Preprints

  1. CPU- and GPU-based Distributed Sampling in Dirichlet Process Mixtures for Large-scale Analysis. arXiv, 2022.
    Or Dinari*, Raz Zamir*, John Fisher III, and Oren Freifeld.
    ("*" indicates both these authors contributed equally)
    [ PDF ] [ Code: Python; Julia; CUDA/C++]

Peer-Reviewed Publications

  1. SpaceJAM: a Lightweight and Regularization-free Method for Fast Joint Alignment of Images. ECCV 2024
    Nir Barel*, Ron Shapira Weber*, Nir Mualem, Shahaf Finder, and Oren Freifeld

  2. Wavelet Convolutions for Large Receptive Fields, ECCV 2024
    Shahaf Finder, Roy Amoyal, Eran Treister, and Oren Freifeld

  3. Trainable Highly-expressive Activation Functions, ECCV 2024
    Irit Chelly*, Shahaf Finder*, Shira Ifergane, and Oren Freifeld

  4. From ViT Features to Training-free Video Object Segmentation via Streaming-data Mixture Models, NeurIPS 2023.
    Roy Uziel, Or Dinari, and Oren Freifeld
    [ PDF ] [ Supplemental Material ] [ Code ]

  5. Regularization-free Diffeomorphic Temporal Alignment Nets, ICML 2023.
    Ron Shapira-Weber and Oren Freifeld
    [ PDF (paper + Supplemental Material) ] [ Code ]

  6. A Deep Moving-camera Background Model, ECCV 2022.
    Guy Erez, Ron Shapira-Weber, and Oren Freifeld
    [ PDF ] [ Supplemental Material ] [ Code ]

  7. Revisiting DP-Means: Fast Scalable Algorithms via Parallelism and Delayed Cluster Creation. UAI 2022.
    Or Dinari and Oren Freifeld.
    [ PDF ] [ Code ].

  8. Variational- and Metric-based Deep Latent Space for Out-of-Distribution Detection. UAI 2022.
    Or Dinari and Oren Freifeld.
    [ PDF ] [ Code ].

  9. DeepDPM: Deep Clustering With an Unknown Number of Clusters. CVPR 2022.
    Meitar Ronen, Shahaf Finder, and Oren Freifeld.
    [ PDF (Paper +Supplemental Material) ] [ Code ]

  10. Sampling in Dirichlet Process Mixture Models for Clustering Streaming Data. AISTATS 2022.
    Or Dinari and Oren Freifeld.
    [ PDF (Paper +Supplemental Material) ] [ Code (Julia) ] [ [Code (Python) ] [ DataSets] [ Example Notebook (Julia) ] [ Example Notebook (Python): Coming Soon ]

  11. Common Failure Modes of Subcluster-based Sampling in Dirichlet Process Gaussian Mixture Models and a Deep-learning Solution. AISTATS 2022.
    Vlad Winter*, Or Dinari* and Oren Freifeld.
    ("*" indicates both these authors contributed equally)
    [ PDF (Paper +Supplemental Material) ] [ Code ]

  12. Effective Learning of a GMRF Mixture Model. Accepted to IEEE Access, 2022.
    Shahaf Finder, Eran Treister, and Oren Freifeld.
    [ PDF ] [ Code ]

  13. Cyclic Diffeomorphic Transformer Nets for Contour Alignment. ICIP 2021.
    Ilya Kaufman, Ron Shapira Weber, and Oren Freifeld.
    [ PDF ] [ Code ]

  14. Scalable and Flexible Clustering of Grouped Data via Parallel and Distributed Sampling in Versatile Hierarchical Dirichlet Processes. UAI 2020.
    Or Dinari and Oren Freifeld.
    [ PDF ] [ Supplemental Material ] [ Code (Julia) ] [ Code (Python) ]

  15. JA-POLS: a Moving-camera Background Model via Joint Alignment and Partially-overlapping Local Subspaces. CVPR 2020.
    Irit Chelly, Vlad Winter, Dor Litvak, David Rosen, and Oren Freifeld.
    [ PDF ] [ Supplemental Material ] [ Videos (example results) ] [ Code ]

  16. Diffeomorphic Temporal Alignment Nets. NeurIPS 2019.
    Ron Shapira Weber, Matan Eyal, Nicki Skafte Detlefsen, Oren Shriki, and Oren Freifeld.
    [ PDF ] [ Supplemental Material ] [ Code ]

  17. Bayesian Adaptive Superpixel Segmentation. ICCV 2019.
    Roy Uziel, Meitar Ronen, and Oren Freifeld
    [ PDF ] [ Supplemental Material ] [ Code ]

  18. Distributed MCMC Inference in Dirichlet Process Mixture Models Using Julia. HPML Workshop, 2019. Best Paper Award.
    Dinari, O.*, Yu, A.*, Freifeld, O., and Fisher III J.
    ("*" indicates both these authors contributed equally)
    [ PDF ] [ Code (Julia) ] [ Code (Python) ]

  19. Deep Diffeomorphic Transformer Networks. CVPR 2018.
    Skafte Detlefsen, N., Freifeld, O., and Hauberg, S.
    [ PDF ] [ Supplemental Material ] [ Nicki Skafte Deftelsen's derivation of the matrix exponentials: PDF; Maple ] [ Code ]

  20. The Manhattan Frame Model -- Manhattan World Inference in the Space of Surface Normals. IEEE-TPAMI 2018.
    Straub, J., Freifeld, O., Rosman, G., Leonard, J., and Fisher III J.
    [ PDF ]

  21. Transformations Based on Continuous Piecewise-Affine Velocity Fields. IEEE-TPAMI 2017.
    Freifeld, O., Hauberg, S., Batmanghelich, K. and Fisher III, J.
    [ PDF ] [ Supplemental Material ] [ Technical Report: Deriving the CPAB Derivative (also includes fixing a small mistake in Eq 24 from the PAMI paper) ]

  22. Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation. AISTATS 2016. Accepted as Oral
    Hauberg, S., Freifeld, O., Larsen, A.B.L., Fisher III, J., and Hansen, L.K.
    [ PDF ] [ Video ] [ Datasets (AlignMNIST and AlignMNIST500) ]

  23. Highly-Expressive Spaces of Well-Behaved Transformations: Keeping It Simple. ICCV 2015.
    Freifeld, O., Hauberg, S., Batmanghelich, K. and Fisher III, J.
    [ PDF ] [ BibTex ] [ Project Webpage ] [ Supplemental Material ] [ Poster ] [ Code 1: uses GPU; requires an NVIDIA card; written in Python+CUDA ] [ Code 2: CPU-only; partial implementation; written in Julia ] [ Video 1: Conditional warp ] [ Video 2: spotlight ]

  24. A Fast Method for Inferring High-Quality Simply-Connected Superpixels. ICIP 2015. Accepted as Oral. Recognized as one of the "Top 10% ICIP 2015 papers".
    Freifeld, O., Li, Y. and Fisher III, J.
    [ PDF ] [ BibTex ] [ Slides ] [ Project Webpage ] [ Code: CUDA + Python/C++/Matlab wrappers ] [ Remarks about the initialization+benchmarks ]
    For additional examples in higher resolution than those in the paper: [ original (~38MB) ] [ slightly compressed (~5MB) ]

  25. A Dirichlet Process Mixture Model for Spherical Data. AISTATS 2015. Accepted as Oral.
    Straub, J., Chang, J., Freifeld, O., and Fisher III, J.
    [ PDF ] [ BibTex ] [ Supplemental Material ] [ Code ]

  26. A Mixture of Manhattan Frames: Beyond the Manhattan World. CVPR 2014. Accepted as Oral.
    Straub, J., Rosman, G., Freifeld, O., Leonard, J. and Fisher III, J.
    [ PDF ] [ BibTex [ Project Webpage ] [ Supplemental Material ] [ Video ] [ Code ]
    After the exposure it received in MIT News, this project was also covered by many technology/robotics websites

  27. Aerial Reconstructions via Probabilistic Data Fusion. CVPR 2014
    Cabezas R., Freifeld, O., Rosman G. and Fisher III, J.
    [ PDF ] [ BibTex ] [ Project Webpage ] [ Supplemental Material ] [ Video ] [ Code ] [ A 3D result reviewer ]

  28. Model Transport: Towards Scalable Transfer Learning on Manifolds. CVPR 2014
    Freifeld, O., Hauberg, S. and Black, M.J.
    [ PDF ] [ BibTex ] [ Supplemental Material ] [ Video ] [ Remark about the data ]

  29. A freely-moving monkey treadmill model. Journal of Neural Engineering, 2014.
    Foster, J.D., Nuyujukian, P., Freifeld, O., Gao, Walker, Ryu, S., Meng, T., Murmann, Black, M.J., Shenoy, K.V.
    [ PDF (coming up soon) ] [ Project webpage at MPI-IS-PS ] [ Shenoy's group at Stanford EE ]

  30. A Geometric take on Metric Learning. NIPS 2012
    Hauberg, S., Freifeld, O. and Black, M.J.
    [ PDF ] [ BibTex ] [ Project Webpage ] [ Supplemental Material ] [ Video ] [ Code ]

  31. Lie Bodies: A Manifold Representation of 3D Human Shape. ECCV 2012.
    Freifeld, O. and Black, M.J.
    [ PDF ] [ BibTex ] [ Project Webpage ] [ Supplemental Material ] [ Poster ] [ Video 1] [ Video 2 (~40 MB) ] [ Code ] [ Remark about the data ]

  32. From pictorial structures to deformable structures. CVPR 2012.
    Zuffi, S., Freifeld O. and Black M.J.
    [ PDF ] [ BibTex ] [ Project Webpage ] [ Code ]

  33. A framework for relating neural activity to freely moving behavior. IEEE-EMBC 2012. Accepted as Oral.
    Foster, J.D., Nuyujukian, P., Freifeld, O., Ryu, S., Black, M.J. and Shenoy, K.V.
    [ BibTex ]

  34. Combining wireless neural recording and video capture for the analysis of natural gait. IEEE-NER 2011. Accepted as Oral.
    Foster, J., Freifeld, O., Nuyujukian, P., Ryu, S., Black, M.J. and Shenoy, K.V.
    [ PDF ] [ BibTex ]

  35. A 2D human body model dressed in eigen clothing. ECCV 2010.
    Guan, P., Freifeld, O. and Black, M.J.
    [ PDF ] [ BibTex ] [ Data ]

  36. Contour people: A parameterized model of 2D articulated human shape. CVPR 2010. Accepted as Oral.
    Freifeld O., Weiss, A., Zuffi, S. and Black, M.J.
    [ PDF ] [ BibTex ] [ Slides ] [ Talk's Video ]

  37. Multiple Sclerosis lesion detection using constrained GMM and curve evolution. International Journal of Biomedical Imaging, 2009.
    Freifeld, O., Greenspan, H. and Goldberger, J.
    [ PDF ]

  38. Lesion detection in noisy MR brain images using constrained GMM and active contours. IEEE-ISBI 2007. Accepted as Oral.
    Freifeld, O., Greenspan, H. and Goldberger, J.
    [ PDF ] [ Slides ]

Theses

  1. Statistics on Manifolds with Applications to Modeling Shape Deformations. PhD Thesis, Brown University, August 2013.
    Freifeld, O.
    [     PDF ] [ BibTex ] [ Eratta ]

  2. MR Brain Image Analysis: Healthy Tissue Segmentation and Multiple Sclerosis Lesion Detection Using Constrained GMM and Curve Evolution. MSc Thesis, Tel-Aviv University, July 2007.
    Freifeld, O.