VI-Net-View-Invariant Quality of Human Movement Assessment

A multimodal dataset of real world mobility activities in Parkinson's disease

Parkinson's disease (PD) is a neurodegenerative disorder characterised by motor symptoms such as gait dysfunction and postural instability. Technological tools to continuously monitor outcomes could capture the hour-by-hour symptom fluctuations of PD. Development of such tools is hampered by the lack of labelled datasets from home settings. To this end, we propose REMAP (REal-world Mobility Activities in Parkinson's disease), a human rater-labelled dataset collected in a home-like setting. It includes people with and without PD doing sit-to-stand transitions and turns in gait. These discrete activities are captured from periods of free-living (unobserved, unstructured) and during clinical assessments. The PD participants withheld their dopaminergic medications for a time (causing increased symptoms), so their activities are labelled as being "on" or "off" medications. Accelerometry from wrist-worn wearables and skeleton pose video data is included. We present an open dataset, where the data is coarsened to reduce re-identifiability, and a controlled dataset available on application which contains more refined data. A use-case for the data to estimate sit-to-stand speed and duration is illustrated.

Gaussian guided frame sequence encoder network for action quality assessment

Can a computer evaluate an athlete’s performance automatically? Many action quality assessment (AQA) methods have been proposed in recent years. Limited by the randomness of video sampling and the simple strategy of model training, the performance of the existing AQA methods can still be further improved. To achieve this goal, a Gaussian guided frame sequence encoder network is proposed in this paper. In the proposed method, the image feature of each video frame is extracted by Resnet model. And then, a frame sequence encoder network is applied to model temporal information and generate action quality feature. Finally, a fully connected network is designed to predict action quality score. To train the proposed method effectively, inspired by the final score calculation rule in Olympic game, Gaussian loss function is employed to compute the error between the predicted score and the label score. The proposed method is implemented on the AQA-7 and MTL–AQA datasets. The experimental results confirm that compared with the state-of-the-art methods, our proposed method achieves the better performance. And detailed ablation experiments are conducted to verify the effectiveness of each component in the module.

HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN

Spatiotemporal representations learned using 3D convolutional neural networks (CNN) are currently used in state-of-the-art approaches for action-related tasks. However, 3D-CNN are notorious for being memory and compute resource intensive as compared with more simple 2D-CNN architectures. We propose to hallucinate spatiotemporal representations from a 3D-CNN teacher with a 2D-CNN student. By requiring the 2D-CNN to predict the future and intuit upcoming activity, it is encouraged to gain a deeper understanding of actions and how they evolve. The hallucination task is treated as an auxiliary task, which can be used with any other action-related task in a multitask learning setting. Thorough experimental evaluation, it is shown that the hallucination task indeed helps improve performance on action recognition, action quality assessment, and dynamic scene recognition tasks. From a practical standpoint, being able to hallucinate spatiotemporal representations without an actual 3D-CNN can enable deployment in resource-constrained scenarios, such as with limited computing power and/or lower bandwidth. We also observed that our hallucination task has utility not only during the training phase, but also during the pre-training phase.