整理:AI算法与图像处理
CVPR2022论文和代码整理:https://github.com/DWCTOD/CVPR2022-Papers-with-Code-Demo
Self-supervised Learning for Sonar Image Classification
标题:声纳图像分类的自我监督学习
Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehicles
标题:自动车辆移动的多摄像机多维对象跟踪
Unsupervised Domain Adaptation for Cardiac Segmentation: Towards Structure Mutual Information Maximization
标题:心脏分割的无监督域适应:朝着结构相互信息最大化
NFormer: Robust Person Re-identification with Neighbor Transformer
标题:NFormer:用Neighbor Transformer进行鲁棒的行人重识别
Human-Object Interaction Detection via Disentangled Transformer
标题:通过解耦Transformer人-机交互检测
NFormer: Robust Person Re-identification with Neighbor Transformer
标题:标题:NFormer:用Neighbor Transformer进行鲁棒的行人重识别
GazeOnce: Real-Time Multi-Person Gaze Estimation
标题:GazeOnce:实时多人瞳孔估计
Hephaestus: A large scale multitask dataset towards InSAR understanding
标题:Hephaestus:一个大规模的多任务数据集,旨在理解
Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation
标题:视觉偏差缓解的认知不确定性加权损失
Reinforced Structured State-Evolution for Vision-Language Navigation
标题:用于视觉语言导航的增强结构状态演变
SpiderNet: Hybrid Differentiable-Evolutionary Architecture Search via Train-Free Metrics
标题:Spidernet:混合可分辨率 - 进化架构通过渔酒指标进行搜索
A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement
标题:更深层次的观察炼热和认知不确定性解剖学
Does Interference Exist When Training a Once-For-All Network?
标题:再训练一次所有网络时都存在干扰吗?
Importance is in your attention: agent importance prediction for autonomous driving
标题:重要性在您的注意力:Agent Instance预测自动驾驶