A Personalized Video-Based Hand Taxonomy: Application for Individuals with Spinal Cord Injury
Not on the map. Why?
Abstract (arXiv)
Hand function is critical for our interactions and quality of life. Spinal cord injuries (SCI) can impair hand function, reducing independence. A comprehensive evaluation of function in home and community settings requires a hand grasp taxonomy for individuals with impaired hand function. Developing such a taxonomy is challenging due to unrepresented grasp types in standard taxonomies, uneven data distribution across injury levels, and limited data. This study aims to automatically identify the dominant distinct hand grasps in egocentric video using semantic clustering. Egocentric video recordings collected in the homes of 19 individual with cervical SCI were used to cluster grasping actions with semantic significance. A deep learning model integrating posture and appearance data was employed to create a personalized hand taxonomy. Quantitative analysis reveals a cluster purity of 67.6% +- 24.2% with with 18.0% +- 21.8% redundancy. Qualitative assessment revealed meaningful clusters in video content. This methodology provides a flexible and effective strategy to analyze hand function in the wild. It offers researchers and clinicians an efficient tool for evaluating hand function, aiding sensitive assessments and tailored intervention plans.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 50 references that are in the map. First posted on arXiv 26 Mar 2024.
Builds on
25 of 50 references.
References · 25
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
- 2020Supervised Contrastive Learningcited by 2,829
- 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
- 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
- 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 675
- 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
- 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
- 2020Understanding Human Hands in Contact at Internet Scalecited by 281
- 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
- 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
- 2020Understanding Self-supervised Learning with Dual Deep Networkscited by 62
- 2022Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspectivecited by 57
13 more
- 2015Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Treecited by 36
- 2017Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoderscited by 32
- 2019Differentiable Deep Clustering with Cluster Size Constraintscited by 22
- 2020Understanding the Decision Boundary of Deep Neural Networks: An Empirical Studycited by 20
- 2017CNN features are also great at unsupervised classificationcited by 9
- 2019Multi-Modal Deep Clustering: Unsupervised Partitioning of Imagescited by 8
- 2019An Effective and Efficient Method for Detecting Hands in Egocentric Videos for Rehabilitation Applicationscited by 7
- 2021Combining pretrained CNN feature extractors to enhance clustering of complex natural imagescited by 7
- 2018Egocentric Video: A New Tool for Capturing Hand Use of Individuals with Spinal Cord Injury at Homecited by 6
- 2021Characterizing and comparing external measures for the assessment of cluster analysis and community detectioncited by 6
- 2015A survey on feature weighting based K-Means algorithmscited by 5
- 2020SA-Net: A deep spectral analysis network for image clusteringcited by 3
- 2022Measuring hand use in the home after cervical spinal cord injury using egocentric videocited by 3
Built on by
Not cited yet.