Towards Instance-Adaptive Inference for Federated Learning
面向联邦学习的实例自适应推理
TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception
TransTIC:将基于 Transformer 的图像压缩从人类感知转移到机器感知
Counting Crowds in Bad Weather
统计恶劣天气下的人群数量
NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection
NeRF-Det:学习用于多视图 3D 对象检测的几何感知体积表示
MEGA: Multimodal Alignment Aggregation and Distillation for Cinematic Video Segmentation
MEGA:用于电影视频分割的多模态对齐聚合和蒸馏
UpCycling: Semi-Supervised 3D Object Detection without Sharing Raw-Level Unlabeled Scenes
UpCycling:半监督 3D 对象检测,无需共享原始级别未标记场景
Graph Matching with Bi-Level Noisy Correspondence
具有双层噪声对应的图匹配
Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception
多智能体协作感知的时空域感知
Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing
多模态服装设计师:用于时尚图像编辑的以人为中心的潜在扩散模型
Towards Unifying Medical Vision-and-Language Pre-Training via Soft Prompts
通过软提示统一医学视觉和语言预训练
MAS: Towards Resource-Efficient Federated Multiple-Task Learning
MAS:迈向资源高效的联合多任务学习
Improving Generalization in Visual Reinforcement Learning via Conflict-Aware Gradient Agreement Augmentation
通过冲突感知梯度协议增强提高视觉强化学习的泛化能力
OmnimatteRF: Robust Omnimatte with 3D Background Modeling
OmnimatteRF:具有 3D 背景建模功能的强大 Omnimatte
Re-Mine, Learn and Reason: Exploring the Cross-Modal Semantic Correlations for Language-Guided HOI Detection
重新挖掘、学习和推理:探索语言引导 HOI 检测的跨模态语义相关性
One-Shot Recognition of any Material Anywhere using Contrastive Learning with Physics-based Rendering
使用对比学习和基于物理的渲染,一次性识别任何地方的任何材料
Fast Full-Frame Video Stabilization with Iterative Optimization
通过迭代优化实现快速全帧视频稳定
Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers
两只鸟,一块石头:图像和视频风格迁移联合学习的统一框架
Multi-Modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion
用于动态图像融合的本地到全球专家的多模态门控混合
SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection
SAFE:用于分布外物体检测的灵敏度感知功能
GeT: Generative Target Structure Debiasing for Domain Adaptation
GeT:用于域适应的生成目标结构去偏
HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending
HairCLIPv2:通过代理特征混合统一头发编辑
Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation
Deformer:用于稳健手部姿势估计的动态融合变压器
Improving Continuous Sign Language Recognition with Cross-Lingual Signs
利用跨语言手语改善连续手语识别
A Parse-then-Place Approach for Generating Graphic Layouts from Textual Descriptions
从文本描述生成图形布局的先解析后放置方法
DISeR: Designing Imaging Systems with Reinforcement Learning
DISeR:利用强化学习设计成像系统
Segmentation of Tubular Structures using Iterative Training with Tailored Samples
使用定制样本的迭代训练来分割管状结构
猜您喜欢
推荐内容
开源项目推荐 更多
热门活动
热门器件
用户搜过
随便看看
热门下载
热门文章
评论