Dr. Santosh Yadav
Currently, I work as a Senior Data Scientist specializing in High-Performance Computing at the WiSAR Lab, ATU. Previously, I worked as an AI Research Scientist at CeADAR, a Postdoctoral Scientist at the National University of Ireland, Galway, and a researcher at Xperi Corporation. Before that, I completed my Ph.D. from the Academy of Scientific & Innovative Research (AcSIR) at CSIR–CEERI, Pilani, under the Supervision of Dr. S. A. Akbar (Chief Scientist, CSIR-CEERI, Pilani) and Co-supervision of Dr. Kamlesh Tiwari (Professor, BITS Pilani).
Currently, I am doing research in the areas of High Performance Computing, Computer Vision, Speech Understanding, Human Action Recognition, and Multimodal Artificial Intelligence. Email me at santosh.yadav@ieee.org for research discussions, collaborations, or just chatting!
ResearchGate | Google Scholar | NUI-Galway | Life Journey | LinkedIn
Recent Publications
SLBERT: A Novel Pre-Training Framework for Joint Speech and Language Modeling
Onkar Susladkar, Prajwal Gatti, Santosh Kumar Yadav
Accepted in IEEE International Conference on Acoustics, Speech and Signal Processing, 2023.
DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition
Santosh Kumar Yadav, Achleshwar Luthra, Esha Pahwa, Kamlesh Tiwari, Heena Rathore, Hari Mohan Pandey, Peter Corcoran
Accepted in Neural Networks, Elsevier, 2023.
SWTF: Sparse Weighted Temporal Fusion for Drone-Based Activity Recognition
Santosh Kumar Yadav, Esha Pahwa, Achleshwar Luthra, Kamlesh Tiwari, Hari Mohan Pandey, Peter Corcoran
Accepted in IEEE International Conference on Consumer Electronics (IEEE ICCE 2023), Las Vegas, USA.
YogNet: A Two-Stream Network for Realtime Multiperson Yoga Action Recognition and Posture Correction
Santosh Kumar Yadav, Aayush Agarwal, Ashish Kumar, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar
Published in Knowledge-Based Systems, Elsevier, 2022.
TBAC: Transformers Based Attention Consensus for Human Activity Recognition
Santosh Kumar Yadav, Shreyas Kera, Raghurama Varma Gonela, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar
Accepted in International Joint Conference on Neural Networks (IJCNN) at IEEE WCCI, Padua, Italy, July 2022.
WTM: Weighted Temporal Attention Module for Group Activity Recognition
Santosh Kumar Yadav, Palaash Agarwal, Kamlesh Tiwari, Ehsan Adeli, Hari Mohan Pandey, Shaik Ali Akbar
Accepted in International Joint Conference on Neural Networks (IJCNN) at IEEE WCCI, Padua, Italy, July 2022.
MS-KARD: A Benchmark for Multimodal Karate Action Recognition
Santosh Kumar Yadav, Aditya Deshmukh, Raghurama Varma Gonela, Shreyas Kera, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar
Accepted in International Joint Conference on Neural Networks (IJCNN) at IEEE WCCI, Padua, Italy, July 2022.
YogaTube: A Video Benchmark for Yoga Action Recognition
Santosh Kumar Yadav, Guntaas Singh, Manisha Verma, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar, Peter Corcoran
Accepted in International Joint Conference on Neural Networks (IJCNN) at IEEE WCCI, Padua, Italy, July 2022.
ARFDNet: An efficient activity recognition & fall detection system using latent feature pooling
Santosh Kumar Yadav, Achleshwar Luthra, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar
Published in Knowledge-Based Systems, Elsevier, 2022.
CSITime: Privacy-preserving human activity recognition using WiFi channel state information
Santosh Kumar Yadav, Siva Sai, Akshay Gundewar, Heena Rathore, Kamlesh Tiwari, Hari Mohan Pandey, Mohit Mathur
Published in Neural Networks, Elsevier, 2022.
Skeleton-based human activity recognition using ConvLSTM and guided feature learning
Santosh Kumar Yadav, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar
Published in Soft Computing, Springer, 2022.
Eformer: Edge Enhancement based Transformer for Medical Image Denoising
Achleshwar Luthra, Harsh Sulakhe, Tanish Mittal, Abhishek Iyer, Santosh Yadav
Published in ICCV, 2021.
A Review of Multimodal Human Activity Recognition with Special Emphasis on Classification, Applications, Challenges, and Future Directions
Santosh Kumar Yadav, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar
Published in Knowledge-Based Systems, Elsevier, 2021.
Demo Videos
Realtime yoga recognition using deep learning
Skeleton-based human activity recognition using ConvLSTM and guided feature learning
Drone-Camera Based Activity Recognition
Karate Action Recognition
YogNet: A Two-Stream Network for Realtime Multiperson Yoga Action Recognition and Posture Correction
ARFDNet: An efficient activity recognition & fall detection system using latent feature pooling
TBAC: Transformers Based Attention Consensus for Human Activity Recognition
Sports video analysis for Gymnastics
Weighted Temporal Attention Module forGroup Activity Recognition
Professional Experience
HPC - Senior Data Scientist at WiSAR Lab, ATUD, Ireland (January 2024 - Present)
AI Research Scientist at CeADAR, Dublin, Ireland (March 2023 - December 2023)
Postdoctoral Scientist at NUI Galway, Ireland (August 2021 - March 2023)
Researcher at Xperi Corporation, Ireland (August 2021 - March 2023)
Project Advisor and Consultant at LiveSmart KK, Japan (June 2021 - December 2021)
Visiting Scholar with Dr. Ehasan Adeli, Stanford University, USA (February 2021 - June 2021)
Research Assistant with Dr. Heena Rathore, The University of Texas San Antonio, USA (January 2021 - May 2021)
Research Assistant with Dr. Hari Mohan Pandey, Edge Hill University, UK (August 2020 - February 2021)
Senior Research Fellow at CSIR–CEERI, Pilani, India (August 2019 - August 2021)
Junior Research Fellow at CSIR–CEERI, Pilani, India (March 2017 - August 2019)
Junior Research Fellow at CSIR–CECRI, Karaikudi, India (August 2016 - March 2017)
Reviewing
IEEE Access - IEEE
Applied Intelligence - Springer
Infrared Physics & Technology - Elsevier
Other Resources
Other Links
ResearchGate | Google Scholar | ORCID | Scopus | CSIR-CEERI | BITS Pilani | NUI-Galway | LinkedIn | GitHub | CogniX