MARC보기
LDR02336nmm uu200421 4500
001000000331816
00520240805165427
008181129s2018 |||||||||||||||||c||eng d
020 ▼a 9780438019713
035 ▼a (MiAaPQ)AAI10825719
035 ▼a (MiAaPQ)ucla:16805
040 ▼a MiAaPQ ▼c MiAaPQ ▼d 248032
0820 ▼a 004
1001 ▼a Qi, Hang.
24512 ▼a A Joint Parsing System for Visual Scene Understanding.
260 ▼a [S.l.] : ▼b University of California, Los Angeles., ▼c 2018
260 1 ▼a Ann Arbor : ▼b ProQuest Dissertations & Theses, ▼c 2018
300 ▼a 93 p.
500 ▼a Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.
500 ▼a Adviser: Song-Chun Zhu.
5021 ▼a Thesis (Ph.D.)--University of California, Los Angeles, 2018.
520 ▼a The computer vision community has been long focusing on classic tasks such as object detection, human attributes classification, action recognition. While the state-of-the-art performance is getting improved every year for a wide range of tasks,
520 ▼a This dissertation contains three main parts.
520 ▼a Firstly, we describe a restricted visual Turing test scenario that evaluates computer vision systems across various tasks with a domain ontology and explicitly tests the grounding of concepts with formal queries. We present a benchmark for evalu
520 ▼a Secondly, we propose a scalable system which leverages off-the-shelf computer vision modules to parse cross-view videos jointly. The system defines a unified knowledge representation for information sharing and is extendable to new tasks and dom
520 ▼a Thirdly, we discuss a principled method to construct parse graph knowledge bases that retains rich structures and grounding details. By casting questions into graph fragments, we present a graph-matching based question-answering system that retr
590 ▼a School code: 0031.
650 4 ▼a Computer science.
690 ▼a 0984
71020 ▼a University of California, Los Angeles. ▼b Computer Science 0201.
7730 ▼t Dissertation Abstracts International ▼g 79-10B(E).
773 ▼t Dissertation Abstract International
790 ▼a 0031
791 ▼a Ph.D.
792 ▼a 2018
793 ▼a English
85640 ▼u http://www.riss.kr/pdu/ddodLink.do?id=T14998800 ▼n KERIS
980 ▼a 201812 ▼f 2019
990 ▼a 관리자