Chirag Parikh

ORCID: 0000-0003-0216-7966
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Neural Network Applications
  • Infrastructure Maintenance and Monitoring
  • Vehicle License Plate Recognition
  • Autonomous Vehicle Technology and Safety
  • Explainable Artificial Intelligence (XAI)
  • Advanced Malware Detection Techniques
  • Nuclear Physics and Applications
  • Video Surveillance and Tracking Methods
  • Network Packet Processing and Optimization
  • Atomic and Subatomic Physics Research
  • Anomaly Detection Techniques and Applications
  • Domain Adaptation and Few-Shot Learning
  • Adversarial Robustness in Machine Learning
  • Speech Recognition and Synthesis
  • High-pressure geophysics and materials

Indian Institute of Technology Hyderabad
2022-2024

NIST Center for Neutron Research
2022

National Institute of Standards and Technology
2022

A description and the performance of very small angle neutron scattering diffractometer at National Institute Standards Technology are presented. The measurement range instrument extends over three decades momentum transfer

10.1107/s1600576722000826 article EN cc-by Journal of Applied Crystallography 2022-02-27

The previous fine-grained datasets mainly focus on classification and are often captured in a controlled setup, with the camera focusing objects. We introduce first Fine-Grained Vehicle Detection (FGVD) dataset wild, from moving mounted car. It contains 5502 scene images 210 unique labels of multiple vehicle types organized three-level hierarchy. While also include makes for different kinds cars, FGVD introduces new class categorizing two-wheelers, autorickshaws, trucks. is challenging as it...

10.1145/3571600.3571626 preprint EN 2022-12-08

Intelligent vehicle systems require a deep understanding of the interplay between road conditions, surrounding entities, and ego vehicle's driving behavior for safe efficient navigation. This is particularly critical in developing countries where traffic situations are often dense unstructured with heterogeneous occupants. Existing datasets, predominantly geared towards structured sparse scenarios, fall short capturing complexity such environments. To fill this gap, we present IDD-X,...

10.48550/arxiv.2404.08561 preprint EN arXiv (Cornell University) 2024-04-12
Coming Soon ...