cs.CV（2023-10-08）

📊 共 13 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 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1 🔗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	Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching	提出开放词汇动物关键点检测方法以解决零-shot检测问题	open-vocabulary open vocabulary feature matching
2	Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data	提出Open-VCLIP++以解决零-shot视频识别问题	open-vocabulary open vocabulary large language model	✅
3	OV-PARTS: Towards Open-Vocabulary Part Segmentation	提出OV-PARTS以解决开放词汇的部件分割问题	open-vocabulary open vocabulary	✅
4	Compositional Semantics for Open Vocabulary Spatio-semantic Representations	提出潜在组合语义嵌入以解决复杂任务推理问题	open-vocabulary open vocabulary
5	LocoNeRF: A NeRF-based Approach for Local Structure from Motion for Precise Localization	提出LocoNeRF以解决视觉定位中的高延迟问题	NeRF neural radiance field
6	Geometry Aware Field-to-field Transformations for 3D Semantic Segmentation	提出基于NeRF的几何感知场到场转换以解决3D语义分割问题	NeRF neural radiance field
7	Improving Discriminative Multi-Modal Learning with Large-Scale Pre-Trained Models	提出MMLoRA以解决多模态学习中的特征适应问题	optical flow

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

#	题目	一句话要点	标签	🔗	⭐
8	UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model	提出UReader以解决视觉场景下的无OCR语言理解问题	large language model multimodal
9	Lightweight In-Context Tuning for Multimodal Unified Models	提出M$^2$IXT以增强多模态统一模型的上下文学习能力	multimodal visual grounding
10	Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling	提出Video-Teller以提升视频到文本生成的效果	large language model foundation model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
11	VisionFM: a Multi-Modal Multi-Task Vision Foundation Model for Generalist Ophthalmic Artificial Intelligence	提出VisionFM以解决眼科人工智能多任务问题	representation learning foundation model
12	Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition	提出CLIP-OCR以提升场景文本识别性能	distillation	✅

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

#	题目	一句话要点	标签	🔗	⭐
13	AANet: Aggregation and Alignment Network with Semi-hard Positive Sample Mining for Hierarchical Place Recognition	提出AANet以解决层次化地点识别中的效率与准确性问题	geometric consistency	✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页