Santosh Yadav

Biography & Research Interests

I am a Postdoctoral Researcher in the C3-Imaging group at National University of Ireland, Galway, and an intern at Xperi. I started the postdoc position in Aug 2021.
I completed my PhD research work from Academy of Scientific and Innovative Research (AcSIR) at CSIR-Central Electronics Engineering Research Institute (CEERI), Pilani, India. My PhD topic was “Unobtrusive Multimodal Human Activity Recognition”, where I used computer vision, wearable sensing, and WiFi sensing for recognizing human activities using single and multiple modalities.
During my PhD research work, I have worked as a visiting scholar at Stanford University with professor Dr. Ehsan Adeli; and as a research assistant at the University Of Texas, San Antonio, United States and the Edge Hill University, United Kingdom, with Dr. Heena Rathore and Dr. Hari Mohan Pandey, respectively.
My research interest include Computer Vision, Wearable Computing, Deep Learning, Multimodal Artificial Intelligence, Action Recognition.

Research Activities

• Development of a multimodal (sound and vision) AI processing platform with low cost and low power consumption to be used for the creation of voice-enabled toys.
• Video Based Yoga Recognition and Posture Correction System Using Deep Learning.
• Multimodal activity recognition using the combination of visual and inertial sensors.
• Karate Action Recognition And Evaluation System using visual and inertial cues using four streams i.e., pose stream, RGB stream, optical flow stream, and sensors stream.
• Realtime Activities Of Daily Living using RGB videos obtained from smartphones.
• Group Activity Recognition using a novel weighted temporal attention module (WTM).
• Transformers For Video Action Recognition with temporal attention for improving 3D-CNNs performance.
• Drone Camera Based Human Activity Recognition using a novel 3D-CNN model with spatial and temporal attention.
• WiFi channel state information based human activity recognition using a novel 2D-CNN with attention model.

Journal Publications

Santosh Kumar Yadav, Aayush Agarwal, Ashish Kumar, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar, “YogNet: A Two-Stream Network for Realtime Multiperson Yoga Action Recognition and Posture Correction”, Published in Knowledge-Based Systems, Elsevier. DOI: https://doi.org/10.1016/j.knosys.2022.109097, 2022. (IF: 8.038)

Santosh Kumar Yadav, Amitojdeep Singh, Abhishek Gupta, Jagdish Lal Raheja, ”Real-Time Yoga Recognition using Deep Learning”, Published in Neural Computing and Applications, Springer, DOI: https://doi.org/10.1007/s00521-019-04232-7,2019.(IF: 5.606).

Santosh Kumar Yadav, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar, ”A Review of Multimodal Human Activity Recognition with Special Emphasis on Classification, Applications, Challenges and Future Directions”, Published in Knowledge Based Systems, Elsevier, DOI: https://doi.org/10.1016/j.knosys.2021.106970, 2021. (IF: 8.038).

Santosh Kumar Yadav, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar, ”Skeleton based Human Activity Recognition using ConvLSTM and Guided Feature Learning”, Published in Soft Computing, Springer, DOI: https://doi.org/10.1007/s00500-021-06238-7, 2021. (IF: 3.643).

Santosh Kumar Yadav, Achleshwar Luthra, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar, “ARFDNet: An Efficient Activity Recognition & Fall Detection System using Latent Feature Pooling”, Published in Knowledge Based Systems, Elsevier, DOI: https://doi.org/10.1016/j.knosys.2021.107948, 2022. (IF: 8.038).

Santosh Kumar Yadav, Siva Sai, Akshay Gundewar, Heena Rathore, Kamlesh Tiwari, Hari Mohan Pandey, Mohit Mathur, "CSITime: Privacy-preserving human activity recognition using WiFi channel state information", Published in Neural Networks, Elsevier. DOI: https://doi.org/10.1016/j.neunet.2021.11.011, 2022. (IF: 8.050).

Conference Participation & Presentations

Santosh Kumar Yadav, Guntaas Singh, Manisha Verma, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar, Peter Corcoran, “YogaTube: A Video Benchmark for Yoga Action Recognition”, Accepted in International Joint Conference on Neural Networks (IJCNN), IEEE WCCI 2022, Padua, Italy.

Santosh Kumar Yadav, Aditya Deshmukh, Raghurama Varma Gonela, Shreyas Kera, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar, “MS-KARD: A Benchmark for Multimodal Karate Action Recognition”, Accepted in International Joint Conference on Neural Networks (IJCNN), IEEE WCCI 2022, Padua, Italy.

Santosh Kumar Yadav, Palaash Agarwal, Kamlesh Tiwari, Ehsan Adeli, Hari Mohan Pandey, Shaik Ali Akbar, “WTM: Weighted Temporal Attention Module for Group Activity Recognition”, Accepted in International Joint Conference on Neural Networks (IJCNN), IEEE WCCI 2022, Padua, Italy.

Santosh Kumar Yadav, Shreyas Kera, Raghurama Varma Gonela, Kamlesh Tiwari, Hari Mohan Pandey, Shaik Ali Akbar, “TBAC: Transformers Based Attention Consensus for Human Activity Recognition”, Accepted in International Joint Conference on Neural Networks (IJCNN), IEEE WCCI 2022, Padua, Italy.

Achleshwar Luthra, Harsh Sulakhe, Tanish Mittal, Abhishek Iyer, Santosh Yadav, “Eformer: Edge Enhancement based Transformer for Medical Image Denoising”, Published in ICCVW 2021, arXiv preprint arXiv:2109.08044, 2021.