cs.CV（2024-03-12）

📊 共 33 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (9 🔗4) 支柱三：空间感知与语义 (Perception & Semantics) (9 🔗1) 支柱八：物理动画 (Physics-based Animation) (1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱一：机器人控制 (Robot Control) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

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

#题目一句话要点标签🔗⭐
1 In-context learning enables multimodal large language models to classify cancer pathology images 利用上下文学习实现多模态大语言模型对癌症病理图像的分类 large language model foundation model multimodal
2 Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models 提出Lumen以增强大规模多模态模型的视觉能力 multimodal instruction following ✅
3 A Multimodal Intermediate Fusion Network with Manifold Learning for Stress Detection 提出多模态中间融合网络以解决压力检测问题 multimodal
4 FluoroSAM: A Language-promptable Foundation Model for Flexible X-ray Image Segmentation 提出FluoroSAM以解决X光图像分割灵活性不足的问题 foundation model ✅
5 Beyond Text: Frozen Large Language Models in Visual Signal Comprehension 提出V2T Tokenizer以实现视觉信号的直接理解 large language model ✅
6 Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models 提出DSEG-LIME以解决LIME框架中分割不足问题 foundation model
7 Let Storytelling Tell Vivid Stories: An Expressive and Fluent Multimodal Storyteller 提出LLaMS以解决多模态故事生成中的简化剧情问题 multimodal
8 Multi-modal Auto-regressive Modeling via Visual Words 提出多模态自回归建模方法以解决视觉信息处理问题 large language model
9 Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost 提出地理数据相似性方法以平衡模型性能与注释成本 foundation model ✅
10 Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery 提出TextGCD框架以解决多模态的通用视觉类别发现问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
11 Motion Mamba: Efficient and Long Sequence Motion Generation 提出Motion Mamba以解决长序列人类动作生成问题 Mamba SSM state space model ✅
12 NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning 提出NavCoT以解决VLN任务中的领域差距问题 world model world models embodied AI ✅
13 Spatiotemporal Representation Learning for Short and Long Medical Image Time Series 提出时空表示学习方法以解决医疗图像时间序列分析问题 representation learning contrastive learning spatiotemporal
14 SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces 提出基于状态空间模型的长视频生成方法以解决计算成本问题 Mamba SSM ✅
15 LKM-UNet: Large Kernel Vision Mamba UNet for Medical Image Segmentation 提出LKM-UNet以解决医学图像分割中的长距离依赖问题 Mamba SSM ✅
16 LG-Traj: LLM Guided Pedestrian Trajectory Prediction 提出LG-Traj以提升行人轨迹预测精度 representation learning large language model
17 Uncertainty-guided Contrastive Learning for Single Source Domain Generalisation 提出CUDGNet以解决单源领域泛化问题 contrastive learning
18 NightHaze: Nighttime Image Dehazing via Self-Prior Learning 提出NightHaze以解决夜间图像去雾问题 masked autoencoder MAE teacher-student
19 Learn and Search: An Elegant Technique for Object Lookup using Contrastive Learning 提出Learn and Search以解决对象查找效率问题 contrastive learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (9 篇)

#题目一句话要点标签🔗⭐
20 StyleGaussian: Instant 3D Style Transfer with Gaussian Splatting 提出StyleGaussian以实现即时3D风格迁移 3D gaussian splatting 3DGS gaussian splatting ✅
21 Open-Vocabulary Scene Text Recognition via Pseudo-Image Labeling and Margin Loss 提出Pseudo-OCR以解决场景文本识别中的OOV问题 open-vocabulary open vocabulary
22 D4D: An RGBD diffusion model to boost monocular depth estimation 提出D4D模型以提升单目深度估计精度 depth estimation monocular depth
23 Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow 提出层次化视觉-运动融合框架以解决场景流问题 scene flow spatiotemporal multimodal
24 MoAI: Mixture of All Intelligence for Large Language and Vision Models 提出MoAI以提升视觉语言模型的场景理解能力 scene understanding large language model
25 Q-SLAM: Quadric Representations for Monocular SLAM 提出Q-SLAM以解决单目SLAM中的深度估计问题 depth estimation NeRF
26 Flow-Based Visual Stream Compression for Event Cameras 提出基于流的视觉流压缩方法以解决事件相机数据传输问题 optical flow spatiotemporal
27 SMURF: Continuous Dynamics for Motion-Deblurring Radiance Fields 提出SMURF以解决运动模糊下的神经辐射场重建问题 NeRF neural radiance field
28 SGE: Structured Light System Based on Gray Code with an Event Camera 提出基于灰码的事件相机结构光系统以解决深度感知问题 depth estimation

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

#题目一句话要点标签🔗⭐
29 RSBuilding: Towards General Remote Sensing Image Building Extraction and Change Detection with Foundation Model 提出RSBuilding以解决遥感图像建筑提取与变化检测问题 spatiotemporal foundation model

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

#题目一句话要点标签🔗⭐
30 Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration 提出KI2HOI框架以解决零样本人机交互检测问题 human-object interaction HOI

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

#题目一句话要点标签🔗⭐
31 BID: Boundary-Interior Decoding for Unsupervised Temporal Action Localization Pre-Trainin 提出边界-内部解码框架以解决无监督时间动作定位问题 motion representation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
32 FeTrIL++: Feature Translation for Exemplar-Free Class-Incremental Learning with Hill-Climbing 提出FeTrIL++以解决无样本类增量学习中的灾难性遗忘问题 manipulation

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

#题目一句话要点标签🔗⭐
33 Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction 提出EvRGBHand以解决手部网格重建中的光照和运动模糊问题 HMR

⬅️ 返回 cs.CV 首页 · 🏠 返回主页