cs.CV（2024-04-24）

📊 共 20 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗5) 支柱三：空间感知与语义 (Perception & Semantics) (5 🔗2) 支柱一：机器人控制 (Robot Control) (2) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱四：生成式动作 (Generative Motion) (1 🔗1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1)

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

#题目一句话要点标签🔗⭐
1 Cantor: Inspiring Multimodal Chain-of-Thought of MLLM 提出Cantor框架以解决多模态视觉推理问题 large language model multimodal chain-of-thought ✅
2 Leveraging Large Language Models for Multimodal Search 提出多模态搜索模型以提升用户搜索体验 large language model multimodal
3 MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI 提出MMT-Bench以评估大型视觉语言模型在多任务AGI中的表现 foundation model multimodal
4 What Makes Multimodal In-Context Learning Work? 提出多模态上下文学习框架以解决现有方法的局限性 large language model multimodal ✅
5 ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction 提出ImplicitAVE数据集以解决隐式属性值提取问题 large language model multimodal ✅
6 Porting Large Language Models to Mobile Devices for Question Answering 将大型语言模型移植到移动设备以实现问答功能 large language model
7 Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision 提出Adam-v2以解决医学影像中的部分-整体关系编码问题 foundation model ✅
8 Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering 提出Multi-MaP以解决个性化视觉多聚类问题 large language model ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)

#题目一句话要点标签🔗⭐
9 GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting 提出GaussianTalker以解决实时高保真说话头合成问题 3D gaussian splatting 3DGS gaussian splatting ✅
10 NeRF-XL: Scaling NeRFs with Multiple GPUs 提出NeRF-XL以解决多GPU训练NeRF的效率问题 NeRF neural radiance field
11 OMEGAS: Object Mesh Extraction from Large Scenes Guided by Gaussian Segmentation 提出OMEGAS以解决大场景中特定物体重建问题 3D reconstruction gaussian splatting splatting ✅
12 ESR-NeRF: Emissive Source Reconstruction Using LDR Multi-view Images 提出ESR-NeRF以解决发光源重建问题 NeRF
13 Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainer 提出语言解释器以解决零样本场景识别问题 scene understanding

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
14 ViViDex: Learning Vision-based Dexterous Manipulation from Human Videos 提出ViViDex以解决多指机器人手的视觉操控问题 manipulation dexterous manipulation reinforcement learning
15 3D Freehand Ultrasound using Visual Inertial and Deep Inertial Odometry for Measuring Patellar Tracking 提出视觉惯性与深度惯性测量方法以解决膝关节追踪问题 motion tracking VIO 3D reconstruction

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
16 A Survey on Visual Mamba 综述Mamba模型在计算机视觉中的应用与挑战 Mamba SSM state space model
17 MiM: Mask in Mask Self-Supervised Pre-Training for 3D Medical Image Analysis 提出Mask in Mask框架以提升3D医学图像分析性能 representation learning masked autoencoder MAE

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

#题目一句话要点标签🔗⭐
18 Enhancing Privacy in Face Analytics Using Fully Homomorphic Encryption 提出全同态加密技术以增强人脸分析中的隐私保护 OMOMO

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
19 Single-View Scene Point Cloud Human Grasp Generation 提出S2HGrasp以解决单视角场景点云下的人类抓取生成问题 penetration ✅

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

#题目一句话要点标签🔗⭐
20 Facilitating Advanced Sentinel-2 Analysis Through a Simplified Computation of Nadir BRDF Adjusted Reflectance 提出sen2nbar以简化Sentinel-2数据的反射率调整 spatiotemporal ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页