The work „Estimating 3D Motion and Forces of Person-Object Interactions From Monocular Video“ co-authored by Jiri Sedlar and Josef Sivic from the Intelligent Machine Perception (IMPACT) project at CIIRC CTU was shortlisted among the best paper finalists at the Conference on Computer Vision and Pattern Recognition 2019 (CVPR 2019) that took place in Long Beach (CA, USA) in summer. CVPR is the premier annual computer vision event.
The paper introduces a new approach for automatic reconstruction of 3D motion and actuation forces of a person interacting with an object from a single RGB video. The objective is to enable robots to learn how to manipulate tools by watching instructional videos that are available at, for example, Youtube. The approach was developed in collaboration with researchers from INRIA in Paris and LAAS-CNRS in Toulouse.
The CVPR conference (IEEE/CVF Conference on Computer Vision and Pattern Recognition) is one of the top three conferences in the field of computer vision (together with ICCV and ECCV) and is listed among the top 10 most cited journals and conferences over all areas of science by Google Scholar. A total of 1294 papers have been accepted this year from a record-high 5160 submissions (25% acceptance rate). The best paper finalists were selected by the program committee as the top 45 papers (1%) from all submissions.
The Intelligent Machine Perception project (IMPACT) brings together researchers from CIIRC in Prague and INRIA in Paris, and focuses on fundamental and applied research in computer vision, machine learning and robotics to develop machines that learn to perceive, reason about, navigate in and interact with complex dynamic environments.