We are proud to announce the release of the InSight app, designed with and for the blind and visually impaired community. The Vision4Blind project is dedicated to the long-term development of advanced computer vision techniques tailored for assistive intelligence. More features are coming soon. InSight needs your insights! Feedback:vision4blind@iar.kit.edu.
We would like to congratulate Dr.-Ing. Jiaming Zhang to his new position!
He accepted a professorship at the School of AI and Robotics at Hunan University in China starting in September 2025 where he will create a new team called Integrated Sensing and Assistive Intelligence (InSAI), https://insailab.org.
The prize is given every two years for doctoral research that combines theory and practice and makes in in-depth technical contributions in the field of Intelligent Transportation Systems.
KIT Doctoral Award of 2023/2024
We proudly announce that once again one of our former PhD students, Dr.-Ing. Jiaming Zhang, has won the 17th Doctoral Award in 2023/2024 for his PhD thesis 'Scene Understanding for Intelligent Transportation and Mobility Assistance Systems'
Image: Gatidis S, Kuestner T. (2022) A whole-body FDG-PET/CT dataset with manually annotated tumor lesions [Dataset]. TCIA. DOI: 10.7937/gkr0-xv29CV:HCI ranks in the top teams in the autoPET tumor segmentation challenge!
From this summer semester on we offer a new seminar called 'Multimodal Large Language Models'. This seminar is intended to provide students with an up-to-date understanding of technologies behind the recent developments in large multimodal models like GPT4.
Please be also informed that we do not offer any longer our lecture 'Biometric Systems for Person Identification' but there is a last chance to take the oral exam until the end of the summer semester 2024.
KIT Doctoral Award of 2022/2023
We proudly announce that our former PhD student Constantin Seibold has won the 16th KIT Doctoral Award of the year 2022/2023.
In his thesis ‘Towards the automatic generation of medical reports in low supervision scenarios’ Constantin has been working on the automatic evaluation of radiological images and methods for the automatic creation of medical reports. In particular, he investigated whether and how it is possible to learn from limited resources such as medical reports available for almost all radiological images or generate supervision signals from alternative medical imaging domains such as Computer Tomographies. In other words, how readily available data can be used to train image processing methods (deep learning models) to detect pathological structures such as pneumonia or pneumothorax. This would eliminate the need to have many thousands of images manually annotated by experts/doctors for training which is too time-consuming and not scaled. In his work, he was able to show that this is possible.
Collaboration with Nutribit - AI for food analysis made in Karlsruhe.
Nutribit, an AI food intelligence startup, is soon introducing their first product: The DishDetective App. The story of Nutribit began in a practical course at cv:hci, and now we are very happy to support them as mentors in their first year as a startup.
With DishDetective, all you have to do is take one picture of your meal, and the app instantly evaluates the meal's nutrients. You don't have to spend time on manual tracking but can start eating right away.
The new name illustrates the topics the center has already been dealing with for many years in service, research and teaching: inclusive studying is to be made possible and support systems for people with visual impairments are to be developed.
Our PostDoc Dr.-Ing. Alina Roitberg won another award for her doctoral thesis 'Uncertainty-aware Models for Deep Learning-based Human Activity Recognition and Applications in Intelligent Vehicles'.
With this award, KIT honors outstanding doctoral researchers, thereby highlighting the great importance of young scientists at KIT.
Dr.-Ing. Alina Roitberg won the second prize of the IEEE Intelligent Transportation Systems Society’s Best PhD Dissertation Award (2021) for her Ph.D. Thesis entitled "Uncertainty-aware Models for Deep Learning-based Human Activity Recognition and Applications in Intelligent Vehicles"
We received the Best Paper Award – Third Place at IV 2021. 2021 - for our paper 'Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive Learning' by Alexander Jaus, Kailun Yang, Rainer Stiefelhagen.
Routago - formerly called iXpoint - was one of our partners in the BMBF-funded Project TERRAIN. Together we developped a navigation app for visually impaired persons and now they are looking for new investors in Germany's 'Höhle der Löwen'
Our paper 'Open Set Driver Activity Recognition' received the Best Student Paper First Runner Up award at the Intelligent Vehicles Symposium 2020. Congratulations to Alina Roitberg, Chaioxang Ma, Monica Haurilet!
We were invited to present our paper by A. Roitberg written in collaboration with M. Martin from Fraunhofer IOSB features Drive&Act, the first large-scale dataset for fine-grained driver activity recognition.
Thepaper by M. Haurilet et al. presents a novel model based on a graph-traversal scheme for Visual Reasoning.
Thepaper by M.S. Sarfraz et al. introduces a highly-efficient approach for clustering using first neighbour relations.
We have two paper accepted at CVPR 2018
The paper by S. Sarfraz et al. presents a novel approach for person re-identification and an unsupervised re-ranking method for retrieval applications.
The paper by V. Sharma et al. presents a novel CNN architecture that can enhance image-specific details via dynamic enhancement filters with the overall all goal to improve classification.
Award won at CVPR Workshop 2017
Monica Haurilet and Ziad Al-Halah participated in the textbook question answering challenge and won the first place on the text-based track and came second in the diagram-based track
At the 26th British Machine Vision Conference (BMVC) 2015, our team received the best industry paper award for the work on thermal-visible face recognition Read more
KITBest Presentation Award
At the 9th International Computer Vision Summer School (ICVSS) 2015, our team member Ziad Al-Halah received the best presentation prize for his work on 'Hierarchical Transfer of Semantic Attributes'.
At the 22nd International Conference on Pattern Recognition (ICPR) Prof. Stiefelhagen's team received the IBM Best Student Paper Award in the Track 'Pattern Recognition and Machine Learning' for the work on "High-Level Semantics in Transfer Metric Learning".
Our research group receives a Google Research Award for its work on "A Mobility and Navigational Aid for Visually Impaired Persons". The "Google Faculty Research Award" is endowed with 83.000 USD for supporting research in computer science, engineering and related disciplines.
