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
Joint Forecasting of Panoptic Segmentations with Difference Attention (Oral)
标题:差异关注联合预测全景分割
Deformable Sprites for Unsupervised Video Decomposition (Oral)
标题:无监督视频分解的可变形Sprites
BEHAVE: Dataset and Method for Tracking Human Object Interactions
标题:BEHAVE:数据集和用于跟踪人类对象交互的方法
SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos
标题:SoccerNet跟踪:多个对象跟踪数据集和足球视频中的基准
Joint Forecasting of Panoptic Segmentations with Difference Attention (Oral)
标题:差异关注联合预测全景分割
Cross-Image Relational Knowledge Distillation for Semantic Segmentation
标题:语义分割的交叉图像关系知识蒸馏
Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling
标题:来回看:视频超分辨率与明确的时间差异建模
MiniViT: Compressing Vision Transformers with Weight Multiplexing
标题:MinioIVIT:压缩具有重量复用的视觉Transformers
ViTOL: Vision Transformer for Weakly Supervised Object Localization
标题:Vitol:视觉Transformers,用于弱监督对象本地化
Implicit Sample Extension for Unsupervised Person Re-Identification
标题:无监督行人重识别的隐式示例扩展
Clothes-Changing Person Re-identification with RGB Modality Only
标题:改变的人只用RGB模态行人重识别
What's in your hands? 3D Reconstruction of Generic Objects in Hands
标题:你手中的是什么?三维重建在手中的通用物体
GIFS: Neural Implicit Function for General Shape Representation
标题:GIFS:一般形状表示的神经隐式功能
The multi-modal universe of fast-fashion: the Visuelle 2.0 benchmark
标题:fast-fashion的多模态宇宙:VISUELLE 2.0基准
Semi-Supervised Training to Improve Player and Ball Detection in Soccer
标题:半监督训练,以改善足球运动员和球侦查
Pyramidal Attention for Saliency Detection
标题:显着性检测的金字塔Attention
OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data
标题:Incam的激光:LIDAR数据上的3D对象探测器的基于遮挡的归属映射