cs.CV（2024-01-19）

📊 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) (5 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (5 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱八：物理动画 (Physics-based Animation) (1) 支柱一：机器人控制 (Robot Control) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
1 MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning 提出MLLM-Tool以解决多模态工具使用理解问题 large language model multimodal ✅
2 Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences 提出Mementos基准以解决多模态大语言模型的图像序列推理问题 large language model multimodal ✅
3 Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering 提出弱监督高斯对比定位以解决视频问答中的关键时刻识别问题 multimodal TAMP
4 PhotoBot: Reference-Guided Interactive Photography via Natural Language 提出PhotoBot以解决自动摄影中的人机交互问题 large language model
5 Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detection 提出粗到细的融合策略以解决RGB-红外物体检测中的冗余信息问题 multimodal

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

#题目一句话要点标签🔗⭐
6 Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data 提出Depth Anything以解决单目深度估计问题 depth estimation monocular depth metric depth ✅
7 Dense 3D Reconstruction Through Lidar: A Comparative Study on Ex-vivo Porcine Tissue 通过激光雷达实现腹腔组织的高精度3D重建 3D reconstruction penetration
8 Motion Consistency Loss for Monocular Visual Odometry with Attention-Based Deep Learning 提出运动一致性损失以提升单目视觉里程计性能 visual odometry
9 Helmholtz-Decomposition and Optical Flow: A new method to characterize GCamP recordings 提出基于Helmholtz分解与光流的新方法以分析GCamP记录 optical flow
10 360ORB-SLAM: A Visual SLAM System for Panoramic Images with Depth Completion Network 提出360ORB-SLAM以解决传统vSLAM系统的深度信息不足问题 visual SLAM

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

#题目一句话要点标签🔗⭐
11 Enhancing medical vision-language contrastive learning via inter-matching relation modelling 提出关系增强对比学习框架以提升医学图像表示能力 representation learning contrastive learning
12 HiCD: Change Detection in Quality-Varied Images via Hierarchical Correlation Distillation 提出HiCD以解决低质量图像对的变化检测问题 distillation
13 On mitigating stability-plasticity dilemma in CLIP-guided image morphing via geodesic distillation loss 提出地理余弦相似损失以解决CLIP引导图像变形的稳定性与可塑性困境 distillation

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

#题目一句话要点标签🔗⭐
14 ActAnywhere: Subject-Aware Video Background Generation 提出ActAnywhere以解决视频背景生成问题 human-scene interaction

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

#题目一句话要点标签🔗⭐
15 Understanding Video Transformers via Universal Concept Discovery 提出视频变换器概念发现算法以解决可解释性问题 spatiotemporal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 Path Choice Matters for Clear Attribution in Path Methods 提出集中原则与SAMP以解决路径选择导致的归因模糊问题 manipulation ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页