Sie sind nicht angemeldet Anmelden | Anmelden
max planck institut
informatik
» Home » Departments »

Michael Stark (Post-Doc)


Contact

Phone
-
Fax
-
Office
133 @ Gates Computer Sciences, Stanford University

News

  • Our CVPR'12 detector DPM-VOC+VP is featured as a baseline detector in the paper introducing the new 3D-PASCAL dataset of Yu Xiang et al.
  • The fine-grained car dataset (196 car categories, 16,185 images) accompanying our 3dRR-13 paper is available here. It includes an ultra-fine-grained subset of 10 BMW categories. The fine-grained car dataset from our BMVC'12 paper (14 categories) is still available here.
  • Our work on occlusion-aware object class detection (OC-DPM) won the detection and viewpoint estimation competition for the car object class of the Reconstruction Meets Recognition (RMRC) Challenge held in connection with ICCV'13.
  • I will be co-organizing the 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13), collocated with ICCV'13, together with Min Sun (University of Washington) and Silvio Savarese (Stanford University).
  • I am now Visiting Assistant Professor at Stanford University, as part of the Max Planck Center for Visual Computing and Communication (MPC-VCC). I am working on Visual Object Recognition and Scene Interpretation with Prof. Daphne Koller.

 

Research Interests

  • Object Class Recognition
  • Probabilistic Models
  • Machine Learning

Teaching

 Supervised Theses

  • Marcus Rohrbach. Visual Knowledge Transfer Using Semantic Relatedness Measures
  • Sandra Ebert. Dirichlet Process Mixture Models for Object Category Recognition
  • Philipp Lies. Extracting Affordance Cues from Observed Human-Object Interactions
  • Sebastian Schneider. Discovering Interaction Points on Objects using Human Hand Tracking

Courses

  • Winter Semester 2007/2008: Introduction to Computer Science 1 (Lab exercises)
  • Summer Semester 2007: Advanced Programming Techniques in Computer Vision (Exercises)
  • Winter Semester 2006/2007: Introduction to Computer Science 1 (Lab exercises)

Short-Bio

 Awards and Honors

Projects

  • Cognitive Systems for Cognitive Assistants (CoSy)

Former Affiliations

 My Erdös Number is at most 4 (via Noga Alon, Dan Suciu, Mary Fernandez).

Other Affiliations

Stanford University, DAGS

Research Projects

Publications

2014
Multi-View Priors for Learning Detectors from Sparse Viewpoint Data, B. Pepik, M. Stark, P. Gehler and B. Schiele, International Conference on Learning Representations (ICLR) 2014, 04/2014, Banff, AB, Canada, (2014)  PDF 
Are Cars Just 3D Boxes? - Jointly Estimating the 3D Shape of Multiple Objects, M Z. Zia, M. Stark and K. Schindler, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA, (2014)  PDF 
2013
3D Object Representations for Fine-Grained Categorization, J. Krause, M. Stark, J. Deng and L. Fei-Fei, 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13, ICCV workshop), November, (2013)  PDF 
Collecting a Large-Scale Dataset of Fine-Grained Cars, J. Krause, J. Deng, M. Stark and F - F. Li, extended abstract - 2nd Workshop on Fine-Grained Visual Categorization (FGVC2, CVPR workshop), June, (2013)  PDF 
Modeling Instance Appearance for Recognition - Can We Do Better Than EM?, A. Chou, H. Wang, M. Stark and D. Koller, Structured Prediction Tractability, Learning, and Inference (SPTLI, CVPR workshop), June, (2013)  PDF 
Occlusion Patterns for Object Class Detection, B. Pepik, M. Stark, P. Gehler and B. Schiele, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June, (2013)  PDF 
Towards Scene Understanding with Detailed 3D Object Representations, Z. Zia, M. Stark and K. Schindler, extended abstract - Scene Understanding Workshop (SUNw, CVPR workshop), June, (2013)
Detailed 3D Representations for Object Recognition and Modeling, Z. Zia, M. Stark, B. Schiele and K. Schindler, IEEE Transactions on Patterm Analysis and Machine Intelligence (PAMI), Volume 35, Number 11, p.2608 - 2623, (2013)
Explicit Occlusion Modeling for 3D Object Class Representations, Z. Zia, M. Stark and K. Schindler, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, USA, (2013)
2012
Combining Language Sources and Robust Semantic Relatedness for Attribute-Based Knowledge Transfer, M. Rohrbach, M. Stark, G. Szarvas and B. Schiele, Trends and Topics in Computer Vision, September, Volume 6553, p.15-28, (2012) Abstract  PDF 
Fine-Grained Categorization for 3D Scene Understanding, M. Stark, J. Krause, B. Pepik, D. Meger, J J. Little, B. Schiele and D. Koller, British Machine Vision Conference (BMVC), September, (2012)  PDF 
3D^2PM - 3D Deformable Part Models, B. Pepik, P. Gehler, M. Stark and B. Schiele, European Conference on Computer Vision (ECCV), October, (2012)  PDF 
What Makes a Good Detector? -- Structured Priors for Learning From Few Examples, T. Gao, M. Stark and D. Koller, European Conference on Computer Vision (ECCV), October, (2012)  PDF 
Teaching 3D Geometry to Deformable Part Models, B. Pepik, M. Stark, P. Gehler and B. Schiele, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June, (2012)  PDF 
2011
Revisiting 3D Geometric Models for Accurate Object Shape and Pose, Z. Zia, M. Stark, K. Schindler and B. Schiele, 3rd International IEEE Workshop on 3D Representation and Recognition (3dRR, ICCV Workshop), November, (2011) 3dRR Best Paper Award Abstract  PDF 
Evaluating Knowledge Transfer and Zero-Shot Learning in a Large-Scale Setting, M. Rohrbach, M. Stark and B. Schiele, IEEE Conference on Computer Vision and Pattern Recognition, June, (2011) Abstract  PDF 
2010
Back to the Future: Learning Shape Models from 3D CAD Data, M. Stark, M. Goesele and B. Schiele, British Machine Vision Conference (BMVC), September, (2010)  PDF 
On Knowledge Transfer in Object Class Recognition, M. Stark, Fachbereich Informatik, September, Ph.D. Thesis, Darmstadt, p.174, (2010)
Combining Language Sources and Robust Semantic Relatedness for Attribute-Based Knowledge Transfer, M. Rohrbach, M. Stark, G. Szarvas and B. Schiele, Trends and Topics in Computer Vision: ECCV 2010 Workshops, October, Volume LNCS.6553, p.15-28, (2010) Abstract
What Helps Where – And Why? Semantic Relatedness for Knowledge Transfer, M. Rohrbach, M. Stark, G. Szarvas, I. Gurevych and B. Schiele, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June, (2010) Abstract  PDF 
Categorical Perception, M. Fritz, M. Andriluka, S. Fidler, M. Stark, A. Leonardis and B. Schiele, Cognitive Systems, Volume 8, (2010)
Multi-Modal Learning, D. Skocaj, M. Kristan, A. Vrecko, A. Leonardis, M. Fritz, M. Stark, B. Schiele, S. Hongeng and J L. Wyatt, Cognitive Systems, Volume 8, (2010)
2009
A Shape-Based Object Class Model for Knowledge Transfer, M. Stark, M. Goesele and B. Schiele, IEEE International Conference on Computer Vision (ICCV), September, (2009) Best Paper Award Honorable Mention by IGD Abstract  PDF 
Shading Cues for Object Class Detection, M. Stark, M. Goesele and B. Schiele, 2nd International IEEE Workshop on 3D Representation for Recognition (3dRR, ICCV Workshop), October, (2009) 3dRR Best Paper Award and Best Paper Award Honoroble Mention by IGD. Abstract  PDF 
2008
Functional Object Class Detection Based on Learned Affordance Cues, M. Stark, P. Lies, M. Zillich, J L. Wyatt and B. Schiele, International Conference on Computer Vision Systems (ICVS), May, (2008) Abstract  PDF 
2007
How Good are Local Features for Classes of Geometric Objects, M. Stark and B. Schiele, IEEE International Conference on Computer Vision (ICCV), October, (2007) Abstract  PDF 
XQuery Streaming a la Carte, M. Fernandez, P. Michiels, J. Simeon and M. Stark, IEEE International Conference on Data Engineering (ICDE), April, (2007) Oral presentation Abstract  PDF 

Copyright Notice

All materials are presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors and other holders (publishers). These works may not be reposted without the explicit permission of the copyright holder.
alte website