papers

Publications (66)

cs.LG2026

MiGHT-EHR: A Multi-task Graph Transformer for Heterogeneous Temporal Electronic Health Records

Anirudh Rayas, Yuan Wang, Pavan Turaga

Learning from Electronic Health Records (EHRs) has gained significant attention due to its potential to improve clinical prediction. However, effective learning remains challenging…

cs.CV2014

Interactively Test Driving an Object Detector: Estimating Performance on Unlabeled Data

Rushil Anirudh, Pavan Turaga

In this paper, we study the problem of `test-driving' a detector, i.e. allowing a human user to get a quick sense of how well the detector generalizes to their specific requirement…

cs.LG2022

Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor Data

Eun Som Jeon, Anirudh Som, Ankita Shukla +3

Deep neural networks are parametrized by several thousands or millions of parameters, and have shown tremendous success in many classification problems. However, the large number o…

cs.CV2025

DecompDreamer: A Composition-Aware Curriculum for Structured 3D Asset Generation

Utkarsh Nath, Rajeev Goel, Rahul Khurana +5

Current text-to-3D methods excel at generating single objects but falter on compositional prompts. We argue this failure is fundamental to their optimization schedules, as simultan…

cs.CV2023

Target-Aware Generative Augmentations for Single-Shot Adaptation

Kowshik Thopalli, Rakshith Subramanyam, Pavan Turaga +1

In this paper, we address the problem of adapting models from a source domain to a target domain, a task that has become increasingly important due to the brittle generalization of…

cs.LG2020

Topological Descriptors for Parkinson's Disease Classification and Regression Analysis

Afra Nawar, Farhan Rahman, Narayanan Krishnamurthi +2

At present, the vast majority of human subjects with neurological disease are still diagnosed through in-person assessments and qualitative analysis of patient data. In this paper,…

cs.CV2023

Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments

Rajhans Singh, Ankita Shukla, Pavan Turaga

Deep networks for image classification often rely more on texture information than object shape. While efforts have been made to make deep-models shape-aware, it is often difficult…

cs.CV2023

Polynomial Implicit Neural Representations For Large Diverse Datasets

Rajhans Singh, Ankita Shukla, Pavan Turaga

Implicit neural representations (INR) have gained significant popularity for signal and image representation for many end-tasks, such as superresolution, 3D modeling, and more. Mos…

cs.CG2016

Persistent Homology of Attractors For Action Recognition

Vinay Venkataraman, Karthikeyan Natesan Ramamurthy, Pavan Turaga

In this paper, we propose a novel framework for dynamical analysis of human actions from 3D motion capture data using topological data analysis. We model human actions using the to…

eess.SP2025

Ground Reaction Force Estimation via Time-aware Knowledge Distillation

Eun Som Jeon, Sinjini Mitra, Jisoo Lee +4

Human gait analysis with wearable sensors has been widely used in various applications, such as daily life healthcare, rehabilitation, physical therapy, and clinical diagnostics an…

cs.CV2025

Guiding Diffusion with Deep Geometric Moments: Balancing Fidelity and Variation

Sangmin Jung, Utkarsh Nath, Yezhou Yang +5

Text-to-image generation models have achieved remarkable capabilities in synthesizing images, but often struggle to provide fine-grained control over the output. Existing guidance…

cs.CV2020

Role of Orthogonality Constraints in Improving Properties of Deep Networks for Image Classification

Hongjun Choi, Anirudh Som, Pavan Turaga

Standard deep learning models that employ the categorical cross-entropy loss are known to perform well at image classification tasks. However, many standard models thus obtained of…

cs.CV2019

Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping

Suhas Lohit, Qiao Wang, Pavan Turaga

Many time-series classification problems involve developing metrics that are invariant to temporal misalignment. In human activity analysis, temporal misalignment arises due to var…

cs.CV2025

Automatic Temporal Segmentation for Post-Stroke Rehabilitation: A Keypoint Detection and Temporal Segmentation Approach for Small Datasets

Jisoo Lee, Tamim Ahmed, Thanassis Rikakis +1

Rehabilitation is essential and critical for post-stroke patients, addressing both physical and cognitive aspects. Stroke predominantly affects older adults, with 75% of cases occu…

cs.CV2020

GraCIAS: Grassmannian of Corrupted Images for Adversarial Security

Ankita Shukla, Pavan Turaga, Saket Anand

Input transformation based defense strategies fall short in defending against strong adversarial attacks. Some successful defenses adopt approaches that either increase the randomn…

cs.CV2018

Perturbation Robust Representations of Topological Persistence Diagrams

Anirudh Som, Kowshik Thopalli, Karthikeyan Natesan Ramamurthy +3

Topological methods for data analysis present opportunities for enforcing certain invariances of broad interest in computer vision, including view-point in activity analysis, artic…

cs.LG2025

AttenGluco: Multimodal Transformer-Based Blood Glucose Forecasting on AI-READI Dataset

Ebrahim Farahmand, Reza Rahimi Azghan, Nooshin Taheri Chatrudi +6

Diabetes is a chronic metabolic disorder characterized by persistently high blood glucose levels (BGLs), leading to severe complications such as cardiovascular disease, neuropathy,…

cs.CV2020

Recovering Trajectories of Unmarked Joints in 3D Human Actions Using Latent Space Optimization

Suhas Lohit, Rushil Anirudh, Pavan Turaga

Motion capture (mocap) and time-of-flight based sensing of human actions are becoming increasingly popular modalities to perform robust activity analysis. Applications range from a…

cs.CV2021

Halluci-Net: Scene Completion by Exploiting Object Co-occurrence Relationships

Kuldeep Kulkarni, Tejas Gokhale, Rajhans Singh +2

Recently, there has been substantial progress in image synthesis from semantic labelmaps. However, methods used for this task assume the availability of complete and unambiguous la…

math.AT2016

A Riemannian Framework for Statistical Analysis of Topological Persistence Diagrams

Rushil Anirudh, Vinay Venkataraman, Karthikeyan Natesan Ramamurthy +1

Topological data analysis is becoming a popular way to study high dimensional feature spaces without any contextual clues or assumptions. This paper concerns itself with one popula…

cs.CV2019

Geometry of Deep Generative Models for Disentangled Representations

Ankita Shukla, Shagun Uppal, Sarthak Bhagat +2

Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an…

cs.CV2016

Fast Integral Image Estimation at 1% measurement rate

Kuldeep Kulkarni, Pavan Turaga

We propose a framework called ReFInE to directly obtain integral image estimates from a very small number of spatially multiplexed measurements of the scene without iterative recon…

cs.CV2020

Invenio: Discovering Hidden Relationships Between Tasks/Domains Using Structured Meta Learning

Sameeksha Katoch, Kowshik Thopalli, Jayaraman J. Thiagarajan +2

Exploiting known semantic relationships between fine-grained tasks is critical to the success of recent model agnostic approaches. These approaches often rely on meta-optimization…

cs.SI2025

Graph Network Modeling Techniques for Visualizing Human Mobility Patterns

Sinjini Mitra, Anuj Srivastava, Avipsa Roy +1

Human mobility analysis at urban-scale requires models to represent the complex nature of human movements, which in turn are affected by accessibility to nearby points of interest,…

cs.CV2026

CMAG: Concept-Scaffolded Retrieval for Marketplace Avatar Generation

Rajeev Goel, Jason Ding, Phani Harish Wajjala +3

Metaverse platforms rely on creator-driven marketplaces where avatars are assembled from discrete, taxonomy-labeled 3D assets (e.g., tops, bottoms, shoes, accessories) under strict…

cs.LG2022

Automated Domain Discovery from Multiple Sources to Improve Zero-Shot Generalization

Kowshik Thopalli, Sameeksha Katoch, Pavan Turaga +1

Domain generalization (DG) methods aim to develop models that generalize to settings where the test distribution is different from the training data. In this paper, we focus on the…

cs.CV2018

Rate-Adaptive Neural Networks for Spatial Multiplexers

Suhas Lohit, Rajhans Singh, Kuldeep Kulkarni +1

In resource-constrained environments, one can employ spatial multiplexing cameras to acquire a small number of measurements of a scene, and perform effective reconstruction or high…

cs.CV2024

Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks

Jinyung Hong, Eun Som Jeon, Changhoon Kim +5

Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications and limit th…

cs.CV2022

Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study

Hongjun Choi, Eun Som Jeon, Ankita Shukla +1

Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the generalization and robustne…

cs.LG2026

CLAD-Net: Continual Activity Recognition in Multi-Sensor Wearable Systems

Reza Rahimi Azghan, Gautham Krishna Gudur, Mohit Malu +4

The rise of deep learning has greatly advanced human behavior monitoring using wearable sensors, particularly human activity recognition (HAR). While deep models have been widely s…

cs.CV2017

Learning Invariant Riemannian Geometric Representations Using Deep Nets

Suhas Lohit, Pavan Turaga

Non-Euclidean constraints are inherent in many kinds of data in computer vision and machine learning, typically as a result of specific invariance requirements that need to be resp…

cs.CV2025

Intra-class Patch Swap for Self-Distillation

Hongjun Choi, Eun Som Jeon, Ankita Shukla +1

Knowledge distillation (KD) is a valuable technique for compressing large deep learning models into smaller, edge-suitable networks. However, conventional KD frameworks rely on pre…

cs.CV2017

Convolutional Neural Networks for Non-iterative Reconstruction of Compressively Sensed Images

Suhas Lohit, Kuldeep Kulkarni, Ronan Kerviche +2

Traditional algorithms for compressive sensing recovery are computationally expensive and are ineffective at low measurement rates. In this work, we propose a data driven non-itera…

cs.CV2015

Reconstruction-free action inference from compressive imagers

Kuldeep Kulkarni, Pavan Turaga

Persistent surveillance from camera networks, such as at parking lots, UAVs, etc., often results in large amounts of video data, resulting in significant challenges for inference i…

q-bio.BM2022

Towards Conditional Generation of Minimal Action Potential Pathways for Molecular Dynamics

John Kevin Cava, John Vant, Nicholas Ho +4

In this paper, we utilized generative models, and reformulate it for problems in molecular dynamics (MD) simulation, by introducing an MD potential energy component to our generati…

cs.CV2022

Domain Alignment Meets Fully Test-Time Adaptation

Kowshik Thopalli, Pavan Turaga, Jayaraman J. Thiagarajan

A foundational requirement of a deployed ML model is to generalize to data drawn from a testing distribution that is different from training. A popular solution to this problem is…

cs.LG2021

Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion

Ankita Shukla, Rushil Anirudh, Eugene Kur +5

In this paper, we develop a Wasserstein autoencoder (WAE) with a hyperspherical prior for multimodal data in the application of inertial confinement fusion. Unlike a typical hypers…

cs.CV2016

Diversity Promoting Online Sampling for Streaming Video Summarization

Rushil Anirudh, Ahnaf Masroor, Pavan Turaga

Many applications benefit from sampling algorithms where a small number of well chosen samples are used to generalize different properties of a large dataset. In this paper, we use…

cs.LG2026

Gated Adaptation for Continual Learning in Human Activity Recognition

Reza Rahimi Azghan, Gautham Krishna Gudur, Mohit Malu +4

Wearable sensors in Internet of Things (IoT) ecosystems increasingly support applications such as remote health monitoring, elderly care, and smart home automation, all of which re…

cs.CV2024

Leveraging Topological Guidance for Improved Knowledge Distillation

Eun Som Jeon, Rahul Khurana, Aishani Pathak +1

Deep learning has shown its efficacy in extracting useful features to solve various computer vision tasks. However, when the structure of the data is complex and noisy, capturing e…

cs.CV2020

PI-Net: A Deep Learning Approach to Extract Topological Persistence Images

Anirudh Som, Hongjun Choi, Karthikeyan Natesan Ramamurthy +2

Topological features such as persistence diagrams and their functional approximations like persistence images (PIs) have been showing substantial promise for machine learning and c…

stat.ML2019

SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation

Kowshik Thopalli, Jayaraman J. Thiagarajan, Rushil Anirudh +1

Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adapta…

cs.LG2025

GluMind: Multimodal Parallel Attention and Knowledge Retention for Robust Cross-Population Blood Glucose Forecasting

Ebrahim Farahmand, Reza Rahimi Azghan, Nooshin Taheri Chatrudi +9

This paper proposes GluMind, a transformer-based multimodal framework designed for continual and long-term blood glucose forecasting. GluMind devises two attention mechanisms, incl…

cs.CV2019

Non-Parametric Priors For Generative Adversarial Networks

Rajhans Singh, Pavan Turaga, Suren Jayasuriya +2

The advent of generative adversarial networks (GAN) has enabled new capabilities in synthesis, interpolation, and data augmentation heretofore considered very challenging. However,…

cs.CV2023

Leveraging Angular Distributions for Improved Knowledge Distillation

Eun Som Jeon, Hongjun Choi, Ankita Shukla +1

Knowledge distillation as a broad class of methods has led to the development of lightweight and memory efficient models, using a pre-trained model with a large capacity (teacher n…

cs.CV2018

CS-VQA: Visual Question Answering with Compressively Sensed Images

Li-Chi Huang, Kuldeep Kulkarni, Anik Jha +3

Visual Question Answering (VQA) is a complex semantic task requiring both natural language processing and visual recognition. In this paper, we explore whether VQA is solvable when…

cs.CV2015

Geometry-based Adaptive Symbolic Approximation for Fast Sequence Matching on Manifolds

Rushil Anirudh, Pavan Turaga

In this paper, we consider the problem of fast and efficient indexing techniques for sequences evolving in non-Euclidean spaces. This problem has several applications in the areas…

cs.CV2023

Learning Pose Image Manifolds Using Geometry-Preserving GANs and Elasticae

Shenyuan Liang, Pavan Turaga, Anuj Srivastava

This paper investigates the challenge of learning image manifolds, specifically pose manifolds, of 3D objects using limited training data. It proposes a DNN approach to manifold le…

cs.CV2018

Multiple Subspace Alignment Improves Domain Adaptation

Kowshik Thopalli, Rushil Anirudh, Jayaraman J. Thiagarajan +1

We present a novel unsupervised domain adaptation (DA) method for cross-domain visual recognition. Though subspace methods have found success in DA, their performance is often limi…

cs.LG2025

Role of Mixup in Topological Persistence Based Knowledge Distillation for Wearable Sensor Data

Eun Som Jeon, Hongjun Choi, Matthew P. Buman +1

The analysis of wearable sensor data has enabled many successes in several applications. To represent the high-sampling rate time-series with sufficient detail, the use of topologi…

cs.CV2016

Shape Distributions of Nonlinear Dynamical Systems for Video-based Inference

Vinay Venkataraman, Pavan Turaga

This paper presents a shape-theoretic framework for dynamical analysis of nonlinear dynamical systems which appear frequently in several video-based inference tasks. Traditional ap…

cs.CV2016

ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements

Kuldeep Kulkarni, Suhas Lohit, Pavan Turaga +2

The goal of this paper is to present a non-iterative and more importantly an extremely fast algorithm to reconstruct images from compressively sensed (CS) random measurements. To t…

cs.LG2021

Interpretable COVID-19 Chest X-Ray Classification via Orthogonality Constraint

Ella Y. Wang, Anirudh Som, Ankita Shukla +2

Deep neural networks have increasingly been used as an auxiliary tool in healthcare applications, due to their ability to improve performance of several diagnosis tasks. However, t…

cs.CV2020

AMC-Loss: Angular Margin Contrastive Loss for Improved Explainability in Image Classification

Hongjun Choi, Anirudh Som, Pavan Turaga

Deep-learning architectures for classification problems involve the cross-entropy loss sometimes assisted with auxiliary loss functions like center loss, contrastive loss and tripl…

cs.CV2025

Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation

Utkarsh Nath, Rajeev Goel, Eun Som Jeon +5

To address the data scarcity associated with 3D assets, 2D-lifting techniques such as Score Distillation Sampling (SDS) have become a widely adopted practice in text-to-3D generati…

eess.SP2024

Topological Persistence Guided Knowledge Distillation for Wearable Sensor Data

Eun Som Jeon, Hongjun Choi, Ankita Shukla +4

Deep learning methods have achieved a lot of success in various applications involving converting wearable sensor data to actionable health insights. A common application areas is…

cs.LG2026

Geometry Preserving Loss Functions Promote Improved Adaptation of Blackbox Generative Model

Sinjini Mitra, Constantine Kyriakakis, Shenyuan Liang +2

Adaptation of blackbox generative models has been widely studied recently through the exploration of several methods including generator fine-tuning, latent space searches, leverag…

cs.CV2018

An Optical Flow-Based Approach for Minimally-Divergent Velocimetry Data Interpolation

Berkay Kanberoglu, Dhritiman Das, Priya Nair +2

Three-dimensional (3D) biomedical image sets are often acquired with in-plane pixel spacings that are far less than the out-of-plane spacings between images. The resultant anisotro…

cs.CV2022

Single-Shot Domain Adaptation via Target-Aware Generative Augmentation

Rakshith Subramanyam, Kowshik Thopalli, Spring Berman +2

The problem of adapting models from a source domain using data from any target domain of interest has gained prominence, thanks to the brittle generalization in deep neural network…

cs.CV2020

Generative Patch Priors for Practical Compressive Image Recovery

Rushil Anirudh, Suhas Lohit, Pavan Turaga

In this paper, we propose the generative patch prior (GPP) that defines a generative prior for compressive image recovery, based on patch-manifold models. Unlike learned, image-lev…

cs.CV2018

Compressive Light Field Reconstructions using Deep Learning

Mayank Gupta, Arjun Jauhari, Kuldeep Kulkarni +3

Light field imaging is limited in its computational processing demands of high sampling for both spatial and angular dimensions. Single-shot light field cameras sacrifice spatial r…

cs.LG2026

Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learning

Reza Rahimi Azghan, Gautham Krishna Gudur, Giulia Pedrielli +2

Large language models generalize well to individual tasks but lack an inherent mechanism for learning them sequentially, leading to catastrophic forgetting. To mitigate this, LoRA-…

cs.CV2019

Product of Orthogonal Spheres Parameterization for Disentangled Representation Learning

Ankita Shukla, Sarthak Bhagat, Shagun Uppal +2

Learning representations that can disentangle explanatory attributes underlying the data improves interpretabilty as well as provides control on data generation. Various learning f…

cs.LG2020

Unsupervised Pre-trained Models from Healthy ADLs Improve Parkinson's Disease Classification of Gait Patterns

Anirudh Som, Narayanan Krishnamurthi, Matthew Buman +1

Application and use of deep learning algorithms for different healthcare applications is gaining interest at a steady pace. However, use of such algorithms can prove to be challeng…

cs.CV2026

Selective Correlation Based Knowledge Distillation for Ground Reaction Force Estimation

Eun Som Jeon, Jisoo Lee, Huisu Lim +3

Wearable sensor-based human gait analysis holds great promise in healthcare, rehabilitation, clinical diagnosis and monitoring, and sports activities. Specifically, ground reaction…

cs.CV2016

Elastic Functional Coding of Riemannian Trajectories

Rushil Anirudh, Pavan Turaga, Jingyong Su +1

Visual observations of dynamic phenomena, such as human actions, are often represented as sequences of smoothly-varying features . In cases where the feature spaces can be structur…