Human Movement Datasets: An Interdisciplinary Scoping Review

Abstract

Movement dataset reviews exist but are limited in coverage, both in terms of size and research discipline. While topic-specific reviews clearly have their merit, it is critical to have a comprehensive overview based on a systematic survey across disciplines. This enables higher visibility of datasets available to the research communities and can foster interdisciplinary collaborations. We present a catalogue of 704 open datasets described by 10 variables that can be valuable to researchers searching for secondary data: name and reference, creation purpose, data type, annotations, source, population groups, ordinal size of people captured simultaneously, URL, motion capture sensor, and funders. The catalogue is available in the supplementary materials. We provide an analysis of the datasets and further review them under the themes of human diversity, ecological validity, and data recorded. The resulting 12-dimension framework can guide researchers in planning the creation of open movement datasets. This work has been the interdisciplinary effort of researchers across affective computing, clinical psychology, disability innovation, ethnomusicology, human-computer interaction, machine learning, music cognition, music computing, and movement neuroscience.

Sensing behavior change in chronic pain: A scoping review of sensor technology for use in daily life

“…Given the effort and expense of collecting these data, data sharing is important. 68 Nor were issues of data storage, security, and privacy of identifiable data much discussed. We have not addressed here technological monitoring of individuals' behavior, even of their physiology, with or without consent, as instituted for benign reasons to detect lack of motion in homes of elderly people living alone.…”

Intelligent Video Analytics for Human Action Recognition: The State of Knowledge

“…Numerous datasets are available for benchmarking and comparing human action recognition methods [244]. The most up-to-date paper [245], published in May of 2022, presents an excellent vast summary with a catalog of the 704 existing multimodal human movement datasets available for researchers prepared in labs and the real world. Table 9 indicates the most popular datasets from real-life scenarios considered when selecting the most representative datasets to evaluate the most promising methods.…”

Movement Representation Learning for Pain Level Classification

“…H UMAN movement modelling is an important topic relevant across several disciplines and pivotal for a wide variety of applications [1]. While areas such as action/activity recognition have benefited from extensive interest and a large number of (open) datasets, higher order problems like affect recognition lag behind [1].…”

“…H UMAN movement modelling is an important topic relevant across several disciplines and pivotal for a wide variety of applications [1]. While areas such as action/activity recognition have benefited from extensive interest and a large number of (open) datasets, higher order problems like affect recognition lag behind [1]. For automatic recognition of affective experience from movement, this is despite consistent findings and discussions on the role of the body in experience and expression [2], [3].…”