgery vision transformer: A video pre-trained foundation model for general surgery 提出通用外科视觉变换器以解决外科数据匮乏问题 foundation model
3 uniGradICON: A Foundation Model for Medical Image Registration 提出uniGradICON以解决医学图像配准的通用性问题 foundation model ✅
4 GPT as Psychologist? Preliminary Evaluations for GPT-4V on Visual Affective Computing 评估GPT-4V在视觉情感计算中的应用潜力 large language model multimodal ✅
5 LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content 提出LTGC框架以解决长尾识别问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
6 UDCR: Unsupervised Aortic DSA/CTA Rigid Registration Using Deep Reinforcement Learning and Overlap Degree Calculation 提出UDCR以解决无监督主动脉DSA/CTA刚性配准问题 reinforcement learning deep reinforcement learning MAE
7 Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning 提出PROPER以解决视觉语言导航中的路径偏差问题 contrastive learning VLN
8 Can Generative Models Improve Self-Supervised Representation Learning? 提出生成模型以增强自监督表示学习的多样性 representation learning
9 Frequency Attention for Knowledge Distillation 提出频域注意力机制以提升知识蒸馏效果 distillation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
10 DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos 提出DO3D以解决单目视频中动态物体的深度与运动估计问题 depth estimation optical flow motion estimation
11 Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving 提出Lightning NeRF以解决自动驾驶场景重建效率问题 NeRF ✅
12 Fast Kernel Scene Flow 提出快速核场景流方法以解决稠密激光雷达数据处理问题 scene flow

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
13 POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View World 提出POV框架以解决手-物体交互视角适应问题 HOI egocentric ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页