cs.CV（2023-10-26）

📊 共 17 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (5 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (2 🔗2) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Three Pillars improving Vision Foundation Model Distillation for Lidar	提出三大支柱以改善激光雷达的视觉基础模型蒸馏	distillation foundation model
2	HyperFields: Towards Zero-Shot Generation of NeRFs from Text	提出HyperFields以实现文本条件下的NeRF零-shot生成	distillation NeRF neural radiance field
3	Noise-Free Score Distillation	提出无噪声评分蒸馏以优化文本到图像生成	distillation classifier-free guidance
4	Understanding the Effects of Projectors in Knowledge Distillation	提出投影器集成方法以提升知识蒸馏性能	teacher-student distillation
5	Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification	提出基于原型对比学习的CLIP微调方法以提升物体重识别性能	contrastive learning	✅

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

#	题目	一句话要点	标签	🔗	⭐
6	LP-OVOD: Open-Vocabulary Object Detection by Linear Probing	提出LP-OVOD以解决开放词汇物体检测问题	open-vocabulary open vocabulary	✅
7	Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow	研究检测防御机制对光流预测的影响	optical flow motion prediction	✅
8	Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction	提出Masked Space-Time Hash编码以解决动态场景重建问题	scene reconstruction	✅
9	Learning depth from monocular video sequences	提出新训练损失以解决单目视频序列深度估计问题	depth estimation monocular depth
10	RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments	提出RIO数据集以解决开放环境中的意图导向物体检测问题	affordance

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Task-driven Prompt Evolution for Foundation Models	提出SAMPOT以优化基础模型的图像分割任务	foundation model
12	ControlLLM: Augment Language Models with Tools by Searching on Graphs	提出ControlLLM框架以解决多模态工具调用问题	large language model	✅

🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
13	Learning Temporal Sentence Grounding From Narrated EgoVideos	提出Clip Merging方法以解决长视频中的时间句子定位问题	egocentric Ego4D TAMP	✅
14	IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting	提出IndustReal数据集以解决工业场景中的程序步骤识别问题	egocentric	✅

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

#	题目	一句话要点	标签	🔗	⭐
15	Affective Video Content Analysis: Decade Review and New Perspectives	综述情感视频内容分析的进展与未来研究方向	motion representation multimodal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
16	CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling	提出CADS以解决扩散模型输出多样性不足问题	classifier-free guidance

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mapping	提出基于局部拉普拉斯滤波的3D查找表以解决HDR图像色调映射问题	manipulation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页