cs.CV（2023-11-07）

📊 共 21 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (7) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗2) 支柱五：交互与反应 (Interaction & Reaction) (1 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (7 篇)

#题目一句话要点标签🔗⭐
1 High-fidelity 3D Reconstruction of Plants using Neural Radiance Field 利用神经辐射场实现植物高保真3D重建 3D reconstruction NeRF neural radiance field
2 Analysis of NaN Divergence in Training Monocular Depth Estimation Model 分析NaN损失以提升单目深度估计模型训练稳定性 depth estimation monocular depth
3 UP-NeRF: Unconstrained Pose-Prior-Free Neural Radiance Fields 提出UP-NeRF以解决无约束图像下的NeRF优化问题 NeRF neural radiance field
4 Fast Sun-aligned Outdoor Scene Relighting based on TensoRF 提出SR-TensoRF以解决户外场景重光照问题 NeRF neural radiance field
5 Meta-Adapter: An Online Few-shot Learner for Vision-Language Model 提出Meta-Adapter以解决CLIP在少样本学习中的在线适应问题 open-vocabulary open vocabulary
6 DeepPatent2: A Large-Scale Benchmarking Corpus for Technical Drawing Understanding 提出DeepPatent2以解决技术图纸理解数据不足问题 3D reconstruction
7 Dual-Stream Attention Transformers for Sewer Defect Classification 提出双流多尺度视觉变换器以解决污水管道缺陷分类问题 optical flow

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

#题目一句话要点标签🔗⭐
8 Random Field Augmentations for Self-Supervised Representation Learning 提出基于高斯随机场的局部变换以增强自监督表示学习 representation learning
9 ADFactory: An Effective Framework for Generalizing Optical Flow with Nerf 提出自动数据工厂框架以解决光流泛化问题 flow matching NeRF optical flow
10 Multimodal deep representation learning for quantum cross-platform verification 提出多模态深度表示学习以解决量子跨平台验证问题 representation learning multimodal
11 Self-MI: Efficient Multimodal Fusion via Self-Supervised Multi-Task Learning with Auxiliary Mutual Information Maximization 提出Self-MI以解决多模态融合中的信息捕获问题 representation learning multimodal
12 Multi-Scale Distillation for RGB-D Anomaly Detection on the PD-REAL Dataset 提出PD-REAL数据集及多尺度蒸馏框架以提升RGB-D异常检测性能 distillation multimodal ✅
13 Supervised domain adaptation for building extraction from off-nadir aerial images 提出监督域适应方法以解决建筑提取中的标签不对齐问题 teacher-student distillation

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

#题目一句话要点标签🔗⭐
14 Selective Visual Representations Improve Convergence and Generalization for Embodied AI 提出选择性视觉表征以提升具身AI的收敛性与泛化能力 embodied AI
15 ETDPC: A Multimodality Framework for Classifying Pages in Electronic Theses and Dissertations 提出ETDPC框架以解决电子论文页面分类问题 multimodal ✅
16 mmFUSION: Multimodal Fusion for 3D Objects Detection 提出mmFUSION以解决多模态融合在3D物体检测中的挑战 multimodal
17 Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining 提出生成负样本挖掘以提升多模态组合推理能力 multimodal ✅
18 Can CLIP Help Sound Source Localization? 提出CLIP模型以解决声源定位问题 multimodal
19 Exploring Dataset-Scale Indicators of Data Quality 提出数据集规模指标以提升计算机视觉数据质量 foundation model

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

#题目一句话要点标签🔗⭐
20 Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models 提出UniHOI以解决开放世界人机交互检测问题 human-object interaction HOI large language model ✅

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

#题目一句话要点标签🔗⭐
21 OtterHD: A High-Resolution Multi-modality Model 提出OtterHD以解决高分辨率视觉输入解析问题 spatial relationship multimodal

⬅️ 返回 cs.CV 首页 · 🏠 返回主页