2 citations · 2 across the 14 of their papers we have counts for
17 papers
Reliability-Preserving Compression for Deployable Medical Image Segmentation
Sagar Kumar, Shailja Sharma, Tirthajit Baruah +1
Post-training compression of pretrained medical segmentation models commonly uses quantization, pruning, or distillation to reduce model size and computational cost. Existing medic…
NVE: A Separability and Coverage-Aware Internal Validation Metric for Biclustering
Paritosh Tiwari, I Navin Kumar, James C. Bezdek +1
Biclustering, or co-clustering, aims to discover coherent submatrices by grouping rows and columns of a data matrix simultaneously. This local two-dimensional structure makes valid…
Why Clipping Matters in AdaGrad? Toward a High-Probability Theory under Generalized Smoothness
Alokendu Mazumder, Ayaan Mohd, Harshit Rawat +3
We analyze the original same-step coordinate-wise AdaGrad under generalized smoothness and heavy-tailed noise with bounded variance. In this setting, local curvature may grow sub-q…
On Hamming-Lipschitz Type Stability of the Subdominant (Minmax) Ultrametric: Theory and Simple Proofs
Alokendu Mazumder, Arnab Roy, Punit Rathore
The subdominant (minmax) ultrametric is a canonical tree-structured summary of a dissimilarity matrix, arising equivalently as the ultrametric induced by single-linkage clustering.…
Unsupervised Detection of Entry and Exit Regions from Vehicle Trajectories for Camera-Agnostic Turning Movement Counts
Parikshit Singh Rathore, Vishwajeet Pattanaik, Punit Rathore
Turning movement counts are essential for intersection-level traffic management, yet their collection remains predominantly manual due to the cost of per-camera region annotation.…
BMD-45: A Large-Scale CCTV Vehicle Detection Dataset for Urban Traffic in Developing Cities
Akash Sharma, Chinmay Mhatre, Sankalp Gawali +8
Robust vehicle detection from fixed CCTV cameras is critical for Intelligent Transportation Systems. Yet existing benchmarks predominantly feature relatively homogeneous, highly or…
Scaling Real-Time Traffic Analytics on Edge-Cloud Fabrics for City-Scale Camera Networks
Akash Sharma, Pranjal Naman, Roopkatha Banerjee +11
Real-time city-scale traffic analytics requires processing 100s-1000s of CCTV streams under strict latency, bandwidth, and compute limits. We present a scalable AI-driven Intellige…
The Urban Vision Hackathon Dataset and Models: Towards Image Annotations and Accurate Vision Models for Indian Traffic
Akash Sharma, Chinmay Mhatre, Sankalp Gawali +10
This report describes the UVH-26 dataset, the first public release by AIM@IISc of a large-scale dataset of annotated traffic-camera images from India. The dataset comprises 26,646…
Physics-informed neural network for predicting fatigue life of unirradiated and irradiated austenitic and ferritic/martensitic steels under reactor-relevant conditions
Dhiraj S Kori, Abhinav Chandraker, Syed Abdur Rahman +2
This study proposes a Physics-Informed Neural Network (PINN) framework to predict the low-cycle fatigue (LCF) life of irradiated austenitic and ferritic/martensitic (F/M) steels us…
STEAM: Squeeze and Transform Enhanced Attention Module
Rishabh Sabharwal, Ram Samarth B B, Parikshit Singh Rathore +1
Channel and spatial attention mechanisms introduced in earlier work enhance the representational capabilities of deep convolutional neural networks (CNNs) but often increase parame…
A Visual-Analytical Approach for Automatic Detection of Cyclonic Events in Satellite Observations
Akash Agrawal, Mayesh Mohapatra, Abhinav Raja +5
Estimating the location and intensity of tropical cyclones holds crucial significance for predicting catastrophic weather events. In this study, we approach this task as a detectio…
Learning Low-Rank Latent Spaces with Simple Deterministic Autoencoder: Theoretical and Empirical Insights
Alokendu Mazumder, Tirthajit Baruah, Bhartendu Kumar +3
The autoencoder is an unsupervised learning paradigm that aims to create a compact latent representation of data by minimizing the reconstruction loss. However, it tends to overloo…
A Theoretical and Empirical Study on the Convergence of Adam with an "Exact" Constant Step Size in Non-Convex Settings
Alokendu Mazumder, Rishabh Sabharwal, Manan Tayal +2
In neural network training, RMSProp and Adam remain widely favoured optimisation algorithms. One of the keys to their performance lies in selecting the correct step size, which can…
DeepVAT: A Self-Supervised Technique for Cluster Assessment in Image Datasets
Alokendu Mazumder, Tirthajit Baruah, Akash Kumar Singh +3
Estimating the number of clusters and cluster structures in unlabeled, complex, and high-dimensional datasets (like images) is challenging for traditional clustering algorithms. In…
ConiVAT: Cluster Tendency Assessment and Clustering with Partial Background Knowledge
Punit Rathore, James C. Bezdek, Paolo Santi +1
The VAT method is a visual technique for determining the potential cluster structure and the possible number of clusters in numerical data. Its improved version, iVAT, uses a path-…
Understanding the Dynamics of Drivers' Locations for Passengers Pickup Performance: A Case Study
Punit Rathore, Ali Zonoozi, Omid Geramifard +1
With the emergence of e-hailing taxi services, a growing number of scholars have attempted to analyze the taxi trips data to gain insights from drivers' and passengers' flow patter…
A Scalable Framework for Trajectory Prediction
Punit Rathore, Dheeraj Kumar, Sutharshan Rajasegarar +2
Trajectory prediction (TP) is of great importance for a wide range of location-based applications in intelligent transport systems such as location-based advertising, route plannin…