cs.CV（2024-01-24）

📊 共 16 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6) 支柱七：动作重定向 (Motion Retargeting) (3 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱八：物理动画 (Physics-based Animation) (1) 支柱一：机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗⭐
1 MLLMReID: Multimodal Large Language Model-based Person Re-identification 提出MLLMReID以解决多模态大语言模型在行人重识别中的应用问题 large language model multimodal
2 UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion 提出UNIMO-G以解决多模态条件图像生成问题 large language model multimodal
3 ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models 提出ConTextual数据集以解决多模态模型在文本丰富视觉推理中的挑战 foundation model multimodal
4 Democratizing Fine-grained Visual Recognition with Large Language Models 提出FineR以解决细粒度视觉识别中的专家标注瓶颈问题 large language model
5 How Good is ChatGPT at Face Biometrics? A First Look into Recognition, Soft Biometrics, and Explainability 探索ChatGPT在面部生物识别中的应用与可解释性 large language model multimodal
6 InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions 提出InstructDoc以解决视觉文档理解的零-shot泛化问题 large language model multimodal

🔬 支柱七：动作重定向 (Motion Retargeting) (3 篇)

#题目一句话要点标签🔗⭐
7 Generative Human Motion Stylization in Latent Space 提出基于潜在空间的人类动作风格化方法以解决内容保持问题 human motion ✅
8 ChatterBox: Multi-round Multimodal Referring and Grounding 提出ChatterBox以解决多轮多模态指称与定位问题 spatial relationship multimodal visual grounding ✅
9 GTAutoAct: An Automatic Datasets Generation Framework Based on Game Engine Redevelopment for Action Recognition 提出GTAutoAct框架以解决动作识别数据集生成问题 human motion

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
10 SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation 提出SegMamba以解决3D医学图像分割中的长程依赖问题 Mamba SSM state space model ✅
11 Towards Customized Knowledge Distillation for Chip-Level Dense Image Predictions 提出定制化知识蒸馏方法以解决图像预测中的边界和连通性问题 distillation
12 Towards Efficient and Effective Deep Clustering with Dynamic Grouping and Prototype Aggregation 提出DigPro以解决深度聚类中的动态分组与原型聚合问题 representation learning contrastive learning ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
13 EndoGaussians: Single View Dynamic Gaussian Splatting for Deformable Endoscopic Tissues Reconstruction 提出EndoGaussians以解决内窥镜动态软组织重建问题 3D reconstruction gaussian splatting splatting
14 FoVA-Depth: Field-of-View Agnostic Depth Estimation for Cross-Dataset Generalization 提出FoVA-Depth以解决大视场深度估计问题 depth estimation stereo depth

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
15 A Spatiotemporal Approach to Tri-Perspective Representation for 3D Semantic Occupancy Prediction 提出S2TPVFormer以解决3D语义占用预测中的时序信息不足问题 spatiotemporal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 Research about the Ability of LLM in the Tamper-Detection Area 评估大语言模型在篡改检测领域的能力 manipulation large language model

⬅️ 返回 cs.CV 首页 · 🏠 返回主页