We plan to provide links to code from various projects completed in our group . Please note disclaimer at the bottom of the page.
- Angular Margin Contrastive Loss
Hongjun Choi, Anirudh Som, Pavan Turaga, “AMC-Loss:Angular Margin Contrastive Loss for Improved Explainability in Image Classification”, 5th International Workshop in Differential Geometry in Computer Vision and Machine Learning (DiffCVML) 2020.
- Companion No. 2
Developed by Xavier Nokes, Companion No. 2 is a project developed to create a custom hardware solution for streaming real-time, low-latency sensor data over OSC. This project has full instructions on usage and a how-to guide for building the circuit. Additional iterations of the circuit, along with software plug-and-play style samples will be included over time. Used by Pavan Turaga in AME 520 Understanding Activity for remote experiments on modeling human movement.
- Topological descriptors for time-series for applications in Parkinson’s disease gait and balance analysis
Afra Nawar, Farhan Rahman, Narayanan Krishnamurthi, Anirudh Som, Pavan Turaga, “Topological Descriptors for Parkinson’s Disease Classification and Regression Analysis”, 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society (EMBC) 2020.
- Temporal Transformer Networks
Suhas Lohit, Qiao Wang, Pavan K. Turaga, “Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019: 12426-12435.
- Improved ReconNet
Implementation in Tensorflow, allows for learning the measurement matrix along with ReconNet, and uses adversarial loss in addition to Euclidean loss. See original ReconNet codebase in the list below.
Suhas Lohit, Kuldeep Kulkarni, Ronan Kerviche, Pavan K. Turaga, Amit Ashok, “Convolutional Neural Networks for Noniterative Reconstruction of Compressively Sensed Images”, IEEE Transactions on Computational Imaging 4(3): 326-340 (2018).
- Perturbed Topological Signatures of Persistence Diagrams
Anirudh Som, Kowshik Thopalli, Karthikeyan N. Ramamurthy, Vinay Venkataraman, Ankita Shukla, Pavan Turaga, “Perturbation Robust Representations of Topological Persistence Diagrams”, in the European Conference on Computer Vision (ECCV) 2018.
- Elastic functional-codes for Riemannian Trajectories
Rushil Anirudh, Pavan Turaga, Jingyong Su, & Anuj Srivastava, “Elastic functional coding of Riemannian trajectories”, in IEEE PAMI 2017.
- Deep-net based compressive light-field Recovery
(Pls contact us if you need the coded mask simulation)
Mayank Gupta, Arjun Jauhari, Kuldeep Kulkarni, Suren Jayasuriya, Alyosha Molnar, Pavan Turaga, “Compressive Light Field Reconstructions using Deep Learning”, Computational Cameras and Displays Workshop (in conjunction with CVPR), 2017.
- ReconNet: CNNs for Compressive Image Recovery
Kuldeep Kulkarni, Suhas Lohit, Pavan Turaga, Ronan Kerviche, Amit Ashok , “ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements”, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
- Riemannian analysis of Topological Persistence Diagrams
Rushil Anirudh, Vinay Venkataraman, Karthikeyan Natesan Ramamurthy, Pavan K. Turaga, “A Riemannian Framework for Statistical Analysis of Topological Persistence Diagrams”, 2nd International Workshop on Differential Geometry in Computer Vision and Machine Learning (Diff-CVML) 2016, in conjunction with CVPR 2016.
- Statistics on Stiefel and Grassmann Manifolds
P. Turaga, A. Veeraraghavan, A. Srivastava, R. Chellappa,”Statistical Computations on Grassmann and Stiefel Manifolds for Image and Video-Based Recognition”, IEEE PAMI Nov 2011.
Permission to use, copy, or modify these software and their documentation for educational and research purposes only and without fee is hereby granted, provided this copyright notice appears on all copies and supporting documentation.
The programs are provided on an ‘as is’ basis without any express or implied warranty of any kind including warranties of merchantability, noninfringement of intellectual property, or fitness for any particular purpose. In no event shall the authors be liable for any damages whatsoever (including, without limitation, damages for loss of profits, business interruption, loss of information) arising out of the use of or inability to use these programs, even if the author has been advised of the possibility of such damages.
The authors may make changes to these materials at any time without notice. The authors make no commitment to update the materials. Each program is provided ‘as is’, without any express or implied warranty, without even the warranty of fitness for a particular purpose.