In this paper, we propose a new approach to learned optimization. As com...
We focus on the task of estimating a physically plausible articulated hu...
We introduce DiffPhy, a differentiable physics-based model for articulat...
We propose a new approach to interactive full-image semantic segmentatio...
This paper aims to reduce the time to annotate images for the panoptic
s...
We introduce Fluid Annotation, an intuitive human-machine collaboration
...
Human poses and motions are important cues for analysis of videos with p...
In this paper we propose an approach for articulated tracking of multipl...
In [1], we proposed a graph-based formulation that links and clusters pe...
Every moment counts in action recognition. A comprehensive understanding...
Current people detectors operate either by scanning an image in a slidin...
Numerous groups have applied a variety of deep learning techniques to
co...
Activity recognition has shown impressive progress in recent years. Howe...
Holistic methods based on dense trajectories are currently the de facto
...
This paper introduces a new architecture for human pose estimation using...