Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Diwei, Yuan, Kun, Muller, Candice, Blanc, Frédéric, Padoy, Nicolas, Seo, Hyewon
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2403.13756
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914972121956352
author Wang, Diwei
Yuan, Kun
Muller, Candice
Blanc, Frédéric
Padoy, Nicolas
Seo, Hyewon
author_facet Wang, Diwei
Yuan, Kun
Muller, Candice
Blanc, Frédéric
Padoy, Nicolas
Seo, Hyewon
contents We present a knowledge augmentation strategy for assessing the diagnostic groups and gait impairment from monocular gait videos. Based on a large-scale pre-trained Vision Language Model (VLM), our model learns and improves visual, textual, and numerical representations of patient gait videos, through a collective learning across three distinct modalities: gait videos, class-specific descriptions, and numerical gait parameters. Our specific contributions are two-fold: First, we adopt a knowledge-aware prompt tuning strategy to utilize the class-specific medical description in guiding the text prompt learning. Second, we integrate the paired gait parameters in the form of numerical texts to enhance the numeracy of the textual representation. Results demonstrate that our model not only significantly outperforms state-of-the-art methods in video-based classification tasks but also adeptly decodes the learned class-specific text features into natural language descriptions using the vocabulary of quantitative gait parameters. The code and the model will be made available at our project page: https://lisqzqng.github.io/GaitAnalysisVLM/.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13756
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Gait Video Analysis in Neurodegenerative Diseases by Knowledge Augmentation in Vision Language Model
Wang, Diwei
Yuan, Kun
Muller, Candice
Blanc, Frédéric
Padoy, Nicolas
Seo, Hyewon
Computer Vision and Pattern Recognition
We present a knowledge augmentation strategy for assessing the diagnostic groups and gait impairment from monocular gait videos. Based on a large-scale pre-trained Vision Language Model (VLM), our model learns and improves visual, textual, and numerical representations of patient gait videos, through a collective learning across three distinct modalities: gait videos, class-specific descriptions, and numerical gait parameters. Our specific contributions are two-fold: First, we adopt a knowledge-aware prompt tuning strategy to utilize the class-specific medical description in guiding the text prompt learning. Second, we integrate the paired gait parameters in the form of numerical texts to enhance the numeracy of the textual representation. Results demonstrate that our model not only significantly outperforms state-of-the-art methods in video-based classification tasks but also adeptly decodes the learned class-specific text features into natural language descriptions using the vocabulary of quantitative gait parameters. The code and the model will be made available at our project page: https://lisqzqng.github.io/GaitAnalysisVLM/.
title Enhancing Gait Video Analysis in Neurodegenerative Diseases by Knowledge Augmentation in Vision Language Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.13756