cs.CV（2023-10-29）

📊 共 14 篇论文 | 🔗 7 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) (5 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗2) 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 Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation 提出非可学习原型正则化以解决弱开放词汇语义分割问题 open-vocabulary open vocabulary ✅
2 Video Frame Interpolation with Many-to-many Splatting and Spatial Selective Refinement 提出多对多溅射框架以解决视频帧插值问题 splatting motion estimation
3 TivNe-SLAM: Dynamic Mapping and Tracking via Time-Varying Neural Radiance Fields 提出TivNe-SLAM以解决动态场景映射与跟踪问题 NeRF neural radiance field
4 Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes 提出Dynamo-Depth以解决动态场景下的无监督深度估计问题 depth estimation monocular depth
5 DynPoint: Dynamic Neural Point For View Synthesis 提出DynPoint以解决长视频视图合成问题 neural radiance field scene flow
6 3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets 提出3DMiner以从大规模无标注图像数据集中挖掘3D形状 3D reconstruction ✅

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

#题目一句话要点标签🔗⭐
7 Dynamic Task and Weight Prioritization Curriculum Learning for Multimodal Imagery 提出动态任务与权重优先级课程学习以提升多模态图像分析性能 curriculum learning multimodal ✅
8 BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping 提出BirdSAT框架以解决鸟类物种分类与生态映射问题 masked autoencoder contrastive learning ✅
9 Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery 提出基于奖励微调的方法以加速无监督物体发现 reinforcement learning RLHF large language model
10 Towards Generalized Multi-stage Clustering: Multi-view Self-distillation 提出多视角自蒸馏方法以解决多阶段聚类中的伪标签偏差问题 contrastive learning distillation
11 Identifiable Contrastive Learning with Automatic Feature Importance Discovery 提出三因子对比学习以解决特征可识别性问题 contrastive learning ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
12 Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection 提出Myriad以解决工业异常检测中的模态差距问题 multimodal instruction following ✅
13 Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V 评估GPT-4V在医学视觉问答中的应用潜力 large language model multimodal ✅

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

#题目一句话要点标签🔗⭐
14 TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding 提出TESTA以解决长视频编码效率瓶颈问题 spatial relationship spatiotemporal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页