An Intelligent Action Recognition System to assess Cognitive Behavior for Executive Function Disorder

Babu, Ashwin Ramesh; Zakizadeh, Mohammad; Brady, James; Calderon, Diane; Makedon, Fillia

doi:10.1109/coase.2019.8843199

Cited by 10 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The third dataset which for simplicity is called Ball-Drop (Ball-Drop-to-the-Beat) is based on one of tasks designed for ATEC system (Activate Test of Embodied Cognition) to assess both audio and visual cue processing of children while performing upper-body movements. The ATEC is an assessment test designed to measure executive functions in children through physically and cognitively demanding tasks [7,3].…”

Section: Datasetsmentioning

confidence: 99%

“…While most of the research in application of selfsupervised learning in computer vision is concentrated on still images, the focus of this paper is human activity recognition in videos. This work is motivated by the real-world ATEC (Activate Test of Embodied Cognition) system [7,3], which assesses executive function in children through physically and cognitively demanding tasks. The system requires manually labeling hundred of hours of videos by experts.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Supervised Human Activity Recognition by Augmenting Generative Adversarial Networks

Zadeh,

Babu,

Jaiswal

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

This article proposes a novel approach for augmenting generative adversarial network (GAN) with a selfsupervised task in order to improve its ability for encoding video representations that are useful in downstream tasks such as human activity recognition. In the proposed method, input video frames are randomly transformed by different spatial transformations, such as rotation, translation and shearing or temporal transformations such as shuffling temporal order of frames. Then discriminator is encouraged to predict the applied transformation by introducing an auxiliary loss. Subsequently, results prove superiority of the proposed method over baseline methods for providing a useful representation of videos used in human activity recognition performed on datasets such as KTH, UCF101 and Ball-Drop. Ball-Drop dataset is a specifically designed dataset for measuring executive functions in children through physically and cognitively demanding tasks. Using features from proposed method instead of baseline methods caused the top-1 classification accuracy to increase by more then 4%. Moreover, ablation study was performed to investigate the contribution of different transformations on downstream task.

show abstract

Section: Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%