通过多尺度窗口建模，提升动作识别的时序连贯性

Despite recognized limitations in modeling long-range temporal dependencies, Human Activity Recognition (HAR) has traditionally relied on a sliding window approach to segment labeled datasets. Deep learning models like the DeepConvLSTM typically classify each window independently, restricting learnable temporal context to within-window information and producing fragmented, temporally incoherent activity timelines. To address this constraint, we propose DeepConvContext, a multi-scale time series classification framework for HAR. Drawing inspiration from the vision-based Temporal Action Localization community, DeepConvContext models both intra- and inter-window temporal patterns separately by processing sequences of time-ordered windows. Across six widely-used HAR benchmarks, DeepConvContext achieves an average 5% improvement in F1-score and up to 18-point improvement in mAP over related approaches, while achieving latency and throughput comparable to prior methods that extend temporal context through hidden state propagation across batches. Our quantitative and qualitative analysis underline the importance of inter-window learning and show how it produces more coherent activity segments even in online prediction scenarios. Code to reproduce our experiments is publicly available via www.github.com/mariusbock/deepconvcontext.