cs.CV（2023-10-31）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (5) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱四：生成式动作 (Generative Motion) (2 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (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 FLODCAST: Flow and Depth Forecasting via Multimodal Recurrent Architectures 提出FLODCAST以解决光流和深度预测问题 optical flow multimodal
2 FPO++: Efficient Encoding and Rendering of Dynamic Neural Radiance Fields by Analyzing and Enhancing Fourier PlenOctrees 提出FPO++以解决动态神经辐射场渲染中的伪影问题 NeRF neural radiance field
3 NeRF Revisited: Fixing Quadrature Instability in Volume Rendering 提出新方法解决NeRF体积渲染中的四重积分不稳定性问题 NeRF neural radiance field
4 Refined Equivalent Pinhole Model for Large-scale 3D Reconstruction from Spaceborne CCD Imagery 提出等效针孔模型以解决大规模3D重建问题 3D reconstruction
5 Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection 提出基于物体检测的排名框架以解决深度学习模型的虚假特征问题 open-vocabulary open vocabulary

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
6 A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysis 评估GPT-4V在医学图像分析中的多模态能力 large language model multimodal visual grounding
7 A Multi-Modal Foundation Model to Assist People with Blindness and Low Vision in Environmental Interaction 提出多模态基础模型以帮助盲人和低视力人士进行环境交互 foundation model
8 Language Guided Visual Question Answering: Elevate Your Multimodal Language Model Using Knowledge-Enriched Prompts 提出知识增强提示以提升多模态语言模型在视觉问答中的表现 multimodal
9 CapsFusion: Rethinking Image-Text Data at Scale 提出CapsFusion以解决多模态数据质量与可扩展性问题 large language model multimodal

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
10 SemanticBoost: Elevating Motion Generation with Augmented Textual Cues 提出SemanticBoost以解决复杂语义描述下的运动生成问题 motion generation large language model
11 Pose-to-Motion: Cross-Domain Motion Retargeting with Pose Prior 提出Pose-to-Motion以解决动作合成数据不足问题 motion synthesis motion retargeting ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
12 StairNet: Visual Recognition of Stairs for Human-Robot Locomotion 提出StairNet以解决人机步态在楼梯环境中的识别问题 locomotion egocentric egocentric vision

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

#题目一句话要点标签🔗⭐
13 Object-centric Video Representation for Long-term Action Anticipation 提出对象中心视频表示以解决长期动作预测问题 human-object interaction Ego4D

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

#题目一句话要点标签🔗⭐
14 GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data 提出GACE以解决LiDAR数据中3D目标检测信心估计不足问题 spatial relationship

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

#题目一句话要点标签🔗⭐
15 ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection 提出ZoomNeXt以解决伪装物体检测中的复杂性问题 spatiotemporal ✅

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
16 Team I2R-VI-FF Technical Report on EPIC-KITCHENS VISOR Hand Object Segmentation Challenge 2023 提出结合PointRend与SAM以解决手部与物体分割问题 egocentric

⬅️ 返回 cs.CV 首页 · 🏠 返回主页