Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85210
Title: | 基於人體步態序列之性別分類與年齡估計方法的相關研究 A Study of Gait-Based Gender Classification and Age Estimation Using Pose Sequences |
Authors: | Jih-Hsiang Yang 楊日翔 |
Advisor: | 吳家麟(Ja-Ling Wu) |
Keyword: | 人類步態,姿態序列,性別分類,年齡估計,圖神經網路,多任務學習, Human Gait,Pose Sequences,Gender Classification,Age Estimation,Graph Neural Networks,Multi-Task Learning, |
Publication Year : | 2021 |
Degree: | 碩士 |
Abstract: | 本篇論文將時空圖卷積網路應用在基於人體姿態序列的步態資料集,進而進行性別分類和年齡估計,這兩項工作即時使用人眼作為判斷依據,仍然可能產生很大的誤差。透過一連串實驗,我們發現,適當的結合多任務學習和資料擴增的方法,可以進一步提升性別分類和年齡估計的正確率。 This work presents a Spatial-Temporal Graph Convolutional Network (ST-GCN) for gender classification and age estimation using pose sequences of gait, which may be hard to comprehend by human eyes. A series of experiments show that an appropriate combination of multi-task learning and data augmentation does improve the expected performances. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85210 |
DOI: | 10.6342/NTU202201964 |
Fulltext Rights: | 同意授權(限校園內公開) |
metadata.dc.date.embargo-lift: | 2022-09-06 |
Appears in Collections: | 資訊工程學系 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
U0001-0208202211510900.pdf Access limited in NTU ip range | 1.26 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.