cs.CV（2024-01-16）

📊 共 24 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) (8 🔗5) 支柱九：具身大模型 (Embodied Foundation Models) (7 🔗2) 支柱一：机器人控制 (Robot Control) (2) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱八：物理动画 (Physics-based Animation) (2) 支柱四：生成式动作 (Generative Motion) (1) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
1 EgoGen: An Egocentric Synthetic Data Generator 提出EgoGen以解决第一人称视角合成数据生成问题 reinforcement learning motion synthesis human mesh recovery ✅
2 Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities 提出专门的视觉基础模型以解决自动驾驶中的数据稀缺问题 world model world models 3D gaussian splatting ✅
3 OBSeg: Accurate and Fast Instance Segmentation Framework Using Segmentation Foundation Models with Oriented Bounding Box Prompts 提出OBSeg以解决遥感图像实例分割中的OBB依赖问题 distillation foundation model ✅
4 Representation Learning on Event Stream via an Elastic Net-incorporated Tensor Network 提出弹性网络张量网络以解决事件流表示学习问题 representation learning spatiotemporal
5 Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization 提出跨层多实例蒸馏框架以解决自监督细粒度视觉分类问题 distillation
6 Multi-view Distillation based on Multi-modal Fusion for Few-shot Action Recognition(CLIP-$\mathrm{M^2}$DF) 提出基于多模态融合的多视角蒸馏方法以解决少样本动作识别问题 distillation ✅
7 Generative Denoise Distillation: Simple Stochastic Noises Induce Efficient Knowledge Transfer for Dense Prediction 提出生成去噪蒸馏方法以提升密集预测任务性能 distillation ✅
8 Adversarial Masking Contrastive Learning for vein recognition 提出对抗掩码对比学习以解决指静脉识别样本稀缺问题 contrastive learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
9 AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception 提出AesBench以解决多模态大语言模型在图像美学感知评估的不足 large language model multimodal ✅
10 Segment Anything Model Can Not Segment Anything: Assessing AI Foundation Model's Generalizability in Permafrost Mapping 评估AI基础模型在永久冻土映射中的可推广性 large language model foundation model
11 MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World 提出MultiPLY以解决多模态交互能力不足的问题 large language model
12 Hidden flaws behind expert-level accuracy of multimodal GPT-4 vision in medicine 揭示多模态GPT-4在医学领域的隐藏缺陷 multimodal
13 DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent) 提出DoraemonGPT以解决动态场景理解问题 large language model ✅
14 Scalable Pre-training of Large Autoregressive Image Models 提出AIM模型以实现大规模自回归图像预训练 large language model
15 Human vs. LMMs: Exploring the Discrepancy in Emoji Interpretation and Usage in Digital Communication 探讨LMMs在数字沟通中对表情符号理解的差异 multimodal

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
16 TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding 构建TACO数据集以解决双手工具操作对象理解问题 manipulation bi-manual egocentric
17 Key-point Guided Deformable Image Manipulation Using Diffusion Model 提出关键点引导的扩散模型以实现图像操控 manipulation optical flow

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
18 Learning Implicit Representation for Reconstructing Articulated Objects 提出隐式表示学习方法以重建关节物体 3D reconstruction implicit representation
19 ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field 提出ProvNeRF以解决NeRF重建质量不足问题 NeRF neural radiance field

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
20 Video Quality Assessment Based on Swin TransformerV2 and Coarse to Fine Strategy 提出基于Swin TransformerV2的无参考视频质量评估方法 spatiotemporal
21 TUMTraf Event: Calibration and Fusion Resulting in a Dataset for Roadside Event-Based and RGB Cameras 提出目标无关的标定与融合方法以解决道路事件监测问题 spatiotemporal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
22 Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation 提出多轨时间线控制以解决文本驱动3D人类动作生成的精细控制问题 motion diffusion model motion diffusion text-driven motion

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

#题目一句话要点标签🔗⭐
23 RoHM: Robust Human Motion Reconstruction via Diffusion 提出RoHM以解决单目视频中的人类运动重建问题 human motion human motion reconstruction motion reconstruction ✅

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

#题目一句话要点标签🔗⭐
24 Mobile Contactless Palmprint Recognition: Use of Multiscale, Multimodel Embeddings 提出多尺度多模态嵌入以提升无接触掌纹识别精度 database matching

⬅️ 返回 cs.CV 首页 · 🏠 返回主页