Learn More
We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discrimina-tive model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task learning problem, our model is able to selectively predict partial poses in the presence of noise and occlusion. Our(More)
We present an unsupervised representation learning approach that compactly encodes the motion dependencies in videos. Given a pair of images from a video clip, our framework learns to predict the long-term 3D motions. To reduce the complexity of the learning framework, we propose to describe the motion as a sequence of atomic 3D flows computed with RGB-D(More)
The standard practice in histopathology of breast cancers is to examine a hematoxylin and eosin (H&E) stained tissue biopsy under a microscope to diagnose whether a lesion is benign or malignant. This determination is made based on a manual, qualitative inspection, making it subject to investigator bias and resulting in low throughput. Hence, a(More)
Recent progress in developing cost-effective depth sensors has enabled new AI-assisted solutions such as assisted driving vehicles and smart spaces. Machine learning techniques have been successfully applied on these depth signals to perceive meaningful information about human behavior. In this work, we propose to deploy depth sensors in hospital settings(More)
One in twenty-five patients admitted to a hospital will suffer from a hospital acquired infection. If we can intelligently track healthcare staff, patients, and visitors, we can better understand the sources of such infections. We envision a smart hospital capable of increasing operational efficiency and improving patient care with less spending. In this(More)
  • 1