cs.CV（2024-03-20）

📊 共 34 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (10 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (10 🔗3) 支柱三：空间感知与语义 (Perception & Semantics) (7 🔗1) 支柱七：动作重定向 (Motion Retargeting) (3) 支柱四：生成式动作 (Generative Motion) (2) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
1 VL-Mamba: Exploring State Space Models for Multimodal Learning 提出VL-Mamba以解决多模态学习中的计算复杂性问题 Mamba state space model large language model
2 DepthFM: Fast Monocular Depth Estimation with Flow Matching 提出DepthFM以解决单目深度估计中的模糊和采样效率问题 flow matching depth estimation monocular depth
3 HyperFusion: A Hypernetwork Approach to Multimodal Integration of Tabular and Medical Imaging Data for Predictive Modeling 提出HyperFusion以解决多模态医疗数据融合问题 predictive model multimodal ✅
4 RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition 提出RAR方法以提升多模态大语言模型的视觉识别能力 contrastive learning large language model multimodal
5 ZigMa: A DiT-style Zigzag Mamba Diffusion Model 提出Zigzag Mamba以解决扩展性和复杂性问题 Mamba multimodal
6 Progressive trajectory matching for medical dataset distillation 提出渐进轨迹匹配方法以解决医疗数据集蒸馏问题 distillation foundation model
7 H-vmunet: High-order Vision Mamba UNet for Medical Image Segmentation 提出H-vmunet以解决医学图像分割中的信息冗余问题 Mamba SSM ✅
8 Scale Decoupled Distillation 提出规模解耦蒸馏方法以提升知识蒸馏性能 teacher-student distillation ✅
9 DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillation 提出DD-RobustBench以评估数据集蒸馏的对抗鲁棒性 distillation
10 Multi-Modal Hallucination Control by Visual Information Grounding 提出多模态互信息解码方法以降低生成模型的幻觉现象 DPO direct preference optimization

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
11 PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns 提出PuzzleVQA以诊断多模态模型的推理挑战 large language model multimodal
12 Learning from Synthetic Data for Visual Grounding 提出SynGround以利用合成数据提升视觉定位能力 visual grounding
13 Recursive Joint Cross-Modal Attention for Multimodal Fusion in Dimensional Emotion Recognition 提出递归联合跨模态注意力以解决多模态情感识别问题 multimodal
14 MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining 提出多任务预训练方法以提升遥感基础模型性能 foundation model
15 Out-of-Distribution Detection Using Peer-Class Generated by Large Language Model 提出ODPC方法以解决OOD检测问题 large language model
16 Mora: Enabling Generalist Video Generation via A Multi-Agent Framework 提出Mora框架以解决开放源代码视频生成的协作与数据问题 large language model multimodal ✅
17 Interpreting Neurons in Deep Vision Networks with Language Models 提出Describe-and-Dissect方法以解析视觉网络中的神经元角色 multimodal ✅
18 AUD-TGN: Advancing Action Unit Detection with Temporal Convolution and GPT-2 in Wild Audiovisual Contexts 提出AUD-TGN以解决野外环境下的面部动作单元检测问题 multimodal
19 FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs 提出FMM-Attack以解决视频基础LLMs的对抗攻击问题 large language model ✅
20 A Unified Optimal Transport Framework for Cross-Modal Retrieval with Noisy Labels 提出统一最优传输框架以解决跨模态检索中的噪声标签问题 multimodal

🔬 支柱三：空间感知与语义 (Perception & Semantics) (7 篇)

#题目一句话要点标签🔗⭐
21 Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion 提出高质量场景重建方法以解决手持摄像机运动模糊问题 VIO 3DGS gaussian splatting
22 RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS 提出RadSplat以解决复杂场景实时渲染问题 gaussian splatting splatting
23 Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments 提出Find n' Propagate以解决城市环境中开放词汇3D物体检测问题 open-vocabulary open vocabulary ✅
24 Advancing 6D Pose Estimation in Augmented Reality -- Overcoming Projection Ambiguity with Uncontrolled Imagery 提出新方法以解决增强现实中的6D姿态估计问题 6D pose estimation
25 T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image 提出T-Pixel2Mesh以解决单视图3D重建中的细节损失问题 3D reconstruction
26 What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models 提出反事实思维方法以缓解大型多模态模型的幻觉问题 scene understanding
27 Learning Novel View Synthesis from Heterogeneous Low-light Captures 提出一种新方法以解决低光照条件下异质亮度图像的视图合成问题 neural radiance field

🔬 支柱七：动作重定向 (Motion Retargeting) (3 篇)

#题目一句话要点标签🔗⭐
28 AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving 提出AMP方法以改进自主驾驶中的运动预测问题 motion prediction AMP
29 Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations 提出自监督类无关运动预测以解决点云标注困难问题 motion prediction
30 DOR3D-Net: Dense Ordinal Regression Network for 3D Hand Pose Estimation 提出DOR3D-Net以解决3D手势估计中的噪声问题 spatial relationship

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
31 LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment 提出LaserHuman以解决现有数据集不足的问题 text-to-motion motion generation physically plausible
32 CoMo: Controllable Motion Generation through Language Guided Pose Code Editing 提出CoMo以解决运动生成过程中的可控性问题 text-to-motion motion generation human motion

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

#题目一句话要点标签🔗⭐
33 Unifying Local and Global Multimodal Features for Place Recognition in Aliased and Low-Texture Environments 提出UMF模型以解决感知别名和低纹理环境下的地点识别问题 feature matching multimodal ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
34 UP-FacE: User-predictable Fine-grained Face Shape Editing 提出UP-FacE以解决面部形状编辑的可预测性问题 manipulation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页