My research focuses on understanding the link between semantics and vision. I believe that our intelligence and ability to perceive our surroundings is strongly influenced by language and meaning. I am also very interested in human emotions, facial expressions, sentiment analysis, multimodal learning, transfer learning and 3D modelling of human bodies and faces; amongst others.
I am interested in human object interaction learning, to start with human ground interaction leaning (walking/ running) and later on would like to extended it to more complex hand manipulated objects.
I am a PhD student of Dr. Michael J Black and I am interested in estimating human bodies and the objects they interact with from images.
Yinghao Huang is a PhD candidate at Max Planck Institute for Intelligent Systems, supervised by Director Michael J. Black. His research interests fall in the areas of Machine Learning, Computer Vision and Computer Graphics. More specifically, he focuses on the topics of Human Body Modelling, 3D Human Shape and Pose Estimation, and other related things.
Perception is a fundamental part of intelligence since perception is necessary to acquire knowledge and knowledge is necessary to understand perception. Therefore computer vision is one of the most important aspects in the realization of intelligent systems. My interest of research lies in computer vision and the combination with machine learning which, to my mind, will enable the realization of intelligent systems. Currently, I am working on optical flow and how to incorporate high-level information to alleviate this ill-posed problem.
Peter Vincent Gehler
I work on decomposing photographs into their intrinsic layers of reflectance and shading using deep learning methods for fast inference. In addition I started to work on interactive semantic segmentation using CNNs.
I'm a second year PhD Student at the department of Perceiving Systems. I'm developing multi-aerial vehicle intelligence for practical research application with prototypes built here at the institute. My current work involves integrating detections from real time deep neural networks into cooperative multi vehicle sensor fusion.
Peter Vincent Gehler
My current research is focused on building probabilistic models on top of deep neural networks for various computer vision tasks. I'm also interested in object detection and recognition, as well as general machine learning algorithms and applications.
My research is based in preclinical imaging at the Werner Siemens Imaging Center, and I am focused on novel molecular imaging techniques. My research involves awake and unrestrained rodents and measurements of a more truthful neurophysiological response (to drugs, stimuli, treatments, etc…). I am interested in building an model for tracking and capturing the most commonly used research rodents in preclinical applications.
My research focuses on the computational analysis of video sequences: In what ways can the temporal dimension of videos be used by a computer to better understand the structure of a scene? And what can we learn from dynamic stimuli processing in the human visual system to make our algorithms more robust?