cs.CV（2024-04-23）

📊 共 25 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10) 支柱三：空间感知与语义 (Perception & Semantics) (6) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (2 🔗2) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 DesignProbe: A Graphic Design Benchmark for Multimodal Large Language Models 提出DesignProbe基准以评估多模态大语言模型在图形设计中的能力 large language model multimodal
2 Automatic Layout Planning for Visually-Rich Documents with Instruction-Following Models 提出多模态指令跟随框架以简化视觉丰富文档的布局规划 multimodal instruction following
3 Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs 提出Wiki-LLaVA以增强多模态LLM的外部知识问答能力 multimodal
4 Re-Thinking Inverse Graphics With Large Language Models 提出IG-LLM以解决逆向图形问题 large language model
5 A review of deep learning-based information fusion techniques for multimodal medical image classification 综述深度学习多模态医学图像分类中的信息融合技术 multimodal
6 Leveraging Speech for Gesture Detection in Multimodal Communication 提出多模态融合方法以解决共语手势检测问题 multimodal
7 GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaboration 提出GSCo框架以实现医学领域的通用AI与专家模型协作 foundation model instruction following
8 Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval 提出半监督图像检索方法以解决图像-文本三元组稀缺问题 large language model
9 ContextualFusion: Context-Based Multi-Sensor Fusion for 3D Object Detection in Adverse Operating Conditions 提出ContextualFusion以解决恶劣环境下3D物体检测问题 multimodal
10 3DBench: A Scalable 3D Benchmark and Instruction-Tuning Dataset 提出3DBench以解决多模态大语言模型评估不足问题 large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (6 篇)

#题目一句话要点标签🔗⭐
11 Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation 提出伪深度标签以解决动态区域的单目深度估计问题 depth estimation monocular depth motion estimation
12 TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting 提出TalkingGaussian以解决动态人脸合成中的失真问题 gaussian splatting splatting
13 DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition 提出DENOISER框架以解决开放词汇动作识别中的噪声问题 open-vocabulary open vocabulary
14 FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent 提出FlowMap以解决高质量相机姿态和深度估计问题 gaussian splatting splatting optical flow
15 SGFormer: Spherical Geometry Transformer for 360 Depth Estimation 提出SGFormer以解决360深度估计中的全景失真问题 depth estimation
16 Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization 提出多会话SLAM以解决跨视频相机运动跟踪问题 visual odometry optical flow

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

#题目一句话要点标签🔗⭐
17 Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation 提出VisionPrefer以解决人类偏好数据不足问题 reinforcement learning large language model multimodal
18 Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model 提出Mamba3D以解决点云分析中的特征提取问题 Mamba SSM state space model ✅
19 CT-GLIP: 3D Grounded Language-Image Pretraining with CT Scans and Radiology Reports for Full-Body Scenarios 提出CT-GLIP以解决3D医学图像与语言对齐问题 contrastive learning foundation model multimodal
20 Test-Time Adaptation for Combating Missing Modalities in Egocentric Videos 提出MiDl方法以解决自我监督测试时缺失模态问题 distillation egocentric

🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)

#题目一句话要点标签🔗⭐
21 Think-Program-reCtify: 3D Situated Reasoning with Large Language Models 提出LLM-TPC框架以解决3D环境中的推理问题 egocentric large language model ✅
22 SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation 提出SMPLer以解决单目3D人类形状与姿态估计中的计算复杂性问题 SMPL ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
23 WANDR: Intention-guided Human Motion Generation 提出WANDR以解决自然人类运动生成问题 locomotion reinforcement learning motion generation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
24 You Think, You ACT: The New Task of Arbitrary Text to Motion Generation 提出一种新方法以解决任意文本到动作生成的挑战 text-to-motion motion generation human motion

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

#题目一句话要点标签🔗⭐
25 3DFlowRenderer: One-shot Face Re-enactment via Dense 3D Facial Flow Estimation 提出3DFlowRenderer以解决面部表情转移的鲁棒性问题 motion estimation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页