Human activity recognition is typically addressed by detecting key concepts like global and local motion, features related to object classes present in the scene, as well as features related to the global context.
No spatial coherence is forced on the glimpse locations, which gives the module liberty to explore different points at each frame and better optimize the process of scrutinizing visual information.
We propose a simple, yet effective, method for the temporal detection of activities in temporally untrimmed videos with the help of untrimmed classification.
Inspired by this, we conduct an extensive set of experiments that analyze different sample generation processes and validation protocols to indicate the vulnerable points in human activity recognition based on wearable sensor data.
Time Series Classification (TSC) problems are encountered in many real life data mining tasks ranging from medicine and security to human activity recognition and food safety.
To the best of our knowledge, we are the first to propose the use of deep learning for computing topological features directly from data.
We conclude that Human Activity Recognition systems should be evaluated by Subject Cross Validation, and that overlapping windows are not worth their extra computational cost.
We propose to use the various slices (such as $x-y$, $x-t$, and $y-t$) of the DVS video as a feature map for HAR and denote them as Motion Maps.
Sparsity learning with known grouping structure has received considerable attention due to wide modern applications in high-dimensional data analysis.