3 papers
cs.CV2025
-Quant: Towards Learnable Quantization for Low-bit Pattern Recognition
Mishal Fatima, Shashank Agnihotri, Marius Bock +4
Most pattern recognition models are developed on pre-proce\-ssed data. In computer vision, for instance, RGB images processed through image signal processing (ISP) pipelines design…
cs.LG2025
Label Leakage in Federated Inertial-based Human Activity Recognition
Marius Bock, Maximilian Hopp, Kristof Van Laerhoven +1
While prior work has shown that Federated Learning updates can leak sensitive information, label reconstruction attacks, which aim to recover input labels from shared gradients, ha…
cs.LG2025
DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity Recognition
Marius Bock, Michael Moeller, Juergen Gall +1
Despite recognized limitations in modeling long-range temporal dependencies, Human Activity Recognition (HAR) has traditionally relied on a sliding window approach to segment label…