cs.CV（2024-08-14）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

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

#题目一句话要点标签🔗⭐
1 MathScape: Benchmarking Multimodal Large Language Models in Real-World Mathematical Contexts MathScape：提出真实世界数学场景多模态大语言模型评测基准 large language model multimodal
2 Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach 提出一种模态不变的多模态学习方法，提升缺失模态下的鲁棒性。 multimodal
3 Robust Semi-supervised Multimodal Medical Image Segmentation via Cross Modality Collaboration 提出一种鲁棒的半监督多模态医学图像分割框架，解决数据稀缺和模态错位问题。 multimodal
4 Enhancing Visual Question Answering through Ranking-Based Hybrid Training and Multimodal Fusion 提出Rank VQA模型，通过排序混合训练和多模态融合提升视觉问答性能。 multimodal
5 LLMI3D: MLLM-based 3D Perception from a Single 2D Image 提出LLMI3D以解决单张2D图像的3D感知问题 large language model multimodal
6 Segment Using Just One Example 提出基于单样本图像的语义分割方法，利用SAM自动生成提示。 foundation model
7 Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach 提出一种数据驱动的文本-视频检索框架，通过增强文本表示解决信息不对称问题。 large language model

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

#题目一句话要点标签🔗⭐
8 Progressive Radiance Distillation for Inverse Rendering with Gaussian Splatting 提出渐进式辐射蒸馏，结合物理渲染与高斯溅射实现高质量逆渲染 distillation gaussian splatting splatting
9 End-to-end Semantic-centric Video-based Multimodal Affective Computing 提出SemanticMAC框架，解决视频多模态情感计算中的语义失衡与失配问题。 representation learning contrastive learning multimodal
10 Domain-invariant Representation Learning via Segment Anything Model for Blood Cell Classification 提出基于SAM的领域不变表征学习框架，提升血细胞跨域分类精度 representation learning foundation model ✅
11 Knowledge Distillation with Refined Logits 提出精炼Logit蒸馏（RLD）方法，提升知识蒸馏效果并保持类间相关性。 distillation ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
12 Rethinking Open-Vocabulary Segmentation of Radiance Fields in 3D Space 提出基于3D空间辐射场的开放词汇分割方法，实现完整3D语义理解 3DGS NeRF open-vocabulary
13 Enhanced Scale-aware Depth Estimation for Monocular Endoscopic Scenes with Geometric Modeling 提出基于几何建模的内窥镜单目深度估计增强方法，解决尺度感知问题 depth estimation monocular depth

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

#题目一句话要点标签🔗⭐
14 UAHOI: Uncertainty-aware Robust Interaction Learning for HOI Detection 提出UAHOI，通过不确定性感知学习提升HOI检测的准确性和鲁棒性 human-object interaction HOI

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
15 3D Gaussian Editing with A Single Image 提出基于单张图像的3D高斯编辑方法，实现对3D场景的直观操控。 manipulation 3D gaussian splatting gaussian splatting

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

#题目一句话要点标签🔗⭐
16 G$^2$V$^2$former: Graph Guided Video Vision Transformer for Face Anti-Spoofing 提出G$^2$V$^2$former，结合人脸和 Landmark，解决视频人脸反欺骗中动态线索缺失问题。 spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页