- Unsupervised Domain Adaptation by Backpropagation (ICML 2015) - called RevGrad in comparisons
- Deep Transfer Learning with Joint Adaptation Networks (ICML 2017) - JAN
- Generate To Adapt: Aligning Domains using Generative Adversarial Networks (CVPR 2018) - Improves over JAN
- Unsupervised Domain Adaptation with Similarity Learning (CVPR 2018) - Improves over JAN
- No More Discrimination: Cross City Adaptation of Road Scene Segmenters
- Domain Adaptation through Synthesis for Unsupervised Person Re-identification
- Spatial Transformer Networks
- [Fast Spatially Varying Indoor Lighting Estimation]
- Data Distillation: Towards Omni-Supervised Learning
- Straight lines have to be straight
- Siamese Neural Networks for One-shot Image Recognition
- High-Speed Tracking with Kernelized Correlation Filters
- Taskonomy: Disentangling Task Transfer Learning
- Transfer of View-manifold Learning to Similarity Perception of Novel Objects
- Cognitive Mapping and Planning for Visual Navigation
- Visual Representations for Semantic Target Driven Navigation
- ECO: Egocentric Cognitive Mapping
- Neural Scene Representation and Learning
- Learning to See by Moving
- Egocentric Future Localization
- Force from Motion: Decoding Physical Sensation from a First Person Video
- Convolutional Pose Machines
- Active Learning for Human Pose Estimation
- Harvesting Multiple Views for Marker-less 3D Human Pose Annotations
- DeepLabCut
- Using DeepLabCut for 3D markerless pose estimation across species and behaviors
- Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies
- ReTiCaM: Real-time Human Performance Capture from Monocular Video
- 3D Menagerie: Modeling the 3D shape and pose of animals
- End-to-end Recovery of Human Shape and Pose
- [Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking]
- Hand Keypoint Detection in Single Images using Multiview Bootstrapping
- MONET: Multiview Semi-supervised Keypoint via Epipolar Divergence
- 3D Semantic Trajectory Reconstruction from 3D Pixel Continuum
- Multiview Supervision By Registration
- Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
- MAP Visibility Estimation for Large-Scale Dynamic 3D Reconstruction
- Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction
- Hyun Soo's SfM tutorial
- Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors
- Dense 3D Motion Capture from Synchronized Video Streams
- Multi-view supervision for single-view reconstruction via differentiable ray consistency
- Unsupervised Learning of Depth and Ego-Motion from Video