Siddharth Roheda
I received my B.Tech degree from Nirma Institute of Technology in 2015. I am currently a PhD student at North Carolina State University, working at the Vision, Information, and Statistical Signal Theories and Applications Lab (VISSTA Lab), under the guidance of Dr. Hamid Krim.
My current research focuses on detection and classification of targets using sensors like radars and telescopic imaging, and developing robust sensor fusion algorithms at the decision level.
Publications:
- Robust Multi-Modal Sensor Fusion: An Adversarial Approach. Roheda, Siddharth, Hamid Krim, and Benjamin S. Riggan. IEEE Sensors Journal (2020).
- Commuting Conditional GANs for Multi-Modal Fusion, Siddharth Roheda, Hamid Krim, Benjamin S. Riggan, ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020.
- Conquering the CNN Over-Parameterization Dilemma: A Volterra Filtering Approach for Action Recognition. Roheda, S., & Krim, H. (2019). To Appear in AAAI 2020. [PDF]
- Decision Level Fusion: An Event Driven Approach, Siddharth Roheda, Hamid Krim, Zhi-Quan Luo, Tianfu Wu, IEEE EUSIPCO 2018 (Presentation). [PDF]
- Cross-Modal Distillation: A Case for Generative Adversarial Networks, Siddharth Roheda, Benjamin S Riggan, Hamid Krim, Liyi Dai, IEEE International Conference on Acoustics , Speech and Signal Processing 2018 (Poster). [PDF]