cs.CV（2023-11-03）

📊 共 18 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) (6 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (3 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗2) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱七：动作重定向 (Motion Retargeting) (1)

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

#题目一句话要点标签🔗⭐
1 Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation 提出基于大规模预训练视觉模型的3D点云分割方法 scene understanding foundation model
2 Estimating 3D Uncertainty Field: Quantifying Uncertainty for Neural Radiance Fields 提出3D不确定性场以解决NeRF预测不确定性问题 NeRF neural radiance field
3 Efficient Cloud Pipelines for Neural Radiance Fields 提出高效云管道以优化神经辐射场生成 NeRF neural radiance field
4 EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation 提出EXIM以解决文本引导的3D形状生成问题 implicit representation ✅
5 EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision 提出EmerNeRF以解决动态驾驶场景的时空表示学习问题 optical flow foundation model
6 Bridging the Gap between Multi-focus and Multi-modal: A Focused Integration Framework for Multi-modal Image Fusion 提出多模态图像融合框架以解决焦点区域与模态信息提取问题 depth estimation ✅

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

#题目一句话要点标签🔗⭐
7 ProS: Facial Omni-Representation Learning via Prototype-based Self-Distillation 提出基于原型自蒸馏的面部全表征学习方法以解决无监督学习挑战 representation learning distillation
8 Holistic Representation Learning for Multitask Trajectory Anomaly Detection 提出一种整体表示学习方法以解决多任务轨迹异常检测问题 representation learning
9 Towards Calibrated Robust Fine-Tuning of Vision-Language Models 提出一种新方法以同时提升视觉语言模型的OOD准确性与置信度校准 distillation multimodal
10 Disentangled Representation Learning with Transmitted Information Bottleneck 提出DisTIB以解决表示学习中的信息压缩与保留问题 representation learning

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
11 What Makes Pre-Trained Visual Representations Successful for Robust Manipulation? 提出视觉表示评估方法以提升机器人操作的鲁棒性 manipulation policy learning visual pre-training
12 Neural Collage Transfer: Artistic Reconstruction via Material Manipulation 提出神经拼贴转移方法以解决拼贴艺术生成问题 manipulation reinforcement learning ✅
13 TailorMe: Self-Supervised Learning of an Anatomically Constrained Volumetric Human Shape Model 提出TailorMe以解决人类形状建模的局限性问题 manipulation physically plausible

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
14 LLM-driven Multimodal Target Volume Contouring in Radiation Oncology 提出LLMSeg以解决放射肿瘤学中的靶区勾画问题 large language model multimodal
15 Robust Fine-Tuning of Vision-Language Models for Domain Generalization 提出一种新方法以增强视觉-语言模型在领域泛化中的鲁棒性 foundation model ✅
16 PILL: Plug Into LLM with Adapter Expert and Attention Gate 提出PILL架构以解决多模态融合挑战 large language model ✅

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

#题目一句话要点标签🔗⭐
17 Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection 提出SG2HOI+框架以统一场景图生成与人机交互检测 human-object interaction HOI

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

#题目一句话要点标签🔗⭐
18 Image Recognition of Oil Leakage Area Based on Logical Semantic Discrimination 基于逻辑语义辨别的油泄漏区域图像识别方法 spatial relationship

⬅️ 返回 cs.CV 首页 · 🏠 返回主页