6 papers
Putting Registers to Work: Task Registers for Token Pruning in Vision Transformers
Hongsen Cao, Mona Jaber, Shanxin Yuan +1
Token-pruning policies are usually designed for a single recognition pipeline, but pretrained Vision Transformers are reused across tasks with different spatial demands. We ask whi…
A low complexity contextual stacked ensemble-learning approach for pedestrian intent prediction
Chia-Yen Chiang, Yasmin Fathy, Gregory Slabaugh +1
Walking as a form of active travel is essential in promoting sustainable transport. It is thus crucial to accurately predict pedestrian crossing intention and avoid collisions, esp…
Reducing AoI and Improving Throughput for NOMA-assisted SGF Systems: A Hierarchical Learning Approach
Yuqin Liu, Mona Jaber, Yan Liu +1
A non-orthogonal multiple access (NOMA) assisted semi-grant-free (SGF) framework is proposed to enable channel access for grant-free users (GFUs) by using residual resources from g…
Intelligent Travel Activity Monitoring: Generalized Distributed Acoustic Sensing Approaches
Ruikang Zhong, Chia-Yen Chiang, Mona Jaber +2
Obtaining data on active travel activities such as walking, jogging, and cycling is important for refining sustainable transportation systems (STS). Effectively monitoring these ac…
A Survey on AI-driven Energy Optimisation in Terrestrial Next Generation Radio Access Networks
Kishan Sthankiya, Nagham Saeed, Greg McSorley +2
This survey uncovers the tension between AI techniques designed for energy saving in mobile networks and the energy demands those same techniques create. We compare modeling approa…
AI-Ready Energy Modelling for Next Generation RAN
Kishan Sthankiya, Keith Briggs, Mona Jaber +1
Recent sustainability drives place energy-consumption metrics in centre-stage for the design of future radio access networks (RAN). At the same time, optimising the trade-off betwe…