Lala Shakti Swarup Ray

I am a PhD researcher at Embedded Intelligence Lab in German Research Center of Artificial Intelligence (DFKI), Kaiserslautern.

Domain: Computer Graphics/Simulation, Sensors, AI

• Contact Me

Education

• PhD. RPTU Kaiserslautern, Germany
  Thesis Title: Elevating sHAR with Simulations and Cross-Modal Insights.
  2023 - Present
• M.Sc. Informatik (Major: Intelligent systems, Minor: Robotics) TU Kaiserslautern, Germany
  (Thesis) Deutsches Forschungszentrum für Künstliche Intelligenz, Kaiserslautern
  Thesis Title: Inferring contact pressure matrix from videos using neural networks and physics simulations.
  2019 - 2022
• B.Tech. Computer Engineering IGIT Sarang, India
  Thesis Title: Mobile VR Application to treat phobias.
  2014 - 2018

Work Experience

• PhD Researcher, Embedded Intelligence Group, Deutsches Forschungszentrum für Künstliche Intelligenz, Kaiserslautern, December 2022 - Present
• Junior Researcher, Embedded Intelligence Group, Deutsches Forschungszentrum für Künstliche Intelligenz, Kaiserslautern, July 2022 - November 2022
• Research Assistant, Image Processing Group, Fraunhofer-Institut für Techno- und Wirtschaftsmathematik, Kaiserslautern, November 2021 - June 2022
• Research Assistant, Augmented Vision Group, Deutsches Forschungszentrum für Künstliche Intelligenz, Kaiserslautern, October 2020 - June 2022
• Technical Internship, Autonomous Driving Group, Zummit Infolabs LLP, Munich, July 2021 - October 2021
• Research Internship, Electronics & Telecommunication Department, IIT Guwahati, April 2017 - July 2017

Supervision Experience

• Yunmin Cho, M.Sc., RPTU Kaiserslautern Thesis: Cloth-Human-Attribute Guided Virtual Try-On Network.
• Shazib Rauf Satti, M.Sc., RPTU Kaiserslautern Thesis: Unsupervised 3D Pose Estimation using Spatial-Temporal Transformer with Temporal and Biomechanical Constraints.
• Jaspreet Singh, M.Sc., RPTU Kaiserslautern Thesis: Sensor based hand gesture recognition.
• Dennis Schneider, M.Sc., RPTU Kaiserslautern Thesis: Enhancing Video Captioning Models with Motion-Grounded Synthetic Data Augmentation.
• Sana Parveen, M.Sc., RPTU Kaiserslautern Thesis: Openvocabulary 3D motion generation from text for ASL.

Organiser Experience

• Program Commitee , Multi- and Cross-Modal Information for Enhanced Pattern Recognition 2024(MCMI 2024)

Technical Skills

• Languages: Python, JavaScript / TypeScript, C++.
• 3D Tools / Frameworks: Blender, Unity3D, Pytorch3D, PyBullet, Three.js.
• AI Tools / Frameworks: Tensorflow, Tensorflow.js, Pytorch, Pytorch geometric, Keras.
• AI Models: MLP, CNN, LSTM, Transformer, GNN, PINN, Quantum neural network, Multimodal learning, Multitask learning, Contrastive learning, Supervised learning, Self-supervised learning, LLM cross-modal learning, Simulation assisted learning, Generative AI, Foundational model.
• Other: Git, GitLab, CUDA, Docker.

Language Skills

• English: Fluent
• German: Intermediate
• Hindi: Fluent
• Odia: Native

Journal Proceedings

• A comprehensive evaluation of marker-based, markerless methods for loose garment scenarios in varying camera configurations
  Lala Shakti Swarup Ray, Bo Zhou, Sungho Suh, and Paul Lukowicz. Frontiers in Computer Science, vol. 6, p. 1 379 925, 2024

• Analysis of Attention Level of Human Body in Different Forms
  Ankit Anand, Lala Shakti Swarup Ray, Ramesh K. Sahoo, and Srinivas Sethi. Emerging Technologies in Data Mining and Information Security IEMIS 2018, Volume 3 (2018): 23-32.

Conference Proceedings

• iMove: Exploring bio-impedance sensing for fitness activity recognition
  Mengxi Liu, Vitor Fortes Rey, Yu Zhang, Lala Shakti Swarup Ray, Bo Zhou, Paul Lukowicz. 2024 IEEE International Conference on Pervasive Computing and Communications (PerCom), Biarritz, France, 2024, pp. 194-205.

• A novel local-global feature fusion framework for body-weight exercise recognition with pressure mapping sensors
  Davinder Pal Singh, Lala Shakti Swarup Ray, Bo Zhou, Sungho Suh, Paul Lukowicz. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, Republic of, 2024, pp. 6375-6379.

• Clothfit: Cloth-human-attribute guided virtual try-on network using 3d simulated dataset
  Yunmin Cho, Lala Shakti Swarup Ray, Kundan Sai Prabhu Thota, Sungho Suh, Paul Lukowicz. 2023 IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia, 2023, pp. 3484-3488.

• Selecting the motion ground truth for loose-fitting wearables: Benchmarking optical mocap methods
  Lala Shakti Swarup Ray, Bo Zhou, Sungho Suh, Paul Lukowicz. 2023 ACM International Symposium on Wearable Computers (ISWC '23). Association for Computing Machinery, New York, NY, USA, 27-32.

• PressureTransferNet: Human Attribute Guided Dynamic Ground Pressure Profile Transfer using 3D simulated Pressure Maps
  Lala Shakti Swarup Ray, Vitor Fortes Rey, Bo Zhou, Sungho Suh, Paul Lukowicz. 2023 Activity and Behavior Computing (ABC 2023), Kaiserslautern, Germany.

• Mocapose: Motion capturing with textile-integrated capacitive sensors in loose-fitting smart garments
  Bo Zhou, Daniel Geissler, Marc Faulhaber, Clara Elisabeth Gleiss, Esther Friederike Zahn, Lala Shakti Swarup Ray, David Gamarra, Vitor Fortes Rey, Sungho Suh, Sizhen Bian, Gesche Joost, and Paul Lukowicz. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 7, 1, Article 41.

Adjunct Proceedings

• Text me the data: Generating Ground Pressure Sequence from Textual Descriptions for HAR
  Lala Shakti Swarup Ray Bo Zhou, Sungho Suh, Lars Krupp, Vitor Fortes Rey, Paul Lukowicz. Frontiers in Computer Science, vol. 6, p. 1 379 925, 2024

• Moca’collection: Normalizing dynamic textile geometry with capacitive sensing in design centric wearables
  Lala Shakti Swarup Ray Sungho Suh, Bo Zhou, and Paul Lukowicz.

• Capafoldable: Self-tracking foldable smart textiles with capacitive sensing
  Lala Shakti Swarup Ray, Sungho Suh, Bo Zhou, and Paul Lukowicz.

• Pressim: An end-to-end framework for dynamic ground pressure profile generation from monocular videos using physics-based 3d simulation
  Lala Shakti Swarup Ray Sungho Suh, Bo Zhou, and Paul Lukowicz.

• Web application to generate synthetic geometric camera calibration dataset for stereo cameras
  Lala Shakti Swarup Ray Sungho Suh, Bo Zhou, and Paul Lukowicz.

Industry collaborations

• Deihl GmbH: Generating Sythetic dataset for training a flight PoV object intruder detection & tracking model.
• Parts GmbH: Training a PINN netowrk to gnerate Flow of injected fluids for different mold shapes.

Proceedings

• Best WIP Runners-up Award: Generating Sythetic dataset for training a flight PoV object intruder detection & tracking model.
• Best Paper Award: Training a PINN netowrk to gnerate Flow of injected fluids for different mold shapes.
• Excellent Paper Award: Training a PINN netowrk to gnerate Flow of injected fluids for different mold shapes.
• Best Paper Award: Training a PINN netowrk to gnerate Flow of injected fluids for different mold shapes.

Challanges & Hackathons

Others

Get in touch

For collaborations, please feel free to contact.