Prof. Dr. Hildegard Kuehne

(nee Koehler)


____________________________________________________________________________________________

Assistant Professor at CVAI Group, Goethe University Frankfurt

Affiliated Professor at MIT-IBM Watson Lab

Please contact me under:
kuehne @ uni - frankfurt . de

Twitter

LinkedIn

Scholar

  

 

 

News
 ____________________________________________________________________________________________

  • The website of our MIT-IBM "Sight and Sound" project is finally online! Check out all the great papers and people working on this: http://sightandsound.csail.mit.edu/
  • I'm giving an invited talk about at the CVPR 2021 "Sight and Sound" workshop on "Multimodal Learning for Video Understanding" - Video will be online soon!
  • Our paper "Differentiable Top-k Classification Learning" has been accteped for ICML 2022 - Big congrats to Felix - Details follow soon!
  • Two papers accteped for CVPR 2022 - Big congrats to Nina and everybody else involved!
  • Our Paper "Monotonic Differentiable Sorting Networks" was accteped for ICLR 2022 - Paper
  • Our Paper "Style Agnostic 3D Reconstruction via Adversarial Style Transfer" is presented at WACV
  • Our Paper "Learning with Algorithmic Supervision via Continuous Relaxations" is presented at NeurIPS 2021
  • HMDB was awarded this years TC-PAMI Helmholtz Award at ICCV2021!
  • I'm giving a talk about at ICCV 2021 "Second International Tutorial on Large Scale Holistic Video Understanding" on Understanding Videos Without Labels - YouTube
  • I'm giving a talk about at ICCV 2021 "6th Workshop on Benchmarking Multi-Target Tracking" on Spatial-temporal action localization in untrimmed videos
  • I'm serving as area chair for CVPR 2021 and 2022, ICCV 2021, BMVC 2021, and WACV 2021 and 2022

    		•

    Projects
     ____________________________________________________________________________________________


     

    Nina Shvetsova, Brian Chen, Andrew Rouditchenko, Samuel Thomas, Brian Kingsbury, Rogerio Feris, David Harwath, James Glass, Hilde Kuehne. Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval, CVPR 2022


    (pdf), (code)


     

    Sivan Harary, Eli Schwartz, Assaf Arbelle, Peter Staar, Shady Abu-Hussein, Elad Amrani, Roei Herzig, Amit Alfassy, Raja Giryes, Hilde Kuehne, Dina Katabi, Kate Saenko, Rogerio Feris, Leonid Karlinsky. Unsupervised Domain Generalization by Learning a Bridge Across Domains, CVPR 2022


    (pdf), (code coming soon),


     

    Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen. Monotonic Differentiable Sorting Networks, ICLR 2022


    (pdf), (Code), (YouTube)


     

    Felix Petersen, Bastian Goldluecke, Oliver Deussen, Hilde Kuehne. Style Agnostic 3D Reconstruction via Adversarial Style Transfer, WACV 2022


    (pdf), (Code), (YouTube)


     

    Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen. Learning with Algorithmic Supervision via Continuous Relaxations, NeurIPS 2021


    (pdf), (code), (Youtube)


     

    Assaf Arbelle, Sivan Doveh, Amit Alfassy, Joseph Shtok, Guy Lev, Eli Schwartz, Hilde Kuehne, Hila Barak Levi, Prasanna Sattigeri, Rameswar Panda, Chun-Fu Chen, Alex Bronstein, Kate Saenko, Shimon Ullman, Raja Giryes, Rogerio Feris, Leonid Karlinsky. Detector-Free Weakly Supervised Grounding by Separation, ICCV 2021 (oral)


    (pdf)


     

    Brian Chen, Andrew Rouditchenko, Kevin Duarte, Hilde Kuehne, Samuel Thomas, Angie Boggust, Rameswar Panda, Brian Kingsbury, Rogerio Feris, David Harwath, James Glass, Michael Picheny, Shih-Fu Chang. Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos, ICCV 2021


    (pdf), (code)


     

    Anna Kukleva, Hilde Kuehne, Bernt Schiele. Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting, ICCV 2021


    (pdf)


     

    Andrew Rouditchenko, Angie Boggust, David Harwath, Brian Chen, Dhiraj Joshi, Samuel Thomas, Kartik Audhkhasi, Hilde Kuehne, Rameswar Panda, Rogerio Feris, Brian Kingsbury, Michael Picheny, Antonio Torralba, James Glass. AVLnet: Learning Audio-Visual Language Representations from Instructional Videos, Interspeech 2021


    (pdf), (AVLNet code)


     

    Andrew Rouditchenko, Angie Boggust, David Harwath, Samuel Thomas, Hilde Kuehne, Brian Chen, Rameswar Panda, Rogerio Feris, Brian Kingsbury, Michael Picheny, James Glass. Cascaded Multilingual Audio-Visual Learning from Videos, Interspeech 2021


    (pdf), (code)


    Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen. Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision, accepted for ICML 2021


    (pdf), (DiffSort code), (YouTube)


     

    Aisha Urooj Khan, Hilde Kuehne, Kevin Duarte, Chuang Gan, Niels Lobo, Mubarak Shah. Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules, CVPR 2021


    (pdf), (code)


    Sirnam Swetha, Hilde Kuehne, Yogesh S Rawat, Mubarak Shah. Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities, arxiv


    (pdf)


     

    Rosaura G VidalMata, Walter J Scheirer, Anna Kukleva, David Cox, Hilde Kuehne. Joint visual-temporal embedding for unsupervised learning of actions in untrimmed sequences, WACV 2021


    (pdf)


     

    Quanfu Fan, Chun-Fu (Richard) Chen, Hilde Kuehne, Marco Pistoia, David Cox. More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation, NeurIPS 2019


    (pdf), (code)


     

    A. Kukleva*, H. Kuehne*, F. Sener, J. Gall. Unsupervised learning of action classes with continuous temporal embedding. CVPR 2019 (accepted)


    (pdf), (code)


     

    Hilde Kuehne*, Alexander Richard*, Juergen Gall, A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2019 (open access)


    (pdf)


     

    Alexander Richard, Hilde Kuehne, Ahsan Iqbal, Juergen Gall. NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018


    (pdf), (code)


     

    Alexander Richard, Hilde Kuehne, Juergen Gall. Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018


    (pdf), (bibtex), (code)


     

    Ahsan Iqbal, Alexander Richard, Hilde Kuehne, Juergen Gall. Recurrent Residual Learning for Action Recognition, German Conference on Pattern Recognition (GCPR), 2017 (Best Master's Award)


    (pdf), (bibtex)


     

    A. Richard, H. Kuehne and J. Gall. Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling, CVPR 2017 (oral)


    (website & downloads)


     

    H. Kuehne, A. Richard and J. Gall. Weakly supervised learning of actions from transcripts, CVIU (in press)


    (website & downloads)


     

    H. Kuehne, J. Gall and T. Serre. An end-to-end generative framework for video segmentation and recognition, WACV 2016


    (website & downloads)


     

    H. Kuehne, A. B. Arslan and T. Serre. The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities, CVPR 2014


    (Breakfast dataset: data & code)

     

    H. Kuehne, D. Gehrig, T. Schultz, R. Stiefelhagen. On-line Action Recognition from sparse Feature Flow, International Conference on Computer Vision Theory and Applications 2012


    (data & annotations)

     

    H. Kuehne, H. Jhuang, E. Garrote, T. Poggio, T. Serre. HMDB: A Large Video Database for Human Motion Recognition, ICCV 2011


    (project website)

    Visapp 2010
    Angers, France

     

     

    H. Kuehne, A. Woerner. Motion Segmentation of Articulated Structures by Integration of Visula Perception Criteria, International Conference on Computer Vision Theory and Applications (VisApp), Angers, France, 2010

    (pdf)(bibtex)

    ICCV 2009,
     Kyoto, Japan

     

    A. Bachmann, H. Kuehne. An Iterative Scheme for Motion-Based Scene Segmentation. ICCV 2009, Workshop on Dynamical Vision (DV), pp. 735-742, Kyoto, Japan, October 2009

    (pdf)(bibtex)

     



     

     

     

     

    Publications
     ____________________________________________________________________________________________


    CVPR 2019

     

    A. Kukleva*, H. Kuehne*, F. Sener, J. Gall. Unsupervised learning of action classes with continuous temporal embedding. CVPR 2019 (accepted)


    TPAMI 2019

     

    Hilde Kuehne*, Alexander Richard*, Juergen Gall, A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2019


    (pdf)


    CVPR 2018

     

    Alexander Richard, Hilde Kuehne, Ahsan Iqbal, Juergen Gall. NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018


    (pdf), (code)


    CVPR 2018

     

    Alexander Richard, Hilde Kuehne, Juergen Gall. Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018


    (pdf), (bibtex), (code)


    GCPR 2017

     

    Ahsan Iqbal, Alexander Richard, Hilde Kuehne, Juergen Gall. Recurrent Residual Learning for Action Recognition, German Conference on Pattern Recognition (GCPR), 2017 (Best Master's Award)


    CVPR 2017

     

    A. Richard, H. Kuehne and J. Gall. Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling, CVPR 2017


    (website)


    arXiv:1610.02237

     

    H. Kuehne, A. Richard and J. Gall. Weakly supervised learning of actions from transcripts (under review)


    (website & downloads)

    arXiv:1508.06073

     

    Cooking in the kitchen: Recognizing and Segmenting Human Activities in Videos, arxiv


    (Website, downloads)

    WACV 2016
    Lake Placid, NY

     

    H. Kuehne, J. Gall and T. Serre. An end-to-end generative framework for video segmentation and recognition, WACV 2016


    (website & downloads)

    PhD

     

    H. Kuehne. Analysis and recognition of human actions with flow features and temporal models, Karlsruhe Institute of Technology, 2015


    (pdf) (ref)

    CVPR 2014
    Columbus, Ohio

     

    H. Kuehne, A. B. Arslan and T. Serre. The Language of Actions: Recovering the Syntax and Semantics of Goal-Directed Human Activities, CVPR 2014


    (website & downloads)

    Visapp 2012
    Rome, Italy

     

    H. Kuehne, D. Gehrig, T. Schultz, R. Stiefelhagen. On-line Action Recognition from sparse Feature Flow, International Conference on Computer Vision Theory and Applications 2012


    (pdf) (bibtex) (website & downloads)

    ICCV 2011
    Barcelona, Spain

     

    H. Kuehne, H. Jhuang, E. Garrote, T. Poggio, T. Serre. HMDB: A Large Video Database for Human Motion Recognition, ICCV 2011


    (project website)

    IROS 2011
    San Francisco, USA

     

    P. Krauthausen, L. Rybok, U. D. Hanebeck, D. Gehrig, H. Kuehne, T. Schultz, R. Stiefelhagen. Combined Intention, Activity, and Motion Recognition for a Humanoid Household Robot, IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2011


    (pdf) (bibtex)

    Visapp 2010
    Angers, France

     

     

    H. Kuehne, A. Woerner. Motion Segmentation of Articulated Structures by Integration of Visula Perception Criteria, International Conference on Computer Vision Theory and Applications (VisApp), Angers, France, 2010

    (pdf)(bibtex)

    Humanoids 2009
    Paris, France

     

    D. Gehrig, H. Kuehne, A. Woerner, T. Schultz. HMM-based Human Motion Recognition with Optical Flow Data. Humanoids 2009, Humanoids 2009, Paris, France, 09. December 2009

    (pdf)(bibtex)

    ICCV 2009,
     Kyoto, Japan

     

    A. Bachmann, H. Kuehne. An Iterative Scheme for Motion-Based Scene Segmentation. ICCV 2009, Workshop on Dynamical Vision (DV), pp. 735-742, Kyoto, Japan, October 2009

    (pdf)(bibtex)

     

    VisApp 2009
    Lisboa, Portugal

     

    H. Kuehne, A. Woerner. Motion-Based Feature Clustering for Articulated Body Tracking, International Conference on Computer Vision Theory and Applications (VisApp), Lisboa, Portugal, February 2009

    (pdf)(bibtex)

     

    Humanoids 2008
    Daejeon, Korea

     

    D. Gehrig, A. Fischer, H. Kuehne, T. Stein, A. Woerner, H. Schwameder and T. Schultz. Online Recognition of Daily-Life Movements. IEEE-RAS International Conference on Humanoid Robots (Humanoids 2008), Workshop Imitation and Coaching in Humanoid Robots. Daejeon, Korea, December 2008


    (pdf)(bibtex)(slides)

    Humanoids 2008
    Daejeon, Korea

     

    M. Do, D. Gehrig, H. Kuehne, P. Azad, P. Pastor, T. Asfour, T. Schultz, A. Woerner, R. Dillmann. Transfer of Human Movements to Humanoid Robots. IEEE-RAS International Conference on Humanoid Robots (Humanoids 2008). Workshop Imitation and Coaching in Humanoid Robots. Daejeon, Korea, December 2008

    (pdf)(bibtex)

     

    ESM 2008
    LeHavre, France

     

    M. Pruzinec, H. Koehler, A. Woerner. Localisation of Joint Rotation Centres for 3D Human Motion Simulation. 22nd annual European Simulation and Modelling Conference. October 2008. LeHavre, France.

    (pdf)(bibtex)

     

    ICMI 2008
    Chania, Greece

     

    H. Koehler, A. Woerner. Motion-based Feature Tracking For Articulated Motion Analysis, IEEE Int. Conf. on Multimodal Interfaces (ICMI 2008), Workshop on Multimodal Interactions Analysis of Users a Controlled Environment. October 20-22, 2008. Chania, Greece.

    (pdf)(bibtex)

     

    Sporttechnologie zwischen Theorie und Praxis, 2007
    Shaker, Aachen

     

    T. Stein, A. Fischer, I. Boesnach, D. Gehrig, H. Koehler, H. Schwameder. Kinematische Analyse menschlicher Alltagsbewegungen für die Mensch-Maschine-Interaktion. In J. Edelmann-Nusser, K. Witte & E.F. Moritz (Hrsg.), Sporttechnologie zwischen Theorie und Praxis V. Shaker, Aachen

    (pdf)(bibtex)

     

    WSCG 2008
    Pilsen,  Czech Republic

     

    H. Koehler, M. Pruzinec, T. Feldmann, A. Woerner. Automatic Human Model Parametrization From 3D Marker Data For Motion Recognition, WSCG'2008 - 16th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, Pilsen, 2008

    (pdf+bibtex)

     

    HLR 2006
    Karlsruhe, Germany

     

    I. Boesnach, H. Koehler, D. Gehrig, G. Stelzner, C. Simonidis, A. Fischer, T. Stein. A large-scale database of human movements to humanize robot motion, French-German Workshop on Humanoid and Legged Robots

    (bibtex)

     

    BMT 2005
    Nürnberg, Germany

     

     

    H. Koehler, T. Wittenberg, D. Paulus. Detection and Segmentation of cervical cell nuclei, Biomedizinische Technik, Schiele und Schön, Berlin, 50, Vol. 1, Part 1, S. 588-589, 10/2005

    (pdf)(bibtex)

     

    SPIE Medical Imaging 2004
    San Diego, CA

     

    H. Koehler, M. Couprie, S. Bouattour, D. Paulus. Extraction and Analysis of Coronary-tree from single X-ray Angiographies, S. 810-819, 2004

    (pdf)(bibtex)

    BVM 2004
    Berlin, Germany

     

    H. Koehler, S. Bouattour, D. Paulus, M. Couprie. Analyse des Herzkranzgefäßbaums für die prä- und post-operative Diagnose, Bildverarbeitung für die Medizin, Springer Verlag, Springer, S. 269-273, 2004

    (pdf)(bibtex)



     

     

     

     

     

     

     

     

     

     

     

    CV


    ____________________________________________________________________________________________

    Since 3/2019

     

    Researcher at MIT-IBM Watson Lab (https://mitibmwatsonailab.mit.edu )

    Since 1/2016

     

    Co Founder and Head of Research and Development of KS-Research (Dr. Hildegard Kuehne - Dr. Stefan Stein GbR, https://www.ks-research.de )

    2/2016 - 2/2019

     

    PostDoc Computer Vision Group Prof Dr. Juergen Gall, Institute of Computer Science III, University of Bonn

    10/2013 - 1/2016

     

    Researcher at the Fraunhofer Institute for Communication, Information Processing and Ergonomics (FKIE), Bonn, department for Sensor Data and Information Fusion (SDF), Dr. Wolfgang Koch

    8/2006 - 10/2013

     

    PhD student at the Karlsruhe Institute of Technology (KIT), Institute for Anthropomathics, Department of Informatics

    6/2005 – 1/2006

     

    Master thesis ‘Detection and Segmentation of cervical cell nuclei‘ at the University Koblenz-Landau

    6/ 2005

     

    Diploma (master) in computer science with specialization in computational visualistics at the University Koblenz-Landau

    3/2003 - 7/2003

     

    Study thesis ‚Extraction and Analysis of Coronary-tree from single X-ray Angiographies’ at the École Supérieure d'Ingénieurs en Électronique et Électrotechnique, ESIEE, Paris

    2001/2002

     

    Pre-Degree in computer sciences (computational visualistics)at the University Koblenz-Landau

    1999 – 2006

     

    Student of computer sciences (computational visualistics) at the University Koblenz-Landau