cs.CV（2023-11-02）

📊 共 22 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (3 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱四：生成式动作 (Generative Motion) (1 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 Multimodal Foundation Models for Zero-shot Animal Species Recognition in Camera Trap Images 提出WildMatch以解决零样本动物物种识别问题 foundation model multimodal
2 4D-Former: Multimodal 4D Panoptic Segmentation 提出4D-Former以解决多模态4D全景分割问题 multimodal
3 Dynamic Multimodal Information Bottleneck for Multimodality Classification 提出动态多模态信息瓶颈以解决临床数据冗余与噪声问题 multimodal ✅
4 Long Story Short: a Summarize-then-Search Method for Long Video Question Answering 提出Long Story Short框架以解决长视频问答问题 large language model multimodal
5 Sam-Guided Enhanced Fine-Grained Encoding with Mixed Semantic Learning for Medical Image Captioning 提出基于SAM的医学图像描述方法以解决细节捕捉不足问题 large language model multimodal
6 Recognize Any Regions 提出RegionSpot以解决开放世界物体检测中的区域识别问题 foundation model
7 What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning 提出一种合成复杂视觉推理指令的方法以提升多模态大语言模型性能 large language model ✅
8 Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection 提出语言衍生外观元素与视觉线索结合的行人检测方法 large language model
9 FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models 提出FaithScore以解决大规模视觉语言模型的幻觉评估问题 instruction following

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

#题目一句话要点标签🔗⭐
10 VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning on Language-Video Foundation Models 提出VideoDreamer以解决多主体定制文本到视频生成问题 dreamer foundation model
11 Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion 提出Copilot4D以解决自主驾驶中的世界模型学习问题 world model world models VQ-VAE
12 Concatenated Masked Autoencoders as Spatial-Temporal Learner 提出CatMAE以解决视频表示学习中的时空理解问题 representation learning masked autoencoder
13 Sequential Subset Matching for Dataset Distillation 提出SeqMatch以解决数据蒸馏中的耦合问题 distillation ✅
14 Cross-Modal Information-Guided Network using Contrastive Learning for Point Cloud Registration 提出跨模态信息引导网络以解决点云配准问题 contrastive learning
15 Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding 提出PPO-TD以解决全景叙事定位中的视觉语言交互问题 PPO multimodal

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
16 Joint 3D Shape and Motion Estimation from Rolling Shutter Light-Field Images 提出一种新方法从滚动快门光场图像中估计3D形状与运动 3D reconstruction motion estimation ✅
17 Learning to Adapt CLIP for Few-Shot Monocular Depth Estimation 提出基于少量样本的CLIP适应方法以解决单目深度估计问题 depth estimation monocular depth
18 CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulation 提出CADSim以解决野外传感器数据稀疏与噪声问题 3D reconstruction

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
19 Expanding Expressiveness of Diffusion Models with Limited Data via Self-Distillation based Fine-Tuning 提出自蒸馏微调方法以提升有限数据下扩散模型的表现力 manipulation distillation
20 UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation 提出UltraLiDAR以解决稀疏LiDAR点云生成与补全问题 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
21 Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs 提出层次语义图以实现运动扩散模型的精细控制 motion diffusion model motion diffusion text-to-motion ✅

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

#题目一句话要点标签🔗⭐
22 IR-UWB Radar-based Situational Awareness System for Smartphone-Distracted Pedestrians 提出UWB辅助安全行走系统以解决智能手机分心行人的安全问题 PULSE

⬅️ 返回 cs.CV 首页 · 🏠 返回主页