Program | Friday, March 15
8:45 – 9:00 | Opening
9:00 – 10:00 | Keynote: Resource Optimized Human Activity Recognition | Prof. Paul Lukowicz
10:30 – 12:00 | Augmented Reality and Edge Computing
- MobileARLoc: On-device Robust Absolute Localisation for Pervasive Markerless Mobile AR | Changkun Liu (The Hong Kong University of Science and Technology, Hong Kong); Yukun Zhao (HK University of Science and Technology, Hong Kong); Tristan Braud (The Hong Kong University of Science and Technology, Hong Kong)
- Active Inference on the Edge: A Design Study | Boris Sedlak, Victor Casamayor Pujol, Praveen Kumar Donta and Schahram Dustdar (Vienna University of Technology, Austria)
- A Genetic Tuner for Fixed-skeleton TinyML Models | Swarnava Dey (TCS Research & Tata Consultancy Service Limited, India); Soma Dasgupta (Tata Consultancy Service Limited, India)
13:30 – 15:00 | Advanced Neural Networks and Machine Learning Techniques
- A Bio-inspired Low-power Hybrid Analog/Digital Spiking Neural Networks for Pervasive Smart Cameras | Yung-Ting Hsieh and Dario Pompili (Rutgers University, USA)
- Painting the Starry Night using XiNets | Alberto Ancilotto (FBK, Italy); Elisabetta Farella (Fondazione Bruno Kessler, Italy)
- An empirical evaluation of tinyML architectures for Class-Incremental Continual Learning | Matteo Tremonti and Davide Dalle Pezze (University of Padova, Italy); Francesco Paissan and Elisabetta Farella (Fondazione Bruno Kessler, Italy); Gian Antonio Susto (University of Padova, Italy)
15:30 – 17:00 | Federated Learning and Multi-device Learning Environments
- Exploring Activity Recognition in Multi-device Environments using Hierarchical Federated Learning | Moid Sandhu (Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australia); David Silvera-Tawil, Wei Lu and Paulo Borges (CSIRO, Australia); Brano Kusy (Team Leader, Data61, CSIRO, Australia)
- Mitigating System Bias in Resource Constrained Asynchronous Federated Learning Systems | Jikun Gao (Toshiba Europe Ltd., United Kingdom (Great Britain)); Ioannis Mavromatis (Digital Catapult, United Kingdom (Great Britain)); Peizheng Li (Toshiba Europe Ltd., United Kingdom (Great Britain)); Pietro Carnelli (Toshiba Research Europe, United Kingdom (Great Britain)); Aftab Khan (Toshiba Europe Ltd., United Kingdom (Great Britain))
- FlowPrecision: Advancing FPGA-Based Real-Time Fluid Flow Estimation with Linear Quantization | Tianheng Ling, Julian Hoever, Chao Qian and Gregor Schiele (University of Duisburg-Essen, Germany)
17:00 – 18:00 | Human Behavior and Activity Recognition
- Closing the Gap in Human Behavior Analysis: A Pipeline for Synthesizing Trimodal Data | Christian Stippel, Thomas Heitzinger, Rafael Sterzinger and Martin Kampel (TU Wien, Austria)
- Complexity-aware Features Selection for Wrist-worn Human Activity Recognition | Susanna Peretti, Chiara Contoli and Emanuele Lattanzi (University of Urbino, Italy)