DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Changick | - |
dc.contributor.advisor | 김창익 | - |
dc.contributor.author | Kim, Youngeun | - |
dc.date.accessioned | 2021-05-13T19:33:06Z | - |
dc.date.available | 2021-05-13T19:33:06Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=911319&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/284710 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2020.2,[v, 50 p. :] | - |
dc.description.abstract | Most video person re-identification (re-ID) methods are mainly based on supervised learning, which requires cross-camera ID labeling. Since the cost of labeling increases dramatically as the number of cameras increases, it is difficult to apply the re-identification algorithm to a large camera network. In this paper, we address the scalability issue by presenting deep representation learning without ID information across multiple cameras. Technically, we train neural networks to generate both ID-discriminative and camera-invariant features. To achieve the ID discrimination ability of the embedding features, we maximize feature distances between different person IDs within a camera by using a metric learning approach. At the same time, considering each camera as a different domain, we apply adversarial learning across multiple camera domains for generating camera-invariant features. We also propose a part-aware adaptation module, which effectively performs multi-camera domain invariant feature learning in different spatial regions. We carry out comprehensive experiments on three public re-ID datasets (i.e., PRID-2011, iLIDS-VID, and MARS). Our method outperforms state-of-the-art methods by a large margin of about 20\% in terms of rank-1 accuracy on the large-scale MARS dataset. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | deep learning▼adomain adaptation▼aperson re-identification▼aunsupervised learning▼aadversarial learning | - |
dc.subject | 딥러닝▼a도메인 적응▼a사람 재식별▼a비지도 학습▼a경쟁적 학습 | - |
dc.title | Learning to align multi-camera domains using part-aware clustering for unsupervised video person re-identification | - |
dc.title.alternative | 비지도 비디오 사람 재식별을 위한 부위 인식 군집화를 이용한 다중 카메라 도메인 정렬 방법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 김영은 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.