자료유형 | 학위논문 |
---|---|
서명/저자사항 | Video Understanding with Deep Networks. |
개인저자 | Ng, Joe Yue-Hei. |
단체저자명 | University of Maryland, College Park. Computer Science. |
발행사항 | [S.l.]: University of Maryland, College Park., 2018. |
발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2018. |
형태사항 | 130 p. |
기본자료 저록 | Dissertation Abstracts International 79-12B(E). Dissertation Abstract International |
ISBN | 9780438154162 |
학위논문주기 | Thesis (Ph.D.)--University of Maryland, College Park, 2018. |
일반주기 |
Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
Adviser: Larry S. Davis. |
요약 | Video understanding is one of the fundamental problems in computer vision. Videos provide more information to the image recognition task by adding a temporal component through which motion and other information can be additionally used. Encourag |
요약 | To effectively utilize deep networks, we need a comprehensive understanding of convolutional neural networks. We first study the network on the domain of image retrieval. We show that for instance-level image retrieval, lower layers often perfor |
요약 | We then propose and evaluate several deep neural network architectures to combine image information across a video over longer time periods than previously attempted. We propose two methods capable of handling full length videos. The first metho |
요약 | Next, we propose a multitask learning model ActionFlowNet to train a single stream network directly from raw pixels to jointly estimate optical flow while recognizing actions with convolutional neural networks, capturing both appearance and moti |
요약 | While recent deep models for videos show improvement by incorporating optical flow or aggregating high-level appearance across frames, they focus on modeling either the long-term temporal relations or short-term motion. We propose Temporal Diffe |
일반주제명 | Computer science. Artificial intelligence. |
언어 | 영어 |
바로가기 |
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |