Talks: Gustave Tuck Lecture Theatre, Main UCL Building
Coffee breaks and lunch: South Cloisters, Main UCL Building
10:30 | Registration |
11:00 | Invited speaker: Yvonne Rogers Session Chair: Mirco Musolesi
Bio: Yvonne Rogers is a Professor of Interaction Design, the director of UCLIC and a deputy head of the Computer Science department at University College London. Her research interests are in the areas of interaction design, human-computer interaction and ubiquitous computing. A central theme of her work is concerned with designing interactive technologies that augment humans. She was awarded the ACM SIGCHI Lifetime Achievement Research Award in 2022, “presented to individuals for outstanding contributions to the study of human-computer interaction.” In the same year, she was elected as a fellow of the Royal Society as “one of the leaders who created the field of Ubiquitous Computing”. |
12:00 | Paper session 1: Efficient and real-time on-device ML Session Chair: Alastair Beresford Xinchi Qiu, Javier Fernandez-Marques, Pedro Gusmao, Yan Gao, Titouan Parcollet and Nicholas Lane. ZeroFL: Efficient On-device Training for Federated Learning with Local Sparsity Lei Xun, Bashir Al-Hashimi, Jonathon Hare and Geoff Merrett Dynamic DNNs meet Runtime Resource Management on Mobile and Embedded Platforms Edgar Liberis and Nicholas D. Lane Differentiable Network Pruning to Enable Smart Applications Young D. Kwon, Jagmohan Chauhan and Cecilia Mascolo |
13:00 | Lunch |
13:45 | Invited speaker: Alex Rogers Session Chair: Christos Efstratiou Title: Prototyping hardware at scale: lessons learned from Joulo, AudioMoth and SnapperGPS Bio: Alex Rogers is a Professor of Computer Science at the University of Oxford where his research applies artificial intelligence and machine learning within physical sensor systems to address real-world problems focusing on sustainability. His work has addressed future energy systems, such as the smart grid, citizen science platforms, and most recently environmental monitoring through the development of low-cost conservation technology. |
14:45 | Paper session 2: Sensing and mobile health Session Chair: George Roussos Catherine Tong, Jinchen Ge and Nicholas Lane Zero-Shot Learning for IMU-Based Activity Recognition Using Video Embeddings Tong Xia, Jing Han, Lorena Qendro and Cecilia Mascolo Evidential Deep Learning for Uncertainty-Aware Mobile Health Yu Wu, Dimitris Spathis, Ignacio Perez-Pozuelo, Tomas Gonzales, Nick Wareham, Soren Brage and Cecilia Mascolo Weak Label Learning for Wearable Cardio-respiratory Fitness Prediction |
15:30 | Coffee break |
16:00 | Invited speaker: Bozidar Radunovic Session Chair: Mahesh Marina Title: 5G: what is it and why should we care? Bio: Bozidar Radunovic is a Principal Researcher in the Azure for Operators Research, in Cambridge, UK. His research interests are in designing and building next generation 5G infrastructure on cloud and edge. He has performed research on computer systems and algorithms with particular interest in access networks, virtualization and wireless communications. Bozidar received his PhD in technical sciences from EPFL. |
17:00 | Reception (in Haldane Room, Main UCL Building) |
Talks: Gustave Tuck Lecture Theatre, Main UCL Building
Coffee breaks and lunch: North Cloisters, Main UCL Building
09:00 | Invited Speaker: Kate Farrahi Session Chair: Nic Lane Title: Machine learning for mobile health and digital epidemics Bio: Kate Farrahi is an assistant professor at the University of Southampton working in the vision, learning and control (VLC) group. The focus of her research is on machine learning, particularly deep learning often applied to health-related applications. She is interested in developing machine learning techniques to address novel sensor-driven healthcare problems, including natural language processing and vision related applications such as medical imaging and contactless vitals measurements. She obtained her PhD in Computer Science from the Swiss Federal Institute of Technology in Lausanne (EPFL), Switzerland. |
10:00 | Paper session 3: privacy as the first-class citizen Session Chair: Chris Xiaoxuan Lu Luis Adán Saavedra del Toro, Alastair R. Beresford, Hridoy S. Dutta and Alice Hutchings. Analysis of Modded Android Apps and Marketplaces Kai Xu. Deep Generative Models for Synthesizing Mobile Traffic Data Yan Gao, Titouan Parcollet, Salah Zaiem, Javier Fernandez-Marques, Pedro P. B. de Gusmao, Daniel J. Beutel and Nicholas Lane. End-to-End Speech Recognition from Federated Acoustic Models |
11:00 | Coffee break |
11:30 | Invited speaker: Hugo Spiers Session Chair: Cecilia Mascolo Title: Using a mobile app to study world-wide cognition Bio: Hugo Spiers is Professor of Cognitive Neuroscience in the Department of Experimental Psychology and a Fellow of the Royal Institute of Navigation. His research explores how our brain constructs representations of the world and uses them to recall the past, navigate the present and imagine the future. Current research from his group use a range of methods including mass online testing with mobile apps, brain imaging, neuropsychological testing, virtual reality and single cell recording to understand brain function and spatial cognition. |
12:30 | Lunch |
13:30 | Paper session 4: Vision and mobility Session Chair: Kate Farrahi Fangqiang Ding and Chris Xiaoxuan Lu. Self-Supervised Learning of 4D Automotive Radar Scene Flow Estimation Qiyue Xia and Chris Xiaoxuan Lu. Robust Human Detection under Visual Degradation with Low-cost mmWave radars and thermal Cameras Nicola Saccomanno, Andrea Brunello and Angelo Montanari. Fraser McLean, Leyang Xue, Chris Xiaoxuan Lu and Mahesh K. Marina. Towards Edge-assisted Real-time 3D Segmentation of Large Scale LIDAR Point Clouds |
14:30 | Invited speaker: Fahim Kawsar Session Chair: Mirco Musolesi Title: Learning Challenges in Designing Multi-Device Experiences
|
15:30 | Community discussion and concluding remarks |
16:00 | End |