cs.CV（2023-11-13）

📊 共 18 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (5 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (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)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
1 What Large Language Models Bring to Text-rich VQA? 提出基于大语言模型的文本丰富视觉问答解决方案 large language model multimodal
2 Vision-Language Integration in Multimodal Video Transformers (Partially) Aligns with the Brain 通过神经科学证据提升多模态视频变换器的语言-视觉整合能力 multimodal
3 SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models 提出SPHINX以解决多模态大语言模型的任务混合与视觉嵌入问题 large language model ✅
4 To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning 提出LVIS-Instruct4V以解决视觉指令调优中的粗粒度问题 large language model multimodal instruction following ✅
5 GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation 提出MM-Navigator以解决智能手机GUI导航问题 multimodal ✅
6 TTMFN: Two-stream Transformer-based Multimodal Fusion Network for Survival Prediction 提出TTMFN以解决癌症生存预测中的多模态信息融合问题 multimodal
7 Semantically Grounded QFormer for Efficient Vision Language Understanding 提出高效的QFormer框架以优化视觉语言理解 multimodal

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

#题目一句话要点标签🔗⭐
8 Open-Vocabulary Video Anomaly Detection 提出开放词汇视频异常检测以解决开放世界异常识别问题 open-vocabulary open vocabulary large language model
9 DeepMetricEye: Metric Depth Estimation in Periocular VR Imagery 提出DeepMetricEye以解决VR眼部深度估计问题 depth estimation metric depth
10 NDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completion 提出NDDepth以解决单目深度估计与补全问题 depth estimation monocular depth ✅
11 $L_0$-Sampler: An $L_{0}$ Model Guided Volume Sampling for NeRF 提出$L_0$-Sampler以优化NeRF的体积采样 3D reconstruction NeRF neural radiance field ✅
12 Amodal Optical Flow 提出Amodal Optical Flow以解决透明或遮挡物体的光流估计问题 optical flow

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

#题目一句话要点标签🔗⭐
13 MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Model 提出MonoDiffusion以解决自监督单目深度估计问题 distillation depth estimation monocular depth ✅
14 SpectralGPT: Spectral Remote Sensing Foundation Model 提出SpectralGPT以解决光谱遥感数据处理不足的问题 representation learning scene understanding foundation model
15 Regenerating Arbitrary Video Sequences with Distillation Path-Finding 提出交互框架以生成任意视频序列，解决动画创作难题 distillation

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
16 Multi Sentence Description of Complex Manipulation Action Videos 提出多句描述框架以解决复杂操作视频自动描述问题 manipulation
17 Registered and Segmented Deformable Object Reconstruction from a Single View Point Cloud 提出一种新方法以实现可变形物体的重建与分割 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
18 Story-to-Motion: Synthesizing Infinite and Controllable Character Animation from Long Text 提出Story-to-Motion以解决长文本驱动的角色动画生成问题 text-to-motion text-driven motion motion synthesis ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页