DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kweon, In So | - |
dc.contributor.advisor | 권인소 | - |
dc.contributor.author | Jang, Youngjoon | - |
dc.date.accessioned | 2023-06-22T19:32:00Z | - |
dc.date.available | 2023-06-22T19:32:00Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=997738&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/308326 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 미래자동차학제전공, 2022.2,[vii, 45 p. :] | - |
dc.description.abstract | In this thesis, two major problems are pointed out through the structural analysis of continuous sign language recognition (CSLR) datasets: (1) Since constructing CSLR dataset is expensive, additional annotations (pose, optical flow and frame-level gloss labels, etc.) are difficult. (2) Various background environments are not considered in the dataset construction process. From the first problem, we propose a lightweight backbone network that can independently extract non-manual (gaze direction, facial expressions and lip patterns) and manual (hand shape, movement) expression features without any additional annotations, and a method to generate more accurate pseudo-labels by combining the model output with the ground truth gloss sequence. In addition, from the second issue, we first construct a sign language dataset including various background scenes and further propose a disentanglement module to effectively distinguish a signer and a background from a sign video. We verify that the proposed methodologies have a great effect on overcoming the limitations caused by the existing CSLR dataset based on various quantitative and qualitative evaluations. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.title | Learning methodology according to characteristics of continuous sign language recognition dataset | - |
dc.title.alternative | 연속 수어 인식 데이터셋 특징에 따른 학습 방법론 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :미래자동차학제전공, | - |
dc.contributor.alternativeauthor | 장영준 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.