cs.CV（2024-02-28）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (4) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
1 Polos: Multimodal Metric Learning from Human Feedback for Image Captioning 提出Polos以解决图像描述模型评估中的人类反馈问题 contrastive learning multimodal
2 CFDNet: A Generalizable Foggy Stereo Matching Network with Contrastive Feature Distillation 提出CFDNet以解决雾霾场景下的立体匹配问题 contrastive learning distillation depth estimation
3 Downstream Task Guided Masking Learning in Masked Autoencoders Using Multi-Level Optimization 提出多级优化掩蔽学习以提升自监督视觉表示学习效果 representation learning masked autoencoder MAE
4 MambaMIR: An Arbitrary-Masked Mamba for Joint Medical Image Reconstruction and Uncertainty Estimation 提出MambaMIR以解决医学图像重建与不确定性估计问题 Mamba representation learning ✅
5 Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection 提出DRET与SRKD以解决雨天3D目标检测问题 distillation
6 PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation 提出PRCL框架以增强半监督语义分割的鲁棒性 contrastive learning
7 Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport 提出ProtoOT以解决无监督跨域图像检索问题 representation learning contrastive learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
8 Multimodal Learning To Improve Cardiac Late Mechanical Activation Detection From Cine MR Images 提出多模态学习框架以提高心脏晚期机械激活检测精度 multimodal
9 OpenMEDLab: An Open-source Platform for Multi-modality Foundation Models in Medicine 提出OpenMEDLab以推动医学领域多模态基础模型的发展 foundation model
10 All in an Aggregated Image for In-Image Learning 提出In-Image Learning以提升多模态推理能力 multimodal chain-of-thought ✅
11 Grounding Language Models for Visual Entity Recognition 提出AutoVER以解决视觉实体识别中的低性能问题 large language model

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

#题目一句话要点标签🔗⭐
12 NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images 提出NToP数据集生成方法以解决顶视鱼眼图像中的人类姿态估计问题 NeRF neural radiance field
13 3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling 提出3DSFLabelling以解决3D场景流估计中的标签稀缺问题 scene flow
14 Digging Into Normal Incorporated Stereo Matching 提出一种结合法线信息的立体匹配框架以解决低纹理区域问题 scene flow geometric consistency
15 Self-Supervised Spatially Variant PSF Estimation for Aberration-Aware Depth-from-Defocus 提出自监督学习方法以解决变焦畸变下的深度估计问题 depth estimation

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

#题目一句话要点标签🔗⭐
16 Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting 提出EgoTAP以解决自我遮挡下的3D姿态估计问题 egocentric

⬅️ 返回 cs.CV 首页 · 🏠 返回主页