cs.CV（2024-03-04）

📊 共 28 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (7 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (7 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱四：生成式动作 (Generative Motion) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (2) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱八：物理动画 (Physics-based Animation) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (7 篇)

#题目一句话要点标签🔗⭐
1 Scalable Vision-Based 3D Object Detection and Monocular Depth Estimation for Autonomous Driving 提出基于视觉的3D物体检测与单目深度估计以解决自动驾驶问题 depth estimation monocular depth
2 DD-VNB: A Depth-based Dual-Loop Framework for Real-time Visually Navigated Bronchoscopy 提出DD-VNB框架以解决实时支气管镜导航问题 depth estimation monocular depth motion estimation
3 Explicit Motion Handling and Interactive Prompting for Video Camouflaged Object Detection 提出EMIP框架以解决视频伪装目标检测中的运动处理问题 optical flow motion estimation ✅
4 DaReNeRF: Direction-aware Representation for Dynamic Scenes 提出方向感知表示以解决动态场景重建问题 NeRF neural radiance field implicit representation
5 Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views 提出深度引导的快速点云融合NeRF以解决稀疏输入视图问题 NeRF
6 Iterative Occlusion-Aware Light Field Depth Estimation using 4D Geometrical Cues 提出基于4D几何线索的迭代遮挡感知光场深度估计方法 depth estimation
7 TripoSR: Fast 3D Object Reconstruction from a Single Image 提出TripoSR以实现快速单图像3D重建 3D reconstruction

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
8 Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations 提出多模态社交互动模型以解决多方互动动态建模问题 multimodal ✅
9 Multi-Spectral Remote Sensing Image Retrieval Using Geospatial Foundation Models 提出地理空间基础模型以解决多光谱遥感图像检索问题 foundation model ✅
10 TNF: Tri-branch Neural Fusion for Multimodal Medical Data Classification 提出三分支神经融合方法以解决多模态医学数据分类问题 multimodal
11 Beyond Specialization: Assessing the Capabilities of MLLMs in Age and Gender Estimation 评估多模态大语言模型在年龄与性别估计中的能力 large language model multimodal
12 RegionGPT: Towards Region Understanding Vision Language Model 提出RegionGPT以解决视觉语言模型区域理解不足问题 large language model
13 3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors 提出3DTopia以解决高效生成高质量3D资产的问题 large language model ✅
14 A New Perspective on Smiling and Laughter Detection: Intensity Levels Matter 提出多模态微笑与笑声分类系统以解决表达检测问题 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
15 JEP-KD: Joint-Embedding Predictive Architecture Based Knowledge Distillation for Visual Speech Recognition 提出JEP-KD以解决视觉语音识别中的性能瓶颈问题 JEPA Joint-Embedding Predictive Architecture joint-embedding predictive architecture
16 Differentially Private Representation Learning via Image Captioning 通过图像描述实现差分隐私表示学习 representation learning multimodal
17 MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection 提出MiM-ISTD以解决红外小目标检测效率低下问题 Mamba state space model
18 Self-Supervised Facial Representation Learning with Facial Region Awareness 提出面部区域意识框架以提升自监督面部表征学习 representation learning
19 Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning 提出无源跨域少样本学习的新方法IM-DCL以解决数据隐私问题 contrastive learning
20 BaCon: Boosting Imbalanced Semi-supervised Learning via Balanced Feature-Level Contrastive Learning 提出BaCon以解决不平衡半监督学习问题 contrastive learning

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
21 DEMOS: Dynamic Environment Motion Synthesis in 3D Scenes via Local Spherical-BEV Perception 提出DEMOS框架以解决动态环境下的运动合成问题 motion synthesis scene-aware motion motion prediction
22 OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on 提出OOTDiffusion以解决可控虚拟试穿问题 classifier-free guidance ✅

🔬 支柱七：动作重定向 (Motion Retargeting) (2 篇)

#题目一句话要点标签🔗⭐
23 DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction 提出DiffMOT以解决复杂非线性运动预测问题 motion prediction
24 Revisiting Learning-based Video Motion Magnification for Real-time Processing 提出一种实时视频运动放大模型以解决处理速度不足问题 motion representation

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

#题目一句话要点标签🔗⭐
25 FreeA: Human-object Interaction Detection using Free Annotation Labels 提出FreeA以解决人机交互检测中的标注依赖问题 human-object interaction HOI

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

#题目一句话要点标签🔗⭐
26 3D Hand Reconstruction via Aggregating Intra and Inter Graphs Guided by Prior Knowledge for Hand-Object Interaction Scenario 提出3D手重建方法以解决手物体交互中的遮挡问题 MANO hand reconstruction

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

#题目一句话要点标签🔗⭐
27 UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control 提出UniCtrl以解决文本生成视频中的时空一致性问题 spatiotemporal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
28 RISeg: Robot Interactive Object Segmentation via Body Frame-Invariant Features 提出RISeg以解决机器人交互下的物体分割问题 manipulation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页