FlowNetU: Accurate Uncertainty Estimation of Optical Flow for Video Object Detection
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kang, Jun-Gu | - |
dc.contributor.author | Roh, Si-Dong | - |
dc.contributor.author | Chung, Ki-Seok | - |
dc.date.accessioned | 2022-07-06T12:12:18Z | - |
dc.date.available | 2022-07-06T12:12:18Z | - |
dc.date.created | 2022-04-06 | - |
dc.date.issued | 2021-09 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/140956 | - |
dc.description.abstract | Video object detection (VOD) is a challenging task to resolve ambiguities owing to various issues such as motion blur and occlusion. Although various types of ambiguities will take place per pixels in an image, flow fields make equal contributions for VOD across the image. This may increase false positive (FP) results. In this paper, we propose a method that utilizes motion uncertainty for VOD. The trained optical flow estimation model helps detector to suppress unreliable flow fields in order to avoid misaggregation which causes mislocalization. Our proposed method improves mean average precision by 1.27% and decreases the FP rate by 10.59%. This verifies that utilizing motion uncertainty for video recognition tasks is very effective. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Association for Computing Machinery | - |
dc.title | FlowNetU: Accurate Uncertainty Estimation of Optical Flow for Video Object Detection | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Chung, Ki-Seok | - |
dc.identifier.doi | 10.1145/3488933.3489027 | - |
dc.identifier.scopusid | 2-s2.0-85125870551 | - |
dc.identifier.bibliographicCitation | ACM International Conference Proceeding Series, pp.36 - 41 | - |
dc.relation.isPartOf | ACM International Conference Proceeding Series | - |
dc.citation.title | ACM International Conference Proceeding Series | - |
dc.citation.startPage | 36 | - |
dc.citation.endPage | 41 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | Motion compensation | - |
dc.subject.keywordPlus | Object detection | - |
dc.subject.keywordPlus | Object recognition | - |
dc.subject.keywordPlus | Optical flows | - |
dc.subject.keywordPlus | Video on demand | - |
dc.subject.keywordPlus | Flow fields | - |
dc.subject.keywordPlus | Estimation models | - |
dc.subject.keywordPlus | False positive | - |
dc.subject.keywordPlus | Image flows | - |
dc.subject.keywordPlus | Mislocalization | - |
dc.subject.keywordPlus | Motion blur | - |
dc.subject.keywordPlus | Motion uncertainty | - |
dc.subject.keywordPlus | Optical flow estimation | - |
dc.subject.keywordPlus | Uncertainty | - |
dc.subject.keywordPlus | Uncertainty estimation | - |
dc.subject.keywordPlus | Video object detections | - |
dc.subject.keywordAuthor | Optical flow estimation | - |
dc.subject.keywordAuthor | Uncertainty | - |
dc.subject.keywordAuthor | Video object detection | - |
dc.identifier.url | https://dl.acm.org/doi/10.1145/3488933.3489027 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.