Computer Vision for Human-Computer Interaction Lab

The CV:HCI lab is part of the Institute for Anthropomatics and Robotics (IAR) of the Department of Computer Science at the Karlsruhe Institute of Technology.

The lab is directed by Prof. Dr. Rainer Stiefelhagen, who also supervises the KIT's Study Center for Visually Impaired Students (SZS). Together with the SZS, we develop new assistive technologies for visually impaired people. We also have a close collaboration with the Fraunhofer IOSB in Karlsruhe.

Our research focuses on the perception of people with applications in the following areas:

Perception of People for HCI

Vision for the Seeing Impaired

Health Care

Image and Video Analysis

Congratulation to our PostDoc Alina Roitberg!

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"

New lecture starting in WS 21/22

We will offer a new lecture from this winter semester on: 'Deep Learning for Computer Vision - Advanced Topics'

The lecture 'Deep Learning for Computer Vision' will be renamed 'Deep Learning for Computer Vision - Basics' and offered in the summer semester.

There will be no more lectures in 'Computer Vision for Human-Computer Interaction'. 


Great news!

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.

Startup is looking for new investor

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'. More

Great news!

We have three papers accepted at 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, United States (Virtual), June 2021:


Title: 'Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation'
Authors: Simon Reiß, Constantin Seibold, Alexander Freytag, Erik Rodner, Rainer Stiefelhagen

Title: 'Capturing Omni-Range Context for Omnidirectional Segmentation'
Authors: Kailun Yang, Jiaming Zhang, Simon Reiß, Xinxin Hu, Rainer Stiefelhagen

Title: 'Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation'
Authors: M. Saquib Sarfraz, Naila Murray, Vviek Sharma, Ali Diba, Luv Van Gool, Rainer Stiefelhagen

Best Student Paper Runner Up Award - IV 2020

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!

Presentation at ICCV 2019

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.

BMVC 2019_Award.JPGBMVC 2019
We did it again!

At the 30th  British Machine Vision Conference (BMVC) 2019 in Cardiff, our team won again the Best Industry Paper Award for its work on Image Translations with Spatial Profile Loss.

Great news!

Our work on Self-Supervised Learning of Face Representations received the best paper award at IEEE Automatic Face and Gesture Recognition 2019

Authors: Vivek Sharma, Makarand Tapaswi, Saquib Sarfraz, and Rainer Stiefelhagen

We have two paper accepted at CVPR 2019!

The paper by M. Haurilet et al. presents a novel model based on a graph-traversal scheme for Visual Reasoning. The architecture searches relevant nodes in the scene graph to find information for answering the current question.   

The paper by M.S. Sarfraz et al. introduces a highly-efficient approach for clustering using first neighbour relations. In comparison to other clustering algorithms, FINCH does not require any hyper-parameters, but is able to deduce the number of clusters automatically.






Great news - We have two paper accepted at CVPR 2018; one of the top computer vision conferences!

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.

Great news - 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. 
The winners were announced in CVPR17 Workshop for visual understanding across modalities - read more

Inauguration of Accessibility Lab at SZS

Our new test lab for a barrier-free access to information for visually imparired persons was inaugurated on 3rd June 2016.

Read more

Best Industry Paper Award

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

Foto Al-Halah Presiverleihung ICVSS 2015
Best 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.

Read more
Thermal faces_Sarfraz
MIT Technology Review, July 2015

MIT Technology Review featured an article on our thermal visible face matching work in July 2015. Read more how 'Deep Neural Nets Can Now Recognize Your Face in Thermal Images'

Read more in 'In the Press'

Foto Al-Halah Presiverleihung
IBM Best Student Paper Award

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".

Further details
"A Mobility and Navigational Aid for Visually Impaired Persons"
Google Faculty Research Award

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.

Further details.
CeBIT Video
How technology analyses faces @ CeBIT 2013

The video production team from the Department of Informatics visited our booth at the CeBIT 2013 and recorded a presentation of our demos there. You can watch it in their video channel KITInformatik.

CeBIT Demo
CeBIT: CVHCI in the press

We received some nice press coverage after CeBIT. Check it out:

Check out our project pages to learn more on our research on face analysis and person identification in multimedia.