cs.CV（2023-11-26）

📊 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) (5 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱七：动作重定向 (Motion Retargeting) (2) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding	提出视觉编程方法以解决零-shot开放词汇3D视觉定位问题	open-vocabulary open vocabulary large language model
2	GS-IR: 3D Gaussian Splatting for Inverse Rendering	提出GS-IR以解决逆向渲染中的几何和光照估计问题	3D gaussian splatting gaussian splatting splatting
3	Obj-NeRF: Extract Object NeRFs from Multi-view Images	提出Obj-NeRF以解决多视角图像中物体NeRF提取问题	3D reconstruction NeRF neural radiance field
4	Efficient Encoding of Graphics Primitives with Simplex-based Structures	提出基于单纯形结构的高效图形原语编码方法	NeRF neural radiance field
5	HumanRecon: Neural Reconstruction of Dynamic Human Using Geometric Cues and Physical Priors	提出HumanRecon以解决动态人类重建中的几何约束问题	implicit representation	✅

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

#	题目	一句话要点	标签	🔗	⭐
6	Choosing Wisely and Learning Deeply: Selective Cross-Modality Distillation via CLIP for Domain Generalization	提出选择性跨模态蒸馏方法以解决领域泛化问题	distillation
7	Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture	提出SAR-JEPA以解决SAR ATR中的自监督学习问题	JEPA Joint-Embedding Predictive Architecture joint-embedding predictive architecture	✅
8	ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images	提出ChAda-ViT以解决生物显微图像的通道适应性问题	representation learning	✅
9	Double Reverse Regularization Network Based on Self-Knowledge Distillation for SAR Object Classification	提出双重反向正则化网络以解决SAR目标分类中的过拟合问题	distillation

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

#	题目	一句话要点	标签	🔗	⭐
10	Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding	提出Insect-1M数据集与基础模型以解决昆虫识别问题	foundation model
11	Context-Aware Indoor Point Cloud Object Generation through User Instructions	提出多模态深度网络以解决室内场景对象生成问题	visual grounding

🔬 支柱七：动作重定向 (Motion Retargeting) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
12	GAIA: Zero-shot Talking Avatar Generation	提出GAIA以解决零样本对话头像生成问题	motion representation
13	ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]	提出ProtoArgNet以解决图像分类可解释性问题	spatial relationship

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

#	题目	一句话要点	标签	🔗	⭐
14	Enhancing HOI Detection with Contextual Cues from Large Vision-Language Models	提出ConCue以解决HOI检测中的上下文信息不足问题	human-object interaction HOI

⬅️ 返回 cs.CV 首页 · 🏠 返回主页