Nandani Sharma

Ph.D. research scholar

Indian Institute of Technology Mandi, Himachal Pradesh, India.

I am a Ph.D. research scholar at the Indian Institute of Technology Mandi (IIT Mandi) in the School of Computing and Electrical Engineering (SCEE) under the supervision of Dr. Dinesh Singh, my research focuses on Facial Expression and Facial Paralysis Detection, Driver Drowsiness a field that integrates advanced computing with human-centered applications.

I hold a B.Tech. (Hons.) and M.Tech. in Computer Science and Engineering from Dr. A.P.J. Abdul Kalam Technical University (AKTU), where I was awarded the Gold Medal for securing the top position in the Computer Science and Engineering branch across Uttar Pradesh.

As an active member of the Visual Intelligence and Machine Learning (VIML) research group at IIT Mandi, led by Dr. Dinesh Singh and Dr. Rohit Saluja, I contribute to cutting-edge research in Computer Vision, Machine Learning, Natural Language Processing, Surveillance Video Analytics, and Biomedical Imaging.

At IIT Mandi, I thrive in an intellectually stimulating environment, dedicated to pushing the boundaries of AI and biomedical engineering. My goal is to develop innovative solutions that enhance human well-being through technology.

Ongoing Work: 

• Fine-Grained Facial Expression Recognition

• Micro-Expression Recognition.

• Facial Paralysis Recognition and Recovery Forecasting. 

Patents:

Jul 2025: Nandani Sharma, Kajal Singh, and Dinesh Singh, ”Method And System For Forecasting Facial Paralysis Severity”, Indian Patent Filed.

Publications and Preprints:

1. Ravi Shankar Prasad, Nandani Sharma, and Dinesh Singh (2026). “Cranio-ID: Graph-Based Craniofacial Identification via Automatic Landmark Annotation in 2D Multi-View X-rays”. In: Proceedings of WCCI-IJCNN. 

2. Dipanshu, Rohit Srivastava, Nandani Sharma, Dinesh Singh (2026). Star-Cut: Spatio-Temporal Attention Reckoning using CNN United Transformer. Under review. 

3. Sharma, Nandani et al. (2026a). “NoMS-FER: Noise-Robust Multimodal Semantic Learning for Fine-Grained Facial Expression Recognition”. In: Under review.

4. Sharma, Nandani et al. (2026b). “STAG: Spatio-temporal Evolving Structural Representation of Action Units for Micro-expression Recognition”. In: arXiv preprint arXiv:2606.28083. doi: 10.48550/arXiv. 2606.28083. arXiv: 2606.28083 [cs.CV]. url: https://doi.org/10.48550/arXiv.2606.28083. Under review.

5. Sharma, N., Sachin, B., Shah, M., & Singh, D. (2026). Improved single-stage facial landmarks for real-time driver drowsiness detection. In: Chatterjee, B., Kothapalli, K., Mittal, N., Natarajan, A.M., Singh, D. (eds) Distributed Computing and Intelligent Technology. ICDCIT 2026. Lecture Notes in Computer Science, vol 16420. Springer, Cham. https://doi.org/10.1007/978-3-032-16632-6_12

6. Nandani Sharma, Ankit Kumar, Dinesh Singh. (2026). Robust Local Pixel Dependency Patterns on CNNs-based Generative Network for Deepfake Detection. Under review. 

7. Sharma, N., Singh, K., & Singh, D. (2025). Para-X: Graph-based facial paralysis detection using structural deformations of facial expression. In Proceedings of the International Joint Conference on Neural Networks (IJCNN) (pp. 1–8). IEEE.  

8. Nandani Sharma, Dinesh Singh. (2025) Exp-Graph: How connections learn facial attributes in graph-based expression recognition. arXiv preprint, arXiv:2507.14608. Under review.