cs.CV（2024-04-25）

📊 共 31 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (5 🔗1) 支柱一：机器人控制 (Robot Control) (4) 支柱四：生成式动作 (Generative Motion) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension 提出SEED-Bench-2-Plus以评估多模态大语言模型的文本丰富视觉理解能力 large language model multimodal ✅
2 How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites 提出InternVL 1.5以缩小开源与商业多模态模型的能力差距 large language model foundation model multimodal ✅
3 List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs 提出逐项列举方法以提升多模态大语言模型的视觉推理能力 large language model multimodal visual grounding ✅
4 Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials 提出Make-it-Real以解决3D对象材料真实感不足问题 large language model multimodal
5 ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving 提出ConsistentID以解决人脸生成中的身份一致性问题 multimodal
6 RadGenome-Chest CT: A Grounded Vision-Language Dataset for Chest CT Analysis 提出RadGenome-Chest CT以解决胸部CT分析数据集不足问题 large language model foundation model multimodal
7 Multimodal Semantic-Aware Automatic Colorization with Diffusion Prior 提出多模态语义感知自动上色方法以解决灰度图像上色问题 multimodal
8 Multimodal Information Interaction for Medical Image Segmentation 提出MicFormer以解决多模态特征融合问题 multimodal ✅
9 Semantic Segmentation Refiner for Ultrasound Applications with Zero-Shot Foundation Models 提出无提示语义分割方法以解决超声影像数据稀缺问题 foundation model
10 TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning 提出TinyChart以解决资源受限环境下的图表理解问题 large language model multimodal ✅
11 Revisiting Relevance Feedback for CLIP-based Interactive Image Retrieval 提出基于CLIP的交互式图像检索系统以解决用户偏好差异问题 zero-shot transfer
12 TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models 提出TI2V-Zero以解决视频生成中的图像条件化问题 foundation model

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

#题目一句话要点标签🔗⭐
13 Promoting CNNs with Cross-Architecture Knowledge Distillation for Efficient Monocular Depth Estimation 提出DisDepth以提升单目深度估计的效率 distillation depth estimation monocular depth
14 Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities 提出CorrKD框架以解决多模态情感分析中的模态缺失问题 distillation multimodal
15 Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud 提出Point-JEPA以解决点云自监督学习中的效率问题 JEPA Joint-Embedding Predictive Architecture joint-embedding predictive architecture
16 Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data 提出零-shot蒸馏方法以有效利用合成数据 distillation foundation model
17 CFMW: Cross-modality Fusion Mamba for Robust Object Detection under Adverse Weather 提出CFMW以解决恶劣天气下物体检测的鲁棒性问题 Mamba ✅
18 OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images 提出OpenDlign以解决3D点云与图像文本对齐问题 representation learning multimodal
19 Dual Expert Distillation Network for Generalized Zero-Shot Learning 提出双专家蒸馏网络以解决零样本学习中的属性不对称问题 distillation

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

#题目一句话要点标签🔗⭐
20 PhyRecon: Physically Plausible Neural Scene Reconstruction 提出PHYRECON以解决多视角神经重建中的物理不合理性问题 3D reconstruction implicit representation scene reconstruction
21 The Third Monocular Depth Estimation Challenge 提出单目深度估计挑战以提升零-shot泛化能力 depth estimation monocular depth Depth Anything
22 MonoPCC: Photometric-invariant Cycle Constraint for Monocular Depth Estimation of Endoscopic Images 提出MonoPCC以解决内窥镜图像单目深度估计中的亮度不一致问题 depth estimation monocular depth
23 LeanGaussian: Breaking Pixel or Point Cloud Correspondence in Modeling 3D Gaussians 提出LeanGaussian以解决3D高斯建模中的像素或点云对应问题 3D reconstruction gaussian splatting splatting ✅
24 Depth Supervised Neural Surface Reconstruction from Airborne Imagery 提出深度监督神经表面重建方法以解决航空影像重建问题 NeRF neural radiance field

🔬 支柱一：机器人控制 (Robot Control) (4 篇)

#题目一句话要点标签🔗⭐
25 Motor Focus: Fast Ego-Motion Prediction for Assistive Visual Navigation 提出Motor Focus以解决视觉导航中的自我运动预测问题 humanoid MAE optical flow
26 Energy-Latency Manipulation of Multi-modal Large Language Models via Verbose Samples 提出冗长样本以解决多模态大语言模型的能耗与延迟问题 manipulation large language model
27 V2A-Mark: Versatile Deep Visual-Audio Watermarking for Manipulation Localization and Copyright Protection 提出V2A-Mark以解决视频篡改取证中的多模态局限问题 manipulation
28 Research on Splicing Image Detection Algorithms Based on Natural Image Statistical Characteristics 提出基于自然图像统计特征的拼接图像检测算法以解决图像篡改问题 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
29 WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Users 提出数据合成技术以改善轮椅用户的姿态估计性能 motion generation

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

#题目一句话要点标签🔗⭐
30 TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation 提出TokenHMR以解决单图像3D人类姿态恢复问题 human mesh recovery

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

#题目一句话要点标签🔗⭐
31 SFMViT: SlowFast Meet ViT in Chaotic World 提出SFMViT以解决混乱场景中的时空动作定位问题 spatiotemporal ✅

⬅️ 返回 cs.CV 首页 · 🏠 返回主页