cs.CV（2024-01-01）

📊 共 13 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (4 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱一：机器人控制 (Robot Control) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
1 Deblurring 3D Gaussian Splatting 提出实时去模糊框架以解决3D高斯点云渲染质量下降问题 3D gaussian splatting gaussian splatting splatting ✅
2 Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Prior 提出Sharp-NeRF以解决模糊图像的快速去模糊问题 NeRF neural radiance field ✅
3 Rethinking RAFT for Efficient Optical Flow 提出基于注意力机制的高效光流估计方法以解决大位移问题 optical flow ✅
4 Geometry Depth Consistency in RGBD Relative Pose Estimation 提出几何深度一致性方法以提升RGBD相对姿态估计 metric depth

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

#题目一句话要点标签🔗⭐
5 Retrieval-Augmented Egocentric Video Captioning 提出EgoInstructor以解决第一人称视频理解问题 representation learning egocentric first-person view ✅
6 Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP 提出针对MedCLIP的后门攻击方法以解决医疗图像文本模型的安全隐患 contrastive learning foundation model
7 Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning 提出多粒度视觉特征学习以提升文本到视频检索效率 representation learning
8 ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention 提出ScatterFormer以解决点云处理中的注意力计算效率问题 linear attention ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
9 COSMO: COntrastive Streamlined MultimOdal Model with Interleaved Pre-Training 提出COSMO模型以解决长文本生成与对齐任务的挑战 large language model multimodal PaLM-E
10 MultiFusionNet: Multilayer Multimodal Fusion of Deep Neural Networks for Chest X-Ray Image Classification 提出MultiFusionNet以解决胸部X光图像分类中的特征提取不足问题 multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
11 PROMPT-IML: Image Manipulation Localization with Pre-trained Foundation Models Through Prompt Tuning 提出PROMPT-IML框架以解决图像篡改定位问题 manipulation foundation model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
12 Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera 提出基于智能手表和头戴相机的轻量级动作捕捉方法 egocentric motion estimation

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
13 Refining Pre-Trained Motion Models 提出自监督训练方法以改进运动估计模型 motion estimation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页