cs.CV（2024-01-29）

📊 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) (8 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (6 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱七：动作重定向 (Motion Retargeting) (2) 支柱一：机器人控制 (Robot Control) (2) 支柱五：交互与反应 (Interaction & Reaction) (1) 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 Muffin or Chihuahua? Challenging Multimodal Large Language Models with Multipanel VQA 提出MultipanelVQA基准以挑战多模态大语言模型的多面板视觉理解能力 large language model multimodal
2 PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology 提出PathMMU以解决病理学领域缺乏高质量基准的问题 multimodal
3 Image-Text Out-Of-Context Detection Using Synthetic Multimodal Misinformation 提出合成多模态虚假信息以解决上下文外检测问题 multimodal
4 LCV2: An Efficient Pretraining-Free Framework for Grounded Visual Question Answering 提出LCV2框架以解决视觉问答中的预训练依赖问题 large language model multimodal visual grounding
5 LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs 提出稀疏LoRA专家混合模型以解决指令微调中的数据冲突问题 large language model multimodal
6 M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining 提出M2-Encoder以解决多语言图像文本理解问题 foundation model multimodal
7 InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model 提出InternLM-XComposer2以解决多模态文本-图像创作与理解问题 multimodal ✅
8 Cutup and Detect: Human Fall Detection on Cutup Untrimmed Videos Using a Large Foundational Video Understanding Model 提出基于Cutup方法的人体摔倒检测以解决长视频分析问题 foundation model

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

#题目一句话要点标签🔗⭐
9 Endo-4DGS: Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splatting 提出Endo-4DGS以解决内窥镜动态场景重建问题 depth estimation monocular depth Depth Anything
10 Depth Anything in Medical Images: A Comparative Study 评估Depth Anything模型在医学图像中的单目深度估计能力 depth estimation monocular depth Depth Anything
11 DeFlow: Decoder of Scene Flow Network in Autonomous Driving 提出DeFlow以解决自动驾驶中的场景流估计问题 scene flow ✅
12 Leveraging Positional Encoding for Robust Multi-Reference-Based Object 6D Pose Estimation 利用位置编码解决多参考物体6D姿态估计问题 6D pose estimation
13 Trustworthy Automated Driving through Qualitative Scene Understanding and Explanations 提出定性可解释图(QXG)以解决自动驾驶场景理解问题 scene understanding
14 Domain adaptation strategies for 3D reconstruction of the lumbar spine using real fluoroscopy data 提出基于真实透视数据的3D重建方法以解决手术导航问题 3D reconstruction

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

#题目一句话要点标签🔗⭐
15 Divide and Conquer: Rethinking the Training Paradigm of Neural Radiance Fields 提出分组训练方法以提升神经辐射场的渲染质量 teacher-student distillation NeRF
16 MV2MAE: Multi-View Video Masked Autoencoders 提出MV2MAE以解决多视角视频自监督学习问题 masked autoencoder MAE
17 Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing 提出Cross-Scale MAE以解决遥感图像多尺度分析问题 representation learning MAE
18 Dynamic Prototype Adaptation with Distillation for Few-shot Point Cloud Segmentation 提出动态原型适应方法以解决少样本点云分割问题 distillation ✅
19 2L3: Lifting Imperfect Generated 2D Images into Accurate 3D 提出2L3框架以解决单幅图像重建3D对象的问题 dreamer 3D reconstruction

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

#题目一句话要点标签🔗⭐
20 FIMP: Future Interaction Modeling for Multi-Agent Motion Prediction 提出FIMP以解决多智能体运动预测中的未来交互建模问题 motion prediction
21 Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression 提出基于空间分解和时间融合的预测方法以提高视频压缩性能 motion estimation

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
22 Knowledge-Aware Neuron Interpretation for Scene Classification 提出知识感知神经元解释框架以解决场景分类中的透明性问题 manipulation concept fusion
23 Hand-Centric Motion Refinement for 3D Hand-Object Interaction via Hierarchical Spatial-Temporal Modeling 提出手中心运动精炼方法以解决3D手物体交互问题 manipulation

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

#题目一句话要点标签🔗⭐
24 Dropout Concrete Autoencoder for Band Selection on HSI Scenes 提出Dropout Concrete Autoencoder以解决高光谱图像带选择问题 HSI

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

#题目一句话要点标签🔗⭐
25 Extending the kinematic theory of rapid movements with new primitives 提出运动学理论变换以扩展快速运动的建模能力 spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页