I am a PhD student at the Center for Visual Information Technology (CVIT - Mobility), IIIT Hyderabad, supervised by Prof. Ravi Kiran Sarvadevabhatla.
Research Interests: My research focuses on grounded video understanding with multimodal models. I am particularly interested in visual grounding, multimodal reasoning, and improving reliability of Multimodal LLMs for dynamic real-world scenes. My work spans both intelligent transportation and more general video domains, with the goal of developing models that can reason about events and interactions, localize relevant entities in space and time, and ground their outputs in visual evidence.
Bio: Before my PhD, I worked on intelligent visual systems for driver behavior monitoring and satellite-based cropland analysis in industry and on robotic vision projects during my undergrad.
I am actively seeking research internship opportunities for 2027, please feel free to reach out by email.
@article{parikh2025roadsocial,
author = {Chirag Parikh and Deepti Rawat and Rakshitha R. T. and Tathagata Ghosh and Ravi Sarvadevabhatla},
title = {RoadSocial: A Diverse VideoQA Dataset and Benchmark for Road Event Understanding from Social Video Narratives},
booktitle = {Proc. of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2025},
}
@inproceedings{parikh2026roadtones,
author = {Chirag Parikh and Siddhi Lipare and Ravi Sarvadevabhatla},
title = {RoadTones: Tone Controllable Text Generation from Road Event Videos},
booktitle = {Proc. of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2026},
}
@inproceedings{parikh2024idd,
author = {Chirag Parikh and Rohit Saluja and CV Jawahar and Ravi Sarvadevabhatla},
title = {IDD-X: A Multi-View Dataset for Ego-relative Important Object Localization and Explanation in Dense and Unstructured Traffic},
booktitle = {Proc. of IEEE International Conference on Robotics and Automation (ICRA)},
year = {2024},
}
@article{mishra2025iddcrs,
author = {Ravi Mishra and Chirag Parikh and Anbumani Subramanian and C.V. Jawahar and Ravi Sarvadevabhatla},
title = {IDD-CRS: A Comprehensive Video Dataset for Critical Road Scenarios in Unstructured Environments},
booktitle = {Proc. of IEEE Intelligent Vehicles Symposium (IV)},
year = {2025},
}
@article{parikh2024transfer,
author = {Chirag Parikh and Ravi Mishra and Rohan Chandra and Ravi Sarvadevabhatla},
title = {Transfer-LMR: Heavy-Tail Driving Behavior Recognition in Diverse Traffic Scenarios},
year = {2024},
journal = {arXiv.org},
}
@inproceedings{khoba2022fine,
author = {Prafful Khoba and Chirag Parikh and CV Jawahar and Ravi Sarvadevabhatla and Rohit Saluja},
title = {A Fine-Grained Vehicle Detection (FGVD) Dataset for Unconstrained Roads},
booktitle = {Proc. of the Thirteenth Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP)},
year = {2022},
}
@misc{pal2024real,
author = {Surjya Pal and Aaquib Khan and Ravi Ranjan and Chirag Parikh and Srikanta Pal and Debashish Chakravarty and Abhik Maiti},
title = {Real Time Surface Defect Analysis And Correction In Friction Stir Welding Process By Image Processing},
year = {2024},
journal = {IN Patent 514,971},
}
@article{parikh2017volumetric,
author = {Chirag Parikh and Ravi Ranjan and Aaquib Khan and Rahul Jain and Raju Mahto and Debashish Chakravarty and Srikanta Pal and Surjya Pal},
title = {Volumetric defect analysis in friction stir welding based on three dimensional reconstructed images},
year = {2017},
journal = {Journal of Manufacturing Processes},
volume = {29},
}
@article{ranjan2016classification,
author = {Ravi Ranjan and Aaquib Khan and Chirag Parikh and Rahul Jain and Raju Mahto and Srikanta Pal and Surjya Pal and Debashish Chakravarty},
title = {Classification and identification of surface defects in friction stir welding: An image processing approach},
year = {2016},
journal = {Journal of Manufacturing Processes},
volume = {22},
}
@article{parikh2023DAN_VQA,
author = {Chirag Parikh and Adhiraj Deshmukh and Neeraj Veerla and Shreya Patil},
title = {Differential Attention Networks for Visual Question Answering},
year = {2023},
school = {CV Project at IIIT Hyderabad},
}
@article{parikh2025VDBMS,
author = {Chirag Parikh},
title = {Integrating storage manager (TASM) and query optimizer (FiGO) in Video-DBMS},
year = {2025},
school = {DS Project at IIIT Hyderabad},
}
@bachelorsthesis{Paul2016Bachelor,
author = {Shubham Paul and Chirag Parikh and Naman Pandey and Anirvan Dutta},
title = {Real-time Shuttlecock Tracking and Trajectory Estimation for Badminton Playing Robot},
year = {2016},
school = {Birla Institute of Technology, Mesra},
}
This page is based on the template of Michael Niemeyer. Checkout his GitHub repository for instructions on how to use it.