Our work Safe Resetless Reinforcement Learning: Enhancing Training Autonomy with Risk-Averse Agents has been accepted at the Twelfth International Workshop on Assistive Computer Vision and Robotics (ACVR). The source code is available on github.
Our work HiCMC: High-Efficiency Contact Matrix Compressor has been published in the Journal BMC Bioinformatics. The source code of HiCMC is available at github.
Our work "Self-supervised Domain Adaptation for Machinery Remaining Useful Life Prediction" has been published in the Journal Reliability Engineering & System Safety as part of the Special Issue RUL Prediction and System Reliability of Complex Systems. For more details, please visit DOI.
Our work "Indoor Scene Change Understanding (SCU): Segment, Describe, and Revert Any Change" in collaboration with EDU/Perth has been accepted at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024). Details will follow.
The “Institut für Informationsverarbeitung” (Institute for Information Processing) is the home of machine learning at the Leibniz University Hannover. We focus on three main research directions, namely (I) computer vision & representation learning, (II) signal processing & -coding and (III) automated machine learning. Our methods range from deep learning, automated machine learning, reinforcement learning, image analysis, remote sensing and compression of audio, image, video as well as DNA to biomedical data. Our efforts are directed towards making efficient use of multi-modal and high dimensional data for reliable predictions, ultimately supporting end-users, developers and decision makers in a vast range of applications.
Since the foundation in 1973, the institute holds a strong tradition of cultivating connections to industry partners and jointly developing solutions to automatically process and harness information. Some of the developed methodology were successfully spun-off commercially as for instance with driver assistance modules, cochlear implants or component testing. The institute is also well known for being actively involved in the standardization of MP3, MPEG-2, AVC (H.264), HEVC (H.265) as well as MPEG-G.
Do you want to join us? We have open positions.
"As a PhD student at the Institute, I benefit not only from the excellent research infrastructure, but also from a supportive and inspiring academic environment that stimulates my scientific curiosity. I can highly recommend the Institute to prospective researchers who want to develop their full potential in a dynamic and interdisciplinary environment."