cs.CV（2024-03-03）

📊 共 14 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (7 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗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 Rethinking CLIP-based Video Learners in Cross-Domain Open-Vocabulary Action Recognition 提出场景感知视频-文本对齐方法以解决跨域开放词汇动作识别问题 open-vocabulary open vocabulary ✅
2 Pyramid Feature Attention Network for Monocular Depth Prediction 提出金字塔特征注意力网络以提升单目深度预测精度 depth estimation monocular depth spatial relationship
3 Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTV 提出SlowTV与CribsTV数据集以解决自监督单目深度估计的泛化问题 depth estimation monocular depth motion estimation ✅
4 Depth Estimation Algorithm Based on Transformer-Encoder and Feature Fusion 提出基于Transformer编码器的深度估计算法以解决结构一致性问题 depth estimation spatial relationship
5 MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images 提出MatchU以解决RGB-D图像中未见物体的6D姿态估计问题 6D pose estimation
6 Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes 提出无符号正交距离场以解决3D形状重建精度问题 implicit representation
7 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos 提出3DGStream以解决动态场景的实时视频流问题 3DGS

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

#题目一句话要点标签🔗⭐
8 Hyperspectral Image Analysis in Single-Modal and Multimodal setting using Deep Learning Techniques 提出深度学习技术以解决高光谱图像分析中的高维度与空间分辨率问题 distillation HSI multimodal
9 SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos 提出SCHEMA以解决教学视频中的程序规划问题 contrastive learning large language model chain-of-thought
10 Self-Supervised Representation Learning with Meta Comprehensive Regularization 提出Meta综合正则化模块以提升自监督学习特征的全面性 representation learning
11 Logit Standardization in Knowledge Distillation 提出基于Z-score标准化的知识蒸馏方法以提升学生模型性能 distillation

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

#题目一句话要点标签🔗⭐
12 InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding 提出InfiMM-HD以解决高分辨率多模态理解问题 large language model multimodal ✅
13 GPTSee: Enhancing Moment Retrieval and Highlight Detection via Description-Based Similarity Features 提出GPTSee以解决视频时刻检索与高亮检测问题 large language model
14 A Simple-but-effective Baseline for Training-free Class-Agnostic Counting 提出一种简单有效的无训练类无关计数基线方法 foundation model

⬅️ 返回 cs.CV 首页 · 🏠 返回主页