Gall, Jürgen

Prof. Dr. Jürgen Gall

University of Bonn

Institute of Computer Science III

Computer Vision Group

Office A.114

Römerstraße 164

53117 Bonn

Germany

E-mail: gall@iai.uni-bonn.de

Phone: +49 228 73 4380

Research Interests

Human pose estimation

Object detection

Action recognition

Job Offers/Theses

PhD and Postdoc positions are available. The topics are in the areas of action recognition, object detection, and human pose estimation. For more details, please contact me.

Several bachelor and master projects are available. The topics include action recognition, object detection, semantic segmentation, scene understanding, human pose estimation, machine learning for computer vision, and computer vision with RGB-D sensors. If you are interested, do not hesitate to contact me.

The University of Bonn offers an excellent master program with focus on Graphics, Vision, Audio. More information including application procedure can be found at the Institute of Computer Science.

Publications

Tzionas D., Ballan L., Srikantha A., Aponte P., Pollefeys M., and Gall J., Capturing Hands in Action using Discriminative Salient Points and Physics Simulation (PDF, Images/Videos/Data), International Journal of Computer Vision, Special Issue on Human Activity Understanding from 2D and 3D data, Vol 118(2), 172-193, Springer, 2016. ©Springer-Verlag

Richard A. and Gall J., Temporal Action Detection using a Statistical Language Model (PDF, Code), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16), To appear.

Yasin H., Iqbal U., Krüger B., Weber A., and Gall J., A Dual-Source Approach for 3D Pose Estimation from a Single Image (PDF), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16), To appear.

Ristin M., Guillaumin M., Gall J., and van Gool L., Incremental Learning of Random Forests for Large-Scale Image Classification (PDF, Images/Code), IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 38, No. 3, 490 - 503, 2016. ©IEEE

Kuehne H., Gall J., and Serre T., An end-to-end generative framework for video segmentation and recognition (PDF), IEEE Winter Conference on Applications of Computer Vision (WACV'16), To appear.

Gall J., Gehler P., and Leibe B. (Eds.), Pattern Recognition - 37th German Conference on Pattern Recognition (GCPR'15) (Book), Image Processing, Computer Vision, Pattern Recognition, and Graphics, Springer, LNCS 9358, 2015.

Tzionas D. and Gall J., 3D Object Reconstruction from Hand-Object Interactions (PDF, Images/Data/Code), International Conference on Computer Vision (ICCV'15), 729 - 737, 2015. ©IEEE

Panareda Busto P., Liebelt L., and Gall J., Adaptation of Synthetic Data for Coarse-to-Fine Viewpoint Refinement (PDF), British Machine Vision Conference (BMVC'15), 2015.

Richard A. and Gall J., A BoW-equivalent Recurrent Neural Network for Action Recognition (PDF, Code), British Machine Vision Conference (BMVC'15), 2015.

Srikantha A. and Gall J., Human Pose as Context for Object Detection (PDF), British Machine Vision Conference (BMVC'15), 2015.

Rafi U., Gall J., and Leibe B., A Semantic Occlusion Model for Human Pose Estimation from a Single Depth Image (PDF, Data), ChaLearn Looking at People Workshop, 67 - 74, 2015. ©IEEE

Ristin M., Gall J., Guillaumin M., and van Gool L., From Categories to Subcateories: Large-scale Image Classification with Partial Class Label Refinement (PDF, Images/Data/Code), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'15), 231 - 239, 2015. ©IEEE

Liu Y., Gall J., Loscos C., and Dai Q., Reconstruction of Human Motion, Digital Representations of the Real World: How to Capture, Model, and Render Visual Reality, Magnor M., Grau O., Sorkine-Hornung O., Theobalt C. (Eds.), CRC Press, 2015. ©Taylor & Francis Group

Dantone M., Gall J., Leistner C., and van Gool L., Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images (PDF, Supplemental material, Extended version, Images/Data), IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 36, No. 11, 2131-2143, 2014. ©IEEE

Eweiwi A., Cheema M., Bauckhage C., and Gall J., Efficient Pose-based Action Recognition (PDF, Code), Asian Conference on Computer Vision (ACCV'14), Springer, LNCS 9007, 428-443, 2015. ©Springer-Verlag

Tzionas D., Srikantha A., Aponte P., and Gall J., Capturing Hand Motion with an RGB-D Sensor, Fusing a Generative Model with Salient Points (PDF, Images/Videos/Data), German Conference on Pattern Recognition (GCPR'14), Springer, LNCS 8753, 277-289, 2014. ©Springer-Verlag

Kostrikov I. and Gall J., Depth Sweep Regression Forests for Estimating 3D Human Pose from Images (PDF, Images), British Machine Vision Conference (BMVC'14), 2014.

Srikantha A. and Gall J., Discovering Object Classes from Activities (PDF, Images/Data), European Conference on Computer Vision (ECCV'14), Springer, LNCS 8694, 415-430, 2014. ©Springer-Verlag

Weinmann M., Gall J., and Klein R., Material Classification based on Training Data Synthesized Using a BTF Database (PDF, Images/Data), European Conference on Computer Vision (ECCV'14), Springer, LNCS 8691, 156-171, 2014. ©Springer-Verlag

Srikantha A. and Gall J., Hough-based Object Detection with Grouped Features (PDF), IEEE International Conference on Image Processing (ICIP'14), 1653 - 1657, 2014. ©IEEE

Ristin M., Guillaumin M., Gall J., and van Gool L., Incremental Learning of NCM Forests for Large-Scale Image Classification (PDF, Images/Code), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'14), 3654 - 3661, 2014. ©IEEE

Gall J., Simulated Annealing, Encyclopedia of Computer Vision, Ikeuchi K. (Eds.), Springer, 737-741, 2014. ©Springer-Verlag

Beetz M., Cremers D., Gall J., Li W., Liu Z., Pangercic D., Sturm J., and Tai Y.-W., Special Issue on Visual Understanding and Applications with RGB-D Cameras (Issue), Journal of Visual Communication and Image Representation, Vol. 25, No. 1, 1-238, 2014.

Jhuang H., Gall J., Zuffi S., Schmid C., and Black M., Towards Understanding Action Recognition (PDF, Images/Data), International Conference on Computer Vision (ICCV'13), 3192 - 3199, 2013. ©IEEE

Ye M., Zhang Q., Wang L., Zhu J., Yang R., and Gall J., A Survey on Human Motion Analysis from Depth Data (PDF, Tutorial), Time-of-Flight and Depth Imaging. Sensors, Algorithms, and Applications, Grzegorzek M., Theobalt C., Koch R., and Kolb A. (Eds.), Springer, LNCS 8200, 149-187, 2013. ©Springer-Verlag

Liu Y., Gall J., Stoll C., Dai Q., Seidel H.-P., and Theobalt C., Markerless Motion Capture of Multiple Characters Using Multi-view Image Segmentation (PDF, Images/Video/Data), IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, No. 11, 2720-2735, 2013. ©IEEE

Tzionas D. and Gall J., A Comparison of Directional Distances for Hand Pose Estimation (PDF, Images/Data), German Conference on Pattern Recognition (GCPR'13), Springer, LNCS 8142, 131-141, 2013. ©Springer-Verlag

Dantone M., Gall J., Leistner C., and van Gool L., Human Pose Estimation using Body Parts Dependent Joint Regressors (PDF, Images/Data), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'13), 3041-3048, 2013. ©IEEE

Gall J. and Lempitsky V., Class-Specific Hough Forests for Object Detection (Images/Code), Decision Forests for Computer Vision and Medical Image Analysis, Criminisi A. and Shotton J. (Eds.), Springer, 145-160, 2013. ©Springer-Verlag

Fanelli G., Dantone M., Gall J., Fossati A. and van Gool L., Random Forests for Real Time 3D Face Analysis (PDF, Images/Videos/Data/Code), International Journal of Computer Vision, Special Issue on Human Computer Interaction, Vol 101(3), 437-458, Springer, 2013. ©Springer-Verlag

Ristin M., Gall J., and van Gool L., Local Context Priors for Object Proposal Generation (PDF, Images), Asian Conference on Computer Vision (ACCV'12), Springer, LNCS 7724, 57-70, 2013. ©Springer-Verlag

Fossati A., Gall J., Grabner H., Ren X., and Konolige K. (Eds.), Consumer Depth Cameras for Computer Vision - Research Topics and Applications (Book, Workshop), Advances in Computer Vision and Pattern Recognition, Springer, 2012.

Razavi N., Gall J., Kohli P., and van Gool L., Latent Hough Transform for Object Detection (PDF, Images), European Conference on Computer Vision (ECCV'12), Springer, LNCS 7574, 312-325, 2012. ©Springer-Verlag

Ballan L., Taneja A., Gall J., van Gool L., and Pollefeys M., Motion Capture of Hands in Action using Discriminative Salient Points (PDF, Images/Videos/Data), European Conference on Computer Vision (ECCV'12), Springer, LNCS 7577, 640-653, 2012. ©Springer-Verlag

Pellegrini S., Gall J., Sigal L., and van Gool L., Destination Flow for Crowd Simulation (PDF), Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams (ARTEMIS'12), Springer, LNCS 7585, 162-171, 2012. ©Springer-Verlag

Razavi N., Alvar N., Gall J., and van Gool L., Sparsity Potentials for Detecting Objects with the Hough Transform (PDF, Images), British Machine Vision Conference (BMVC'12), 2012.

López-Méndez A., Gall J., Casas J., and van Gool L., Metric Learning from Poses for Temporal Clustering of Human Motion (PDF, Images/Videos), British Machine Vision Conference (BMVC'12), 2012.

Gall J., Razavi N., and van Gool L., An Introduction to Random Forests for Multi-class Object Detection (PDF, Images/Code), Theoretic Foundations of Computer Vision: Outdoor and Large-Scale Real-World Scene Analysis, Dellaert F, Frahm J.-M., Pollefeys M., Rosenhahn B., and Leal-Taixé L. (Eds.), Springer, LNCS 7474, 243-263, 2012. ©Springer-Verlag

Pons-Moll G., Leal-Taixé L., Gall J., and Rosenhahn B., Data-driven Manifolds for Outdoor Motion Capture (PDF, Images/Videos), Theoretic Foundations of Computer Vision: Outdoor and Large-Scale Real-World Scene Analysis, Dellaert F, Frahm J.-M., Pollefeys M., Rosenhahn B., and Leal-Taixé L. (Eds.), Springer, LNCS 7474, 305-328, 2012. ©Springer-Verlag

Yao A., Gall J., and van Gool L., Coupled Action Recognition and Pose Estimation from Multiple Views (PDF, Images/Videos/Code), International Journal of Computer Vision, Vol 100(1), 16-37, Springer, 2012. ©Springer-Verlag

Dantone M., Gall J., Fanelli G., and van Gool L., Real-time Facial Feature Detection using Conditional Regression Forests (PDF, Images/Videos/Data/Code), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'12), 2578-2585, 2012. ©IEEE

Yao A., Gall J., Leistner C., and van Gool L., Interactive Object Detection (PDF, Images/Videos), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'12), 3242-3249, 2012. ©IEEE

Fanelli G., Gall J., and van Gool L., Real Time 3D Head Pose Estimation: Recent Achievements and Future Challenges (PDF, Images/Videos/Data/Code), 5th International Symposium on Communications, Control and Signal Processing (ISCCSP'12), 2012. ©IEEE

Yao A., Gall J., van Gool L., and Urtasun R., Learning Probabilistic Non-Linear Latent Variable Models for Tracking Complex Activities (PDF, Images/Code), Neural Information Processing Systems (NIPS'11), 2011.

Pons-Moll G., Baak A., Gall J., Leal-Taixe L., Mueller M., Seidel H.-P., Rosenhahn B., Outdoor Human Motion Capture using Inverse Kinematics and von Mises-Fisher Sampling (PDF, Images/Videos), International Conference on Computer Vision (ICCV'11), 1243-1250, 2011. ©IEEE

Stoll C., Hasler N., Gall J., Seidel H.-P., and Theobalt C., Fast Articulated Motion Tracking using a Sums of Gaussians Body Model (PDF, Images/Videos), International Conference on Computer Vision (ICCV'11), 951-958, 2011. ©IEEE

Uebersax D., Gall J., van den Bergh M., and van Gool L., Real-time Sign Language Letter and Word Recognition from Depth Data (PDF, Supplemental material, Video), IEEE Workshop on Human Computer Interaction: Real-Time Vision Aspects of Natural User Interfaces (HCI'11), 383-390, 2011. ©IEEE

Gall J., Yao A., Razavi N., van Gool L., and Lempitsky V., Hough Forests for Object Detection, Tracking, and Action Recognition (PDF, Images/Code), IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 33, No. 11, 2188-2202, 2011. ©IEEE

Yao A., Gall J., Fanelli G., and van Gool L., Does Human Action Recognition Benefit from Pose Estimation? (PDF, Images), British Machine Vision Conference (BMVC'11), 2011.

Fanelli G., Weise T., Gall J., and van Gool L., Real Time Head Pose Estimation from Consumer Depth Cameras (PDF, Images/Videos/Data/Code), 33rd Annual Symposium of the German Association for Pattern Recognition (DAGM'11), Springer, LNCS 6835, 101-110, 2011. ©Springer-Verlag

Gall J., Fossati A., and van Gool L., Functional Categorization of Objects using Real-time Markerless Motion Capture (PDF, Images/Video/Data), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11), 1969-1976, 2011. ©IEEE

Grabner H., Gall J., and van Gool L., What Makes a Chair a Chair? (PDF, Images/Data), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11), 1529-1536, 2011. ©IEEE

Razavi N., Gall J., and van Gool L., Scalable Multi-class Object Detection (PDF, Images/Code), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11), 1505-1512, 2011. ©IEEE

Fanelli G., Gall J., and van Gool L., Real Time Head Pose Estimation with Random Regression Forests (PDF, Images/Videos/Data/Code), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11), 617-624, 2011. ©IEEE

Liu Y., Stoll C., Gall J., Seidel H.-P., and Theobalt C., Markerless Motion Capture of Interacting Characters Using Multi-view Image Segmentation (PDF, Images/Video/Data), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11), 1249-1256, 2011. ©IEEE

Hamer H., Gall J., Urtasun R., and van Gool L., Data-Driven Animation of Hand-Object Interactions (PDF, Video with Audio), IEEE Conference on Automatic Face and Gesture Recognition, 360-367, 2011. ©IEEE

Stoll C., Gall J., de Aguiar E., Thrun S., and Theobalt C., Video-based Reconstruction of Animatable Human Characters (PDF, Images/Videos), ACM Transactions on Graphics (SIGGRAPH Asia 2010), Vol. 29, No. 6, 2010. ©ACM

Yao A., Uebersax D., Gall J., and van Gool L., Tracking People in Broadcast Sports (PDF), 32nd Annual Symposium of the German Association for Pattern Recognition (DAGM'10), Springer, LNCS 6376, 151-161, 2010. ©Springer-Verlag

Gall J., Yao A., and van Gool L., 2D Action Recognition Serves 3D Human Pose Estimation (PDF, Images/Videos/Code), European Conference on Computer Vision (ECCV'10), Springer, LNCS 6313, 425-438, 2010. ©Springer-Verlag

Razavi N., Gall J., and van Gool L., Backprojection Revisited: Scalable Multi-view Object Detection and Similarity Metrics for Detections (PDF, Images/Videos), European Conference on Computer Vision (ECCV'10), Springer, LNCS 6311, 620-633, 2010. ©Springer-Verlag

Fanelli G., Yao A., Noel P.-L., Gall J., and van Gool L., Hough Forest-based Facial Expression Recognition from Video Sequences, Workshop on Sign, Gesture and Activity (SGA'10), 2010. ©Springer-Verlag

Gall J., Razavi N., and van Gool L., On-line Adaption of Class-specific Codebooks for Instance Tracking (PDF, Images/Videos), British Machine Vision Conference (BMVC'10), 2010.

Fanelli G., Gall J., Romsdorfer H., Weise T., and van Gool L., A 3D Audio-Visual Corpus of Affective Communication (PDF, Data), IEEE Transactions on Multimedia, Special Issue on Multimodal Affective Interaction, Vol. 12, No. 6, 591-598, 2010. ©IEEE

Waltisberg D., Yao A., Gall J., and van Gool L., Variations of a Hough-Voting Action Recognition System (PDF, Images/Videos), Proceedings of the ICPR 2010 Contests, Springer, LNCS 6388, 306-312, 2010. ©Springer-Verlag

Yao A., Gall J., and van Gool L., A Hough Transform-Based Voting Framework for Action Recognition (PDF, Images/Videos), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'10), 2010. ©IEEE

Hamer H., Gall J., Weise T., and van Gool L., An Object-Dependent Hand Pose Prior from Sparse Training Data (PDF, Images/Videos), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'10), 2010. ©IEEE

Fanelli G., Gall J., Romsdorfer H., Weise T., and van Gool L., 3D Vision Technology for Capturing Multimodal Corpora: Chances and Challenges (PDF), Multimodal Corpora: Advances in Capturing, Coding and Analyzing Multimodality, 2010.

Brox T., Rosenhahn B., Gall J., and Cremers D., Combined Region- and Motion-based 3D Tracking of Rigid and Articulated Objects (PDF), IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol 32(3), 402-415, 2010. ©IEEE

Gall J., Rosenhahn B., Brox T., and Seidel H.-P., Optimization and Filtering for Human Motion Capture - A Multi-layer Framework (PDF, Images/Videos), International Journal of Computer Vision, Special Issue on Evaluation of Articulated Human Motion and Pose Estimation, Vol 87(1), 75-92, Springer, 2010. ©Springer-Verlag

Shaheen M., Gall J., Strzodka R., van Gool L., and Seidel H.-P., A Comparison of 3D Model-based Tracking Approaches for Human Motion Capture in Uncontrolled Environments (PDF, Images/Videos), IEEE Workshop on Applications of Computer Vision (WACV'09), 2009. ©IEEE

Fanelli G., Gall J., van Gool L., Hough Transform-based Mouth Localization for Audio-Visual Speech Recognition (PDF, Images/Videos), British Machine Vision Conference (BMVC'09), 2009.

Gall J., Stoll C., de Aguiar E., Theobalt C., Rosenhahn B., and Seidel H.-P., Motion Capture Using Joint Skeleton Tracking and Surface Estimation (PDF, Images/Videos/Data), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09), 2009. ©IEEE

Gall J. and Lempitsky V., Class-Specific Hough Forests for Object Detection (PDF, Images/Code), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09), 2009. ©IEEE

Hasler N., Rosenhahn B., Thormählen T., Wand M., Gall J., and Seidel H.-P., Markerless Motion Capture with Unsynchronized Moving Cameras (PDF, Images/Videos), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09), 2009. ©IEEE

Gall J., Rosenhahn B., Gehrig S., and Seidel H.-P., Model-based Motion Capture for Crash Test Video Analysis (PDF, Images/Videos), 30th Annual Symposium of the German Association for Pattern Recognition (DAGM'08), Springer, LNCS 5096, 92-101, 2008. ©Springer-Verlag

Gall J., Rosenhahn B., and Seidel H.-P., Drift-free Tracking of Rigid and Articulated Objects (PDF, Images/Videos), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'08), 2008. ©IEEE

Gall J., Rosenhahn B., and Seidel H.-P., An Introduction to Interacting Simulated Annealing (PDF), Human Motion - Understanding, Modeling, Capture and Animation, Klette R., Metaxas D., and Rosenhahn B. (Eds.), Computational Imaging and Vision, Vol 36, 319-345, Springer, 2008. ©Springer-Verlag

Gehrig S., Badino H., and Gall J., Accurate and Model-Free Pose Estimation of Crash Test Dummies Human Motion - Understanding, Modeling, Capture and Animation, Klette R., Metaxas D., and Rosenhahn B. (Eds.), Computational Imaging and Vision, Springer, Vol 36, 453-473, 2008. ©Springer-Verlag

Gall J., Brox T., Rosenhahn B., and Seidel H.-P., Global Stochastic Optimization for Robust and Accurate Human Motion Capture (PDF), Technical Report MPI-I-2007-4-008, Department 4: Computer Graphics, Max-Planck Institute für Informatik, Saarbrücken, Germany, Dec. 2007.

Gall J., Rosenhahn B., and Seidel H.-P., Clustered Stochastic Optimization for Object Recognition and Pose Estimation (PDF, Images/Videos), 29th Annual Symposium of the German Association for Pattern Recognition (DAGM'07), Springer, LNCS 4713, 32-41, 2007. ©Springer-Verlag

Gall J., Potthoff J., Schnörr C., Rosenhahn B., and Seidel H.-P., Interacting and Annealing Particle Filters: Mathematics and a Recipe for Applications, Journal of Mathematical Imaging and Vision. Springer, 28(1), 1-18, 2007. ©Springer-Verlag

Gall J., Potthoff J., Schnörr C., Rosenhahn B., and Seidel H.-P., Interacting and Annealing Particle Filters: Mathematics and a Recipe for Applications (PDF), Technical Report MPI-I-2006-4-009, Department 4: Computer Graphics, Max-Planck Institute für Informatik, Saarbrücken, Germany, Sept. 2006.

Gall J., Rosenhahn B., and Seidel H.-P., Robust Pose Estimation with 3D Textured Models (PDF, Images/Videos), IEEE Pacific-Rim Symposium on Image and Video Technology (PSIVT'06), Springer, LNCS 4319, 84-95, 2006. ©Springer-Verlag

Gall J., Rosenhahn B., Brox T., and Seidel H.-P., Learning for Multi-View 3D Tracking in the Context of Particle Filters (PDF, Images/Videos), International Symposium on Visual Computing (ISVC'06), Springer, LNCS 4292, 59-69, 2006. ©Springer-Verlag

Software

Temporal Action Detection using a Statistical Language Model

A BoW-equivalent Recurrent Neural Network for Action Recognition

3D Object Reconstruction from Hand-Object Interactions

From Categories to Subcateories: Large-scale Image Classification with Partial Class Label Refinement

Efficient Pose-based Action Recognition

Incremental Learning of NCM Forests for Large-Scale Image Classification

Real-time Facial Feature Detection using Conditional Regression Forests

Learning Probabilistic Non-Linear Latent Variable Models for Tracking Complex Activities

Real Time Head Pose Estimation with Random Regression Forests

Scalable Multi-class Object Detection

2D Action Recognition Serves 3D Human Pose Estimation

A Hough Transform-Based Voting Framework for Action Recognition

Class-Specific Hough Forests for Object Detection

Data

Capturing Hands in Action using Discriminative Salient Points and Physics Simulation

3D Object Reconstruction from Hand-Object Interactions

A Semantic Occlusion Model for Human Pose Estimation from a Single Depth Image

From Categories to Subcateories: Large-scale Image Classification with Partial Class Label Refinement

Material Classification based on Training Data Synthesized Using a BTF Database

Capturing Hand Motion with an RGB-D Sensor, Fusing a Generative Model with Salient Points

Discovering Object Classes from Activities

Towards Understanding Action Recognition

Human Pose Estimation using Body Parts Dependent Joint Regressors

Motion Capture of Hands in Action using Discriminative Salient Points

Real-time Facial Feature Detection using Conditional Regression Forests

Real Time Head Pose Estimation with Random Regression Forests

Functional Categorization of Objects using Real-time Markerless Motion Capture

What Makes a Chair a Chair?

Biwi 3D Audiovisual Corpus of Affective Communication - B3D(AC)^2

Hand-Object Interaction (HOI) Dataset

Motion Capture Using Joint Skeleton Tracking and Surface Estimation

Markerless Motion Capture with Unsynchronized Moving Cameras

Projects

Analysis and Representation of Complex Activities in Videos (ARCA), ERC Starting Grant

Mapping on Demand (MoD), DFG Research Unit FOR 1505

Human Focused Visual Scene Understanding (HFVSA), DFG Independent Junior Research Group

Workshops/Conferences/Special Issues/Tutorials

Cross-Media Big Data Analytics, Journal of Visual Communication and Image Representation (JVCI). Guest Editors: An-An Liu (Tianjin University), Ke Gao (Chinese Academy of Sciences), Liqiang Nie (National University of Singapore), Juergen Gall (University of Bonn), and Yi Yang (University of Technology Sydney).

Deep Learning with Applications to Visual Representation and Analysis, Signal Processing: Image Communication. Guest Editors: Lei Wang (University of Wollongong), Ce Zhu (University of Electronic Science and Technology of China), Jieping Ye (University of Michigan), and Juergen Gall (University of Bonn).

37th German Conference on Pattern Recognition (GCPR), Aachen, Germany, 7-10 October 2015. Call for papers. General chair: Bastian Leibe (RWTH Aachen University). Program chairs: Juergen Gall (University of Bonn) and Peter Gehler (Max Planck Institute for Intelligent Systems).

Visual Perception of Affordances and Functional Visual Primitives for Scene Analysis, Zurich, Switzerland, 7 September 2014, in conjunction with ECCV'14. Organizers: Karthik Mahesh Varadarajan (Technical University of Vienna), Alireza Fathi (Stanford University), Juergen Gall (University of Bonn), Markus Vincze (Technical University of Vienna).

Workshop on Consumer Depth Cameras for Computer Vision, Zurich, Switzerland, 6 September 2014, in conjunction with ECCV'14. Organizers: Andrea Fossati (ETH Zurich), Juergen Gall (University of Bonn), and Miles Hansard (Queen Mary University London).

Affordances in Vision for Cognitive Robotics, Berkeley, CA, USA, 13 July 2014, in conjunction with RSS'14. Organizers: Karthik Mahesh Varadarajan (Technical University of Vienna), Markus Vincze (Technical University of Vienna), Trevor Darrell (University of California, Berkeley), and Juergen Gall (University of Bonn).

Tutorial on Towards Solving Real-World Vision Problems with RGB-D Cameras, Columbus, OH, USA, 28 June 2014, in conjunction with CVPR'14. Organizers: Juergen Gall (University of Bonn), Xiaofeng Ren (Amazon), and Pushmeet Kohli (Microsoft Research Cambridge).

Workshop on Consumer Depth Cameras for Computer Vision, Sydney, Australia, 2 December 2013, in conjunction with ICCV'13. Organizers: Andrea Fossati (ETH Zurich), Juergen Gall (University of Bonn), Helmut Grabner (ETH Zurich), and Miles Hansard (Queen Mary University London).

Bonn Vision Workshop 2013, Bonn, Germany, 1 October 2013. Organizers: Simone Frintrop (University of Bonn), Juergen Gall (University of Bonn), and Armin B. Cremers (University of Bonn).

Tutorial on Towards Solving Real-World Vision Problems with RGB-D Cameras, Portland, OR, USA, 23 June 2013, in conjunction with CVPR'13. Organizers: Xiaofeng Ren (Amazon), Pushmeet Kohli (Microsoft Research Cambridge), and Juergen Gall (University of Bonn).

Workshop on Consumer Depth Cameras for Computer Vision, Firenze, Italy, 12 October 2012, in conjunction with ECCV'12. Organizers: Andrea Fossati (ETH Zurich), Juergen Gall (Max Planck Institute for Intelligent Systems), Helmut Grabner (ETH Zurich), Xiaofeng Ren (Intel Labs), Kurt Konolige (Willow Garage), Seungkyu Lee (Samsung Advanced Institute of Technology), and Miles Hansard (Queen Mary University London).

Visual Understanding and Applications with RGB-D Cameras, Journal of Visual Communication and Image Representation (JVCI). Guest Editors: Michael Beetz (TU Munich), Daniel Cremers (TU Munich), Juergen Gall (ETH Zurich), Wanqing Li (University of Wollongong), Zicheng Liu (Microsoft Research Redmond), Dejan Pangercic (TU Munich), Juergen Sturm (TU Munich), and Yu-Wing Tai (KAIST).

IEEE Workshop on Consumer Depth Cameras for Computer Vision, Barcelona, Spain, 12 November 2011, in conjunction with ICCV'11. Organizers: Andrea Fossati (ETH Zurich), Juergen Gall (ETH Zurich), Helmut Grabner (ETH Zurich), Xiaofeng Ren (Intel Labs Seattle), and Kurt Konolige (Willow Garage).

Editorial

Journal of Visual Communication and Image Representation

PeerJ Computer Science

Teaching

Römer-Friedrich PhD Seminar - Graphics, Vision, Audio for Intelligent Systems, SS13, WS13/14, SS14, WS14/15, SS15, WS15/16, SS16

BA-INF 062 - Begleitseminar zur Bachelorarbeit: Computer Vision, SS14, WS14/15, SS15, WS15/16, SS16

MA-INF 2201 - Computer Vision, WS13/14, WS14/15, WS15/16

MA-INF 2213 - Computer Vision II, SS14, SS15, SS16

MA-INF 2206 - Seminar Vision: Selected Topics in Computer Vision, WS13/14, SS14, WS14/15, SS15, WS15/16, SS16

MA-INF 2307 - Lab Vision: RGBD cameras, WS13/14, SS14, WS14/15, SS15, WS15/16, SS16

MA-INF 0402 - Master Thesis, Accompanying Seminar, WS14/15, SS15, WS15/16, SS16

Talks

Estimating Human Pose and Activity, Centre for Applied Autonomous Sensor Systems, Örebro University, Sweden, 2016

Estimating Human Pose and Activity, University of Essex, Colchester, UK, 2016

Capturing Interacting Characters and Hands, Chalmers University of Technology, Gothenburg, Sweden, 2016

Modeling Humans, Objects and their Relations, Perspectives in Computer Vision and Pattern Recognition, Siegen, Germany, 2015

Estimating Pose and Activity, IEEE Workshop on Interaction of Automated Vehicles with other Traffic Participants, Las Palmas, Gran Canaria, Spain, 2015

Capturing Interacting Hands and Objects, IEEE Workshop on Observing and Understanding Hands in Action, Boston, Massachusetts, USA, 2015

A Semantic Occlusion Model for Human Pose Estimation from a Single Depth Image, ChaLearn Looking at People Workshop, Boston, Massachusetts, USA, 2015

Capturing Hands in Action, Computer Vision Laboratory, ETH Zurich, Switzerland, 2015

Human Pose: A Cue for Activities and Objects, Holistic Scene Understanding, IBFI Schloss Dagstuhl, Germany, 2015

Human Pose: A Cue for Activities and Objects, Digital Image Computing: Techniques and Applications (DICTA), Wollongong, Australia, 2014

Classification and Regression Forests - Theory and Applications, ZESS, Siegen, Germany, 2014

Random Forests and their Applications in Computer Vision, German Conference on Pattern Recognition (GCPR), Münster, Germany, 2014

Activities, Objects, and Poses, Computer Vision Laboratory, ETH Zurich, Switzerland, 2014

Action Recognition, Tutorial Towards Solving Real-World Vision Problems with RGB-D Cameras, Columbus, Ohio, USA, 2014

Face Analysis, Tutorial Towards Solving Real-World Vision Problems with RGB-D Cameras, Columbus, Ohio, USA, 2014

Vom Mensch zum Avatar, Bonner Wissenschaftsnacht, Bonn, Germany, 2014

Wie Computer lernen, Bilder zu verstehen, Dies Academicus, Bonn, Germany, 2014

Auf Menschen fokussiertes visuelles Erkennen und Verstehen von Szenen, GIBU 2014: GI-Beirat der Universitätsprofessoren, IBFI Schloss Dagstuhl, Germany, 2014

From Pose to Affordance, International Time of Flight Workshop, Ein-Gedi, Israel, 2014

Is Human Pose an Important Cue for Scene Understanding?, Institute for Computer Graphics and Vision, TU Graz, Austria, 2014

Classification and Regression Forests - Applications, Summer School on Explorative Analysis and Visualization of Large Information Spaces, Gaschurn, Austria, 2013

Classification and Regression Forests - Theory, Summer School on Explorative Analysis and Visualization of Large Information Spaces, Gaschurn, Austria, 2013

Random Forests and their Applications in Computer Vision, Bonn Vision Workshop, Bonn, Germany, 2013

Towards Scene Understanding, Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS, Sankt Augustin, Germany, 2013

Action Recognition, Tutorial Towards Solving Real-World Vision Problems with RGB-D Cameras, Portland, Oregon, USA, 2013

Face Analysis, Tutorial Towards Solving Real-World Vision Problems with RGB-D Cameras, Portland, Oregon, USA, 2013

Hands and Humans in Action, University of Washington, Seattle, WA, USA, 2013

Pose Estimation of Hands and Faces, Institute for Neuro- and Bioinformatics, Lübeck, Germany, 2013

Random Forests for Face Analysis and Body Pose Estimation, Workshop Kinect untangled: from basics to applications, Valencia, Spain, 2013

Hands and Humans in Action, Universitat Politècnica de Catalunya, Barcelona, Spain, 2012

Will Depth Cameras Have a Long-term Impact on Computer Vision Research?, Time-of-Flight Imaging: Algorithms, Sensors and Applications, IBFI Schloss Dagstuhl, Germany, 2012

Hough Forests and their Applications in Computer Vision, University of Bonn, Germany, 2012

Hough Forests for Object Detection, Tracking, and Action Recognition, Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark, 2011

Real-time Sign Language Letter and Word Recognition from Depth Data, IEEE Workshop on Human Computer Interaction: Real-Time Vision Aspects of Natural User Interfaces (HCI'11), Barcelona, Spain, 2011

Capturing and Modeling Human Interactions, Max Planck Institute for Intelligent Systems, Tübingen, Germany, 2011

Capturing and Modeling Human Interactions, Computer Graphics Group, University of Bonn, Germany, 2011

Objects are More Than Bounding Boxes, Outdoor and Large-Scale Real-World Scene Analysis. 15th Workshop "Theoretical Foundations of Computer Vision", IBFI Schloss Dagstuhl, Germany, 2011

Markerless Motion Capture of Interacting Characters Using Multi-view Image Segmentation (PPTX), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'11), Colorado Springs, CO, USA, 2011

Hough Forests for Object Detection, Tracking, and Action Recognition, Max Planck Symposium on Intelligent Systems, Tübingen, Germany, 2011

Hough Forests for Object Detection, Tracking, and Action Recognition, MMCI, University of Saarland, Saarbrücken, Germany, 2011

Vision-based Human Motion Capture: State-of-the-art and Applications, Computer Vision Winter Workshop, Mitterberg, Austria, 2011

Marker-less Human Motion Capture for In-house Monitoring and Computer Games, Toshiba Cambridge Research Laboratory, Cambridge, UK, 2010

On-line Adaption of Class-specific Codebooks for Instance Tracking, British Machine Vision Conference (BMVC'10), Aberystwyth, UK, 2010

From 2D Object Detection to 3D Pose Estimation, Computer Vision Group, University of California, Berkeley, CA, USA, 2010

Evaluation of Face Motion in Video Sequences (PPT/ZIP, PDF), HERMES Final Review Meeting (PDF, Video), Barcelona, Spain, 2009

Class-Specific Hough Forests for Object Detection (PPT, PDF), IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09), Miami, FL, USA, 2009

Filtering and Optimization Strategies for Marker-less Human Motion Capture with Skeleton-based Shape Models, CVG, ETH Zurich, Switzerland, 2009

Filtering and Optimization Strategies for Marker-less Human Motion Capture with Skeleton-based Shape Models, PERCEPTION, INRIA Grenoble Rhone-Alpes, France, 2009

Filtering and Optimization Strategies for Marker-less Human Motion Capture with Skeleton-based Shape Models, Computer Vision Group, University of Bonn, Germany, 2008

Filtering and Optimization Strategies for Marker-less Human Motion Capture with Skeleton-based Shape Models, BIWI, ETH Zurich, Switzerland, 2008

Model-based Motion Capture for Crash Test Video Analysis, 30th Annual Symposium of the German Association for Pattern Recognition (DAGM'08), Munich, Germany, 2008

Clustered Stochastic Optimization for Object Recognition and Pose Estimation, 29th Annual Symposium of the German Association for Pattern Recognition (DAGM'07), Heidelberg, Germany, 2007

Rendering for Tracking - A Perspective from Computer Vision, Visual Computing - Convergence of Computer Graphics and Computer Vision, IBFI Schloss Dagstuhl, Germany, 2007

Pose Estimation with 3D Textured Models, IEEE Pacific-Rim Symposium on Image and Video Technology (PSIVT'06), Hsinchu, Taiwan, 2006

Learning for Multi-View 3D Tracking in the Context of Particle Filters, Second International Symposium on Visual Computing (ISVC'06), Lake Tahoe, NV, USA, 2006

Generalised Annealed Particle Filter - Impact on Tracking Articulated Objects, SensoMotoric Instruments, Teltow / Berlin, Germany, 2006

Learning a Dynamic Independent Pose Distribution within a Bayesian Framework, Human Motion - Understanding, Modeling, Capture and Animation. 13th Workshop "Theoretical Foundations of Computer Vision", IBFI Schloss Dagstuhl, Germany, 2006

Awards

German Pattern Recognition Award, Münster, 2014

Nomination for ITG Innovation Award, Zurich, 2012

DAGM Main Prize, Heidelberg, 2007

SMI-DAGM Graduation Award, Berlin, 2006

Senior Foulkes Prize, University of Wales Swansea, 2004

Media Coverage

Rhein-Neckar-Zeitung, 3 May 2016

Rhein-Neckar-Zeitung, 29 February 2016

Einstein, SF1, Swiss TV channel, 3 March 2011

NewScientist, 24 October 2010

Planetopia, SAT.1, German TV channel, 24 June 2007

Education/Experience

June 2013 - present:
Professor at the University of Bonn, Germany

April 2012 - May 2013
Senior Research Scientist at the Perceiving Systems Department, Max Planck Institute for Intelligent Systems, Germany

March 2009 - March 2012:
Postdoc at the Computer Vision Laboratory, ETH Zurich, Switzerland

November 2008 - February 2009:
Ph. D. student in Computer Science at the Universität des Saarlandes, Saarbrücken, Germany and the Max-Planck-Institut für Informatik
Title of Ph. D. Thesis: Filtering and Optimization Strategies for Marker-less Human Motion Capture with Skeleton-based Shape Models (supervisors: Prof. Dr. B. Rosenhahn, Prof. Dr. H.-P. Seidel)

August 2008 - October 2008:
Intern at the Machine Learning and Perception Group, Microsoft Research Cambridge, UK

January 2006 - July 2008:
Ph. D. student in Computer Science at the Universität des Saarlandes, Saarbrücken, Germany and the Max-Planck-Institut für Informatik

October 2004 - December 2005:
Studies in Mathematics at the University of Mannheim
Title of Master's Thesis (Diplomarbeit): Generalised Annealed Particle Filter - Mathematical Framework, Algorithms and Applications (supervisors: Prof. Dr. J. Potthoff, Prof. Dr. C. Schnörr) (PDF, PS)

September 2003 - July 2004:
Studies in Mathematics at the University of Wales Swansea, UK
Bachelor of Science in Mathematics with First Class Honours

October 2000 - August 2003:
Studies in Mathematics at the University of Mannheim

June 1999:
Abitur at the Gymnasium, Christian-von-Bomhard Schule Uffenheim, Germany

Researchers/Students/Visitors

Postdocs:
Hildegard Kühne (Bonn)

Ph. D. students:
Alexander Richard (Bonn)
Umar Iqbal (Bonn)
Pau Panareda-Busto (EADS)
Martin Garbade (Bonn)
Abhilash Srikantha (MPI-IS/Bonn)
Dimitrios Tzionas (MPI-IS/Bonn)

Alumni:
Marko Ristin (graduated 2015)
Matthias Dantone (graduated 2014)
Nima Razavi (graduated 2012)
Uwe Hiemer (intern 2012)
Angela Yao (graduated 2012)
Gabriele Fanelli (graduated 2012)
Adolfo López Méndez (visitor 2012)
Henning Hamer (graduated 2011)