cs.CV（2024-03-22）

📊 共 28 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) (11 🔗5) 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) (5 🔗2) 支柱四：生成式动作 (Generative Motion) (1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation 提出动态一体化模型以解决多模态地球观测问题 foundation model multimodal ✅
2 MedPromptX: Grounded Multimodal Prompting for Chest X-ray Diagnosis 提出MedPromptX以解决胸部X光诊断中的多模态数据整合问题 large language model multimodal visual grounding ✅
3 LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models 提出PruMerge以解决大规模多模态模型的视觉token冗余问题 large language model multimodal ✅
4 IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection 提出IS-Fusion以解决多模态3D物体检测中的信息融合问题 multimodal ✅
5 Caption-Matching: A Multimodal Approach for Cross-Domain Image Retrieval 提出Caption-Matching以解决跨域图像检索问题 multimodal
6 Multimodal Fusion with Pre-Trained Model Features in Affective Behaviour Analysis In-the-wild 提出多模态融合方法以解决情感行为分析问题 multimodal
7 Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery 提出Surgical-LVLM以解决复杂外科视觉问答问题 multimodal visual grounding
8 MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection 提出MSCoTDet以解决多光谱行人检测中的模态偏差问题 large language model chain-of-thought
9 Continual Vision-and-Language Navigation 提出持续视觉与语言导航以解决环境适应问题 VLN instruction following
10 Augmented Reality Warnings in Roadway Work Zones: Evaluating the Effect of Modality on Worker Reaction Times 通过多模态增强现实警告提升道路施工区工人反应时间 multimodal
11 Shadow Generation for Composite Image Using Diffusion model 提出基于扩散模型的阴影生成方法以解决图像合成中的阴影问题 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🔗⭐
12 Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting 提出Semantic Gaussians以解决开放词汇3D场景理解问题 3D gaussian splatting gaussian splatting splatting
13 Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation 提出Metric3D v2以解决单幅图像的度量深度和表面法线估计问题 depth estimation monocular depth metric depth ✅
14 Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splatting 提出Pixel-GS以解决3D Gaussian Splatting中的模糊与伪影问题 3D gaussian splatting 3DGS gaussian splatting
15 Language-Based Depth Hints for Monocular Depth Estimation 利用语言深度提示改善单目深度估计 depth estimation monocular depth
16 EndoGSLAM: Real-Time Dense Reconstruction and Tracking in Endoscopic Surgeries using Gaussian Splatting 提出EndoGSLAM以解决内窥镜手术中的实时重建与跟踪问题 gaussian splatting splatting
17 Recent Trends in 3D Reconstruction of General Non-Rigid Scenes 综述非刚性场景的3D重建技术以应对动态建模挑战 3D reconstruction
18 DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data 提出DiffusionMTL以解决部分标注数据下的多任务噪声预测问题 scene understanding ✅
19 WSCLoc: Weakly-Supervised Sparse-View Camera Relocalization 提出WSCLoc以解决稀疏视图下的弱监督相机重定位问题 NeRF

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
20 InternVideo2: Scaling Foundation Models for Multimodal Video Understanding 提出InternVideo2以解决多模态视频理解问题 contrastive learning spatiotemporal foundation model ✅
21 SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series 提出SiMBA以解决长序列建模的稳定性问题 Mamba SSM state space model ✅
22 STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians 提出STAG4D以解决高保真4D生成中的时空一致性问题 distillation 3D gaussian splatting gaussian splatting
23 FastCAD: Real-Time CAD Retrieval and Alignment from Scans and Videos 提出FastCAD以解决实时CAD检索与对齐问题 contrastive learning 3D reconstruction
24 Self-Supervised Backbone Framework for Diverse Agricultural Vision Tasks 提出自监督学习框架以解决农业视觉任务中的标注数据瓶颈问题 representation learning contrastive learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
25 GPT-Connect: Interaction between Text-Driven Human Motion Generator and 3D Scenes in a Training-free Manner 提出GPT-Connect以解决文本驱动人类动作生成与3D场景的交互问题 text-driven motion motion generation scene-aware motion

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

#题目一句话要点标签🔗⭐
26 InterFusion: Text-Driven Generation of 3D Human-Object Interaction 提出InterFusion以解决3D人机交互生成中的文本驱动问题 human-object interaction HOI spatial relationship

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

#题目一句话要点标签🔗⭐
27 Cell Tracking according to Biological Needs -- Strong Mitosis-aware Multi-Hypothesis Tracker with Aleatoric Uncertainty 提出一种强大的有丝分裂感知多假设追踪器以解决细胞追踪问题 motion estimation motion representation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
28 Classification of colorectal primer carcinoma from normal colon with mid-infrared spectra 利用中红外光谱分类结直肠原发癌与正常结肠组织 manipulation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页