cs.CV（2024-01-18）

📊 共 21 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (7 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (5 🔗2) 支柱一：机器人控制 (Robot Control) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
1 Veagle: Advancements in Multimodal Representation Learning 提出Veagle以提升多模态表示学习能力 representation learning large language model multimodal
2 WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens 提出WorldDreamer以解决通用世界模型在视频生成中的局限性 world model world models dreamer
3 VMamba: Visual State Space Model 提出VMamba以解决计算机视觉中的网络架构效率问题 Mamba state space model ✅
4 P2Seg: Pointly-supervised Segmentation via Mutual Distillation 提出P2Seg以解决点级监督实例分割中的边界预测问题 distillation semantic map MDM
5 Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation 提出QA-CLIMS框架以解决弱监督语义分割中的激活不足问题 contrastive learning open-vocabulary open vocabulary ✅
6 CPCL: Cross-Modal Prototypical Contrastive Learning for Weakly Supervised Text-based Person Retrieval 提出CPCL以解决弱监督文本基础的人物检索问题 contrastive learning
7 MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection 提出MAMBA以解决视频目标检测中的内存结构效率问题 Mamba ✅

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

#题目一句话要点标签🔗⭐
8 Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models 提出一种新方法以解决多模态大语言模型中的时间幻觉问题 large language model multimodal TAMP
9 Towards Language-Driven Video Inpainting via Multimodal Large Language Models 提出语言驱动的视频修复方法以解决传统方法的局限性 large language model multimodal
10 SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model 提出SkyEyeGPT以解决遥感视觉-语言理解问题 large language model instruction following visual grounding ✅
11 Supervised Fine-tuning in turn Improves Visual Foundation Models 提出ViSFT方法以提升视觉基础模型的性能 foundation model
12 Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generation 提出显式推理与视觉问题生成的多模态模型以提升视觉理解能力 large language model chain-of-thought
13 Improving fine-grained understanding in image-text pre-training 提出SPARC以解决图像-文本预训练中的细粒度理解问题 multimodal

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

#题目一句话要点标签🔗⭐
14 GaussianBody: Clothed Human Reconstruction via 3d Gaussian Splatting 提出GaussianBody以解决动态人类重建问题 3D gaussian splatting gaussian splatting splatting
15 Instance Brownian Bridge as Texts for Open-vocabulary Video Instance Segmentation 提出实例布朗桥模型以解决开放词汇视频实例分割问题 open-vocabulary open vocabulary
16 OMG-Seg: Is One Model Good Enough For All Segmentation? 提出OMG-Seg以解决多种分割任务的统一建模问题 open-vocabulary open vocabulary ✅
17 DDM: A Metric for Comparing 3D Shapes Using Directional Distance Fields 提出DDM以解决3D形状比较中的效率与有效性问题 implicit representation scene flow ✅
18 BPDO:Boundary Points Dynamic Optimization for Arbitrary Shape Scene Text Detection 提出边界点动态优化方法以解决任意形状场景文本检测问题 scene understanding

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
19 ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions 提出ParaHome系统以捕捉家庭环境中的人机交互动态 manipulation dexterous hand human-object interaction

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

#题目一句话要点标签🔗⭐
20 GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition 提出GPT4Ego以解决零样本自我中心动作识别问题 egocentric

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

#题目一句话要点标签🔗⭐
21 DataViz3D: An Novel Method Leveraging Online Holographic Modeling for Extensive Dataset Preprocessing and Visualization 提出DataViz3D以解决复杂数据集可视化问题 spatial relationship

⬅️ 返回 cs.CV 首页 · 🏠 返回主页