Publications


Cross-Domain Matching with Squared-Loss Mutual Information

M. Yamada, L. Sigal, M. Raptis, M. Toyoda, Y. Chang, M. Sugiyama. In IEEE Transactions on Pattern Analysis and Machine Leanring (PAMI), 2015.

Nonparametric Clustering with Distance Dependent Hierarchies

S. Soumya, M. Raptis, L. Sigal and E. B. Sudderth. In Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), 2014.
(PDF)

Action is in the Eye of the Beholder: Eye-gaze Driven Model for Spatio-Temporal Action Localization

N. Shapovalova, M. Raptis, L. Sigal and G. Mori. In Proceedings of Advances in Neural Information Processing Systems (NIPS), 2013.
(PDF, Video)

From Subcategories to Visual Composites: A Multi-Level Framework for Object Recognition

T. Lan, M. Raptis, L. Sigal and G. Mori. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (ICCV), 2013.
(PDF)

Covariate Shift Adaptation for Discriminative 3D Pose Estimation

M. Yamada, L. Sigal and M. Raptis. In IEEE Transactions on Pattern Analysis and Machine Leanring (PAMI), 2013. (PDF)

Poselet Key-framing: A Model for Human Activity Recognition

M. Raptis and L. Sigal. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
(PDF, Video, BibTeX)

No Bias Left Behind: Covariate Shift Adaptation for Discriminative 3D Pose Estimation.

M. Yamada, L. Sigal, and M. Raptis. In Proceedings of European Conference of Computer Vision (ECCV), 2012.
(PDF, supplementary material)

SuperFloxels: A Mid-Level Representation for Video Sequences.

A. Ravichandran, C. Wang, M. Raptis and S. Soatto. In ARTEMIS Workshop , ECCV, 2012 (Oral).
(PDF)

Discovering Discriminative Action Parts from Mid-Level Video Representations

M. Raptis, I. Kokkinos and S. Soatto. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012.
(PDF, Project page: Annotations & Code, Poster)

Sparse Occlusion Detection with Optical Flow

A. Ayvaci, M. Raptis, and S. Soatto. In International Journal of Computer Vision (IJCV), 2011.
(PDF, Code)

Real-Time Classification of Dance Gestures from Skeleton Animation

M. Raptis, D. Kirovski, and H. Hoppes. In Proceedings of Symposium on Computer Animation (SCA), 2011.
(PDF, Project page) (Honorable Mention)

Occlusion Detection and Motion Estimation with Convex Optimization

A. Ayvaci, M. Raptis, and S. Soatto. In Proceedings of Advances in Neural Information Processing Systems (NIPS), 2010.
(PDF, Code)

Tracklet Descriptors for Action Modeling and Video Analysis

M. Raptis, and S. Soatto. In Proceedings of the European Conference on Computer Vision (ECCV), 2010.
(PDF, Poster, Code)

Spike Train Driven Dynamical Models for Human Motion

M. Raptis, K. Wnuk and S. Soatto. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
(PDF, Poster, Code)

Flexible Dictionaries for Action Classification.

M. Raptis, K. Wnuk and S. Soatto. In Proceedings of the International Workshop on Machine Learning for Vision-based Motion Analysis (MLVMA08) (oral). In conjunction with ECCV 2008.
(PDF, Poster)

Time Warping Under Dynamic Constraints.

M. Raptis, M. Bustreo, and S. Soatto. In Proceedings of the Workshop on Dynamical Vision in conjunction with ICCV 2007.
(PDF)

Understanding the Spatio-Temporal Structure of Human Actions

M. Raptis. Ph.D. thesis, UCLA, August 2011.
(PDF)