cs.CV（2024-02-19）

📊 共 23 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗4) 支柱三：空间感知与语义 (Perception & Semantics) (8 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2) 支柱一：机器人控制 (Robot Control) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 The Revolution of Multimodal Large Language Models: A Survey 综述多模态大语言模型以推动生成智能的发展 large language model multimodal instruction following
2 ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning 提出ChartX与ChartVLM以解决复杂图表推理问题 large language model foundation model ✅
3 Integrating kNN with Foundation Models for Adaptable and Privacy-Aware Image Classification 提出kNN与基础模型结合以解决数据隐私问题 foundation model ✅
4 InMD-X: Large Language Models for Internal Medicine Doctors 提出InMD-X以满足内科医生的语言处理需求 large language model
5 MM-SurvNet: Deep Learning-Based Survival Risk Stratification in Breast Cancer Through Multimodal Data Fusion 提出MM-SurvNet以解决乳腺癌生存风险分层问题 multimodal
6 LVCHAT: Facilitating Long Video Comprehension 提出LVChat以解决长视频理解中的过度压缩问题 large language model multimodal ✅
7 Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization 提出多线性专家混合模型以解决专家特化的计算成本问题 foundation model ✅
8 ISCUTE: Instance Segmentation of Cables Using Text Embedding 提出基于文本嵌入的电缆实例分割方法以解决识别挑战 foundation model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (8 篇)

#题目一句话要点标签🔗⭐
9 Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships 提出Open3DSG以解决开放世界3D场景图预测问题 open-vocabulary open vocabulary foundation model
10 SDGE: Stereo Guided Depth Estimation for 360$^\circ$ Camera Sets 提出立体引导深度估计方法以解决360°摄像头重叠区域问题 depth estimation
11 Colorizing Monochromatic Radiance Fields 提出基于Lab色彩空间的单色辐射场上色方法以解决色彩重建问题 NeRF neural radiance field ✅
12 Unveiling the Depths: A Multi-Modal Fusion Framework for Challenging Scenarios 提出多模态融合框架以解决复杂场景下的单目深度估计问题 depth estimation monocular depth
13 Landmark-based Localization using Stereo Vision and Deep Learning in GPS-Denied Battlefield Environment 提出基于地标的定位方法以解决无GPS战场环境中的定位问题 visual odometry
14 An evaluation of Deep Learning based stereo dense matching dataset shift from aerial images and a large scale stereo dataset 提出基于LiDAR生成真实场景的稠密匹配数据集以解决数据集偏移问题 scene reconstruction ✅
15 Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis 提出二进制不透明网格以解决细结构重建问题 NeRF
16 One2Avatar: Generative Implicit Head Avatar For Few-shot User Adaptation 提出One2Avatar以解决个性化头像创建的挑战 neural radiance field

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

#题目一句话要点标签🔗⭐
17 Pan-Mamba: Effective pan-sharpening with State Space Model 提出Pan-Mamba以解决全色图像与多光谱图像融合问题 Mamba state space model ✅
18 NOTE: Notable generation Of patient Text summaries through Efficient approach based on direct preference optimization 提出NOTE以高效生成患者出院总结，解决临床工作负担问题 DPO direct preference optimization large language model
19 Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning 提出多阶段对比学习框架以解决特征抑制问题 contrastive learning multimodal
20 Separating common from salient patterns with Contrastive Representation Learning 提出SepCLR以解决对比分析中的模式分离问题 representation learning contrastive learning ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
21 An Endoscopic Chisel: Intraoperative Imaging Carves 3D Anatomical Models 提出基于内窥镜视频更新3D解剖模型以解决导航手术问题 manipulation depth estimation monocular depth
22 Feudal Networks for Visual Navigation 提出一种新型的封建网络以解决视觉导航问题 teleoperation

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
23 A Spatiotemporal Illumination Model for 3D Image Fusion in Optical Coherence Tomography 提出时空光照模型以解决OCT图像融合中的伪影问题 spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页