Articulated pose estimation of multiple persons: pose co-estimation

consider each person independently.
On the contrary during my research I focused on joint pose estimation
of multiple persons.
During the talk I'll briefly summarize the research, which together
with my adviser prof. Vittorio Ferrari, we've carried out in this
topic. I will focus in particular on a new setting coined Human Pose
Co-Estimation (PCE), where multiple persons are in a common, but
unknown pose.
The task of PCE is to estimate their poses jointly and to produce
prototypes characterizing the shared pose. Since the poses of the
individual persons should be similar to the prototype, PCE has less
freedom compared to estimating each pose independently, which
simplifies the problem. I'll demonstrate the PCE technique on several
applications. The first is estimating pose of people performing the
same activity synchronously, such as during aerobic, cheerleading and
dancing in a group. The second application is learning prototype poses
characterizing a pose class directly from an image search engine
queried by the class name (e.g. `lotus pose'). For both applications I
will demonstrate that PCE improves pose estimation accuracy over
estimating each person independently and it learns meaningful
prototypes which can be used as priors for pose estimation in novel
images.