Key Research Areas
Optical Character Recognition, Road Safety, Computer Vison Applications related to Environment and Agriculture
About
I have done B.E. Hons. from BITS Goa in EEE and have worked at BHEL for four years. I completed my Ph.D. in Robust Multilingual Indic OCR from IITB-Monash Research Academy and did a postdoc on road safety-related problems at IIIT Hyderabad. My research interests lie in the fields of Computer Vision, applied ML, deep learning, human interactive applications, road safety, open world models, Computer Vision in extreme weather conditions, and applications related to agriculture and saving environment.
I have received several awards from my works which are listed here: https://rohitsaluja22.github.io/awards.html
Recent Publications
1. S. N. Rai, R. Saluja, C. Arora, V. N. Balasubramanian, A. Subramanian, and C. Jawahar, "FLUID: Few-Shot Self-Supervised Image Deraining," in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 3077-3086.
2. A. Goyal, D. Agarwal, A. Subramanian, C. Jawahar, R. K. Sarvadevabhatla, and R. Saluja, "Detecting, Tracking and Counting Motorcycle Rider Traffic Violations on Unconstrained Roads," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4303-4312.
3. D. K. Singh et al., "ORDER: Open World Object Detection on Road Scenes," in Proc. NeurIPS Workshops, 2021.
4. R. Saluja, A. Maheshwari, G. Ramakrishnan, P. Chaudhuri, and M. Carman, "Ocr on-the-go: Robust end-to-end systems for reading license plates & street signs," in 2019 International Conference on Document Analysis and Recognition (ICDAR), 2019, pp. 154-159.
5. R. Saluja, D. Adiga, P. Chaudhuri, G. Ramakrishnan, and M. Carman, "Error detection and corrections in Indic OCR using LSTMs," in 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, vol. 1, pp. 17-22.
Course Taught
1. Presently teaching "Computing and Data Science". Have not taught any other course in last 3 years.