Suhas Lohit

Suhas Lohit

Principal Research Scientist at MERL working on deep learning and computer vision

Publications

Updated list, citations and bibtex can be found on my Google Scholar page

  1. Suhas Lohit, Rajhans Singh, Kuldeep Kulkarni and Pavan Turaga, “Rank-Regularized Measurement Operators for Compressive Imaging”, Asilomar 2019

  2. Suhas Lohit, Qiao Wang and Pavan Turaga, “Temporal transformer networks: Joint learning of invariant and discriminative time warping”, CVPR 2019, PDF, Code, Poster

  3. Suhas Lohit, Dehong Liu, Hassan Mansour, Petros Boufounos, “Unrolled projected gradient descent for multispectral image fusion”, ICASSP 2019, PDF, Poster

  4. Suhas Lohit, Kuldeep Kulkarni, Ronan Kerviche, Pavan Turaga and Amit Ashok, “Convolutional neural networks for non-iterative reconstruction of compressively sensed images”, IEEE Transactions on Computational Imaging, 2018, PDF, Code

  5. Li-Chi Huang, Kuldeep Kulkarni, Anik Jha, Suhas Lohit, Suren Jayasuriya and Pavan Turaga, “CS-VQA: Visual question answering with compressively sensed images”, ICIP 2018, PDF, Poster

  6. Suhas Lohit, Ankan Bansal, Nitesh Shroff, Jaishanker Pillai, Pavan Turaga and Rama Chellappa, “Predicting dynamical evolution of human activities from a single image”, CVPRW 2018, PDF, Poster, Slides

  7. Suhas Lohit and Pavan Turaga, “Learning Invariant Riemannian Geometric Representations Using Deep Nets”, ICCVW: From Euclid to Riemann, 2018, PDF, Poster, Slides

  8. Suhas Lohit, Kuldeep Kulkarni and Pavan Turaga, “Direct Inference on Compressive Measurements using Convolutional Neural Networks”, ICIP 2016, PDF, Poster

  9. Kuldeep Kulkarni, Suhas Lohit, Pavan Turaga, Ronan Kerviche and Amit Ashok, “ReconNet: Non-iterative Reconstruction of Images from Compressively Sensed Measurements”, CVPR 2016, PDF, Code, Poster

  10. Suhas Lohit, Kuldeep Kulkarni, Pavan Turaga, Jian Wang and Aswin Sankaranarayanan, “Reconstruction-free Inference on Compressive Measurements”, CVPRW 2015, Best Paper Award, PDF, Slides

  11. Qiao Wang, Suhas Lohit, Meynard Toledo, Matthew Buman and Pavan Turaga, “A statistical estimation framework for energy expenditure of physical activities from a wrist-worn accelerometer”, EMBC 2016, PDF

Preprints and working papers

  1. Suhas Lohit, Rajhans Singh, Kuldeep Kulkarni and Pavan Turaga, “Rate-Adaptive Neural Networks for Spatial Multiplexers”, arXiv preprint arXiv:1809.02850, PDF

  2. Kaushik Koneripalli, Suhas Lohit, Rushil Anirudh and Pavan Turaga, “Rate-Invariant Autoencoding of Time-Series”, under review in ICASSP 2019, PDF

  3. Suhas Lohit, Rushil Anirudh and Pavan Turaga, “Reconstructing Dynamics of Unobserved Joints in 3D Human Actions Using Deep Generative Priors”, under review, PDF

Theses

  1. PhD Dissertation: Building Constraints, Geometric Invariants and Interpretability in Deep Learning: Applications in computational imaging and vision, PDF

  2. Master’s thesis: Reconstruction-Free Inference From Compressive Measurements, PDF