计算机视觉-数据集

1. CVonline: Image Databases

Index by Topic
Action Databases
Agriculture
Attribute recognition
Autonomous Driving
Biological/Medical
Camera calibration
Face and Eye/Iris Databases
Fingerprints
General Images
General RGBD and depth datasets
General Videos
Hand, Hand Grasp, Hand Action and Gesture Databases
Image, Video and Shape Database Retrieval
Object Databases
People (static and dynamic), human body pose
People Detection and Tracking Databases (See also Surveillance)
Remote Sensing
Robotics
Scenes or Places, Scene Segmentation or Classification
Segmentation
Simultaneous Localization and Mapping
Surveillance and Tracking (See also People)
Textures
Urban Datasets
Vision and Natural Language
Other Collection Pages
Miscellaneous Topics

2. Human Pose Based on Depth

• Kinect2 Human Pose Dataset (K2HPD) - Kinect2 Human Pose Dataset (K2HPD) includes about 100K depth images with various human poses under challenging scenarios. (Keze Wang, Liang Lin, Shengfu Zhai, Dengke Dong) [Before 28/12/19]

  • “Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation”, Xipeng Chen, Kwan-Yee Lin, Wentao Liu, Chen Qian, and Liang Lin*, Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  • “DRPose3D: Depth Ranking in 3D Human Pose Estimation”, Min Wang, Xipeng Chen, Wentao Liu, Chen Qian, Liang Lin, and Lizhuang Ma, Proc. of International Joint Conference on Artificial Intelligence (IJCAI), 2018.
  • “Human Pose Estimation from Depth Images via Inference Embedded Multi-task Learning”, Keze Wang, Shengfu Zhai, Hui Cheng, Xiaodan Liang, and Liang Lin
  • Keze Wang, Liang Lin, Chenhan Jiang, Chen Qian, and Pengxu Wei, “3D Human Pose Machines with Self-supervised Learning”. To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2019.
  • DeepPose: Human Pose Estimation via Deep Neural Networks

• MVOR Dataset

• UTD Multimodal Human Action Dataset (UTD-MHAD)

• Human3.6M

  • The Ranking of 3D Human Pose Estimation on Human3.6M