Human Pose, Shape and Action
3D Pose from Images
2D Pose from Images
Beyond Motion Capture
Action and Behavior
Body Perception
Body Applications
Pose and Motion Priors
Clothing Models (2011-2015)
Reflectance Filtering
Learning on Manifolds
Markerless Animal Motion Capture
Multi-Camera Capture
2D Pose from Optical Flow
Body Perception
Neural Prosthetics and Decoding
Part-based Body Models
Intrinsic Depth
Lie Bodies
Layers, Time and Segmentation
Understanding Action Recognition (JHMDB)
Intrinsic Video
Intrinsic Images
Action Recognition with Tracking
Neural Control of Grasping
Flowing Puppets
Faces
Deformable Structures
Model-based Anthropometry
Modeling 3D Human Breathing
Optical flow in the LGN
FlowCap
Smooth Loops from Unconstrained Video
PCA Flow
Efficient and Scalable Inference
Motion Blur in Layers
Facade Segmentation
Smooth Metric Learning
Robust PCA
3D Recognition
Object Detection
Data Team
Computer vision research today is driven by data. Capturing and processing data is both specialized and time consuming. Our unique multi-disciplinary Data Team supports researchers in collecting and processing data ranging from 4D body scans to crowd-sourced image labeling.
For example, we help design, organize and run human subject trials in our capture hall. The team is expert at using our unique technologies to combine and adapt systems to the changing research needs of the department.
We get involved early at the study design stage. We help prepare ethics proposals and trial protocols and coordinate human subject studies. Conducting experiments involves operating various capture systems, as well as taking accurate anthropometric measurements and handling payment and paperwork.
Once collected, the data needs to be processed and organized. We take great care with data safety and privacy and also provide specialized training in data handling to department researchers.
Labelling data and running perceptual studies is also part of our skill set. Depending on the specifics of the project, we rely on crowd sourcing or well-trained staff members to achieve the best results. We explore alternative ways of collecting data, such as web-based studies.
The data team is also responsible for demos, events and visits at our capture facilities.