1 resultado para CASCADE DECAYS
em Massachusetts Institute of Technology
Filtro por publicador
- JISC Information Environment Repository (1)
- Aberdeen University (3)
- Academic Archive On-line (Stockholm University; Sweden) (1)
- Adam Mickiewicz University Repository (1)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (1)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (2)
- Aquatic Commons (7)
- ArchiMeD - Elektronische Publikationen der Universität Mainz - Alemanha (5)
- Archimer: Archive de l'Institut francais de recherche pour l'exploitation de la mer (1)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (9)
- Aston University Research Archive (17)
- B-Digital - Universidade Fernando Pessoa - Portugal (1)
- Biblioteca de Teses e Dissertações da USP (1)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (7)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (3)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (5)
- Bioline International (1)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (62)
- Boston University Digital Common (6)
- Bulgarian Digital Mathematics Library at IMI-BAS (2)
- CaltechTHESIS (31)
- Cambridge University Engineering Department Publications Database (80)
- CentAUR: Central Archive University of Reading - UK (17)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (187)
- Cochin University of Science & Technology (CUSAT), India (1)
- CORA - Cork Open Research Archive - University College Cork - Ireland (7)
- Dalarna University College Electronic Archive (1)
- Deakin Research Online - Australia (14)
- DI-fusion - The institutional repository of Université Libre de Bruxelles (10)
- Digital Archives@Colby (2)
- Digital Commons at Florida International University (3)
- Digital Knowledge Repository of Central Drug Research Institute (1)
- Diposit Digital de la UB - Universidade de Barcelona (2)
- Doria (National Library of Finland DSpace Services) - National Library of Finland, Finland (1)
- DRUM (Digital Repository at the University of Maryland) (1)
- Duke University (20)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (4)
- Gallica, Bibliotheque Numerique - Bibliothèque nationale de France (French National Library) (BnF), France (2)
- Glasgow Theses Service (1)
- Greenwich Academic Literature Archive - UK (2)
- Helda - Digital Repository of University of Helsinki (65)
- Indian Institute of Science - Bangalore - Índia (113)
- Instituto Gulbenkian de Ciência (1)
- Iowa Publications Online (IPO) - State Library, State of Iowa (Iowa), United States (1)
- Massachusetts Institute of Technology (1)
- National Center for Biotechnology Information - NCBI (23)
- Plymouth Marine Science Electronic Archive (PlyMSEA) (2)
- Publishing Network for Geoscientific & Environmental Data (2)
- QSpace: Queen's University - Canada (1)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (87)
- Queensland University of Technology - ePrints Archive (74)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (68)
- Universidad Politécnica de Madrid (5)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (1)
- Université de Montréal (1)
- Université de Montréal, Canada (1)
- University of Michigan (3)
- University of Queensland eSpace - Australia (5)
- University of Washington (1)
Resumo:
We seek to both detect and segment objects in images. To exploit both local image data as well as contextual information, we introduce Boosted Random Fields (BRFs), which uses Boosting to learn the graph structure and local evidence of a conditional random field (CRF). The graph structure is learned by assembling graph fragments in an additive model. The connections between individual pixels are not very informative, but by using dense graphs, we can pool information from large regions of the image; dense models also support efficient inference. We show how contextual information from other objects can improve detection performance, both in terms of accuracy and speed, by using a computational cascade. We apply our system to detect stuff and things in office and street scenes.