cs.CV（2024-03-10）

📊 共 16 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (6 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗3) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱一：机器人控制 (Robot Control) (1 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

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

#题目一句话要点标签🔗⭐
1 WorldGPT: A Sora-Inspired Video AI Agent as Rich World Models from Text and Image Inputs 提出Sora启发的多模态学习框架以解决视频生成中的时间一致性问题 world model world models multimodal
2 PEPSI: Pathology-Enhanced Pulse-Sequence-Invariant Representations for Brain MRI 提出PEPSI以解决脑MRI分析中的脉冲序列不变性问题 representation learning PULSE ✅
3 Decoupled Contrastive Learning for Long-Tailed Recognition 提出解耦对比学习以解决长尾识别问题 representation learning contrastive learning distillation ✅
4 Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning 提出SCL-RHE以解决人类标注错误对对比学习的影响 representation learning contrastive learning
5 Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning 提出BlindNet以解决语义分割中的风格盲域泛化问题 contrastive learning
6 Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing 提出BRCD方法以解决无监督语义哈希中的知识蒸馏问题 distillation ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
7 Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models 提出Mipha以解决多模态助手的计算需求问题 large language model multimodal ✅
8 FOAA: Flattened Outer Arithmetic Attention For Multimodal Tumor Classification 提出FOAA以解决多模态肿瘤分类问题 multimodal ✅
9 A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets 提出多模态少样本增量学习方法以解决细粒度数据集问题 multimodal
10 Towards In-Vehicle Multi-Task Facial Attribute Recognition: Investigating Synthetic Data and Vision Foundation Models 提出合成数据与视觉基础模型以解决车内多任务面部属性识别问题 foundation model
11 Reframe Anything: LLM Agent for Open World Video Reframing 提出RAVA以解决视频重构中的自动化问题 large language model foundation model
12 Low-dose CT Denoising with Language-engaged Dual-space Alignment 提出语言参与的双空间对齐损失以解决低剂量CT去噪问题 large language model ✅

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

#题目一句话要点标签🔗⭐
13 Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation 提出Platypose以解决多假设3D人类运动估计问题 human motion human motion estimation motion estimation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 Debiased Noise Editing on Foundation Models for Fair Medical Image Classification 提出DNE策略以解决医疗图像分类中的偏见问题 manipulation foundation model ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
15 Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis? 提出多输入MLP以解决少量视图合成中的过拟合问题 NeRF neural radiance field

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

#题目一句话要点标签🔗⭐
16 Test-time Distribution Learning Adapter for Cross-modal Visual Reasoning 提出TT-DNA以解决跨模态视觉推理中的泛化问题 human-object interaction

⬅️ 返回 cs.CV 首页 · 🏠 返回主页