Ir al contenido
Universidad de Chile

Buscador

Facultades U-Cursos Ucampus Mi Uchile Bibliotecas English
MENÚ

Laboratorio PRISMA (Pattern Recognition, Indexing, and Similarity Search for Social Media and Multimodal Analysis)

    Descripción

    PRISMA centra su trabajo de investigación en las áreas de minería de datos, análisis de social media y análisis Web, bases de datos multimedia, reconocimiento de patrones y búsqueda por similitud. Nuestro objetivo principal es doble: 1) desarrollar métodos eficientes y eficaces para la recuperación de información multimedia y 2) extraer conocimiento valioso de datos sociales y multimodales para mejorar el entendimiento humano de grandes colecciones de datos.

    Equipamiento e instrumentos

    • Un servidor Lanix SPINE 1U.
    • Un servidor de disco NAS con aproximadamente 12 Tb de capacidad.
    • Un servidor DELL PowerEdge R-420.

    Miembros permanentes

    Académicos responsables

    • Prof. Dr. Bárbara Poblete
      Teléfono: +562 29784947
      Correo electrónico: bpoblete@dcc.uchile.cl
      Dirección: Av. Blanco Encalada 2120, 4to piso
    • Prof. Dr. Benjamin Bustos
      Teléfono: +56 2 29784969
      Correo electrónico: bebustos@dcc.uchile.cl
      Dirección: Av. Blanco Encalada 2120, 3er piso

    Proyectos asociados

    • Proyecto FONDECYT 1140783, "Efficient 3D Shape Matching Using Local Descriptors" (2014-2016)
    • Proyecto FONDECYT 1110111 "Interest Points Detection Algorithms for 3D Shape Matching" (2011-2013)
    • Proyecto FONDEF D09I1185 "Real-Time Scalable Observatories in the Web" (2011-2013)
    • German Research Foundation DFG within Chile-German Cooperation Program, Project number SCHR 1229/2-1 "German-Chile Research Cooperation on 3D Object Retrieval" (2010)
    • Proyecto FONDECYT 11070037 "Effective and Efficient Retrieval in Multimedia Databases" (2007-2009)
    • Proyecto FONDECYT 11121511 "Automatic Knowledge Extraction from Social Media Data and User-Generated Contents for Improving the Web" (2012-2014)

    Publicaciones

    • Felipe Bravo-Marquez, Marcelo Mendoza, Barbara Poblete. Meta-level sentiment models for big social data analysis. Knowl.-Based Syst. 69: 86-99, 2014.
    • Jose Saavedra and Benjamin Bustos. Sketch-based image retrieval using keyshapes. Multimedia Tools and Applications 73 (3):2033-2062. Springer, 2014.
    • Ivan Sipiran, Rafael Meruane, Benjamin Bustos, Tobias Schreck, Bo Li, Yijuan Lu, and Henry Johan. A benchmark of simulated range images for partial shape retrieval. The Visual Computer 30(11):1293-1308. Springer, 2014.
    • Juan Manuel Barrios, Benjamin Bustos, and Tomas Skopal. Analyzing and dynamically indexing the query set. Information Systems 45:37-47. Elsevier, 2014.
    • Bo Li, Yijuan Lu, Afzal Godil, Tobias Schreck, Benjamin Bustos, Alfredo Ferreira, Takahiko Furuya, Manuel Fonseca, Henry Johan, Takahiro Matsuda, Ryutarou Ohbuchi, Pedro Pascoal, and Jose Saavedra. A comparison of methods for sketch-based 3D shape retrieval. Computer Vision and Image Understanding 119:57-80. Elsevier, 2014.
    • Ivan Sipiran and Benjamin Bustos. Key-components: Detection of salient regions on 3D meshes. The Visual Computer 29 (12):1319-1332. Springer, 2013.
    • Ivan Sipiran, Benjamin Bustos, and Tobias Schreck. Data-aware 3D partitioning for generic shape retrieval. Computer & Graphics 37(5):460-472. Elsevier, 2013.
    • Felipe Bravo-Marquez, Marcelo Mendoza, Barbara Poblete: Combining strengths, emotions and polarities for boosting Twitter sentiment analysis. WISDOM 2013: 2, 2013.
    • Marcelo Mendoza, Barbara Poblete, Felipe Bravo-Marquez, Daniel Gayo-Avello: Long-memory time series ensembles for concept shift detection. BigMine 2013: 23-30, 2013.
    • Zhouhui Lian, Afzal Godil, Benjamin Bustos, Mohamed Daoudi, Jeroen Hermans, Shun Kawamura, Yukinori Kurita, Guillaume Lavouè, Hien Van Nguyen, Ryutarou Ohbuchi, Yuki Ohkita, Yuya Ohishi, Fatih Porikli, Martin Reuter, Ivan Sipirán, Dirk Smeets, Paul Suetens, Hedi Tabia, Dirk Vandermeulen. A comparison of methods for non-rigid 3D shape retrieval. Pattern Recognition, 46(1):449-461. Elsevier Science, 2013.
    • Carlos Castillo, Marcelo Mendoza, Barbara Poblete: Predicting information credibility in time-sensitive social media. Internet Research 23(5): 560-588, 2013.
    • Juan Manuel Barrios and Benjamin Bustos. Competitive content-based video copy detection using global descriptors. Multimedia Tools and Applications, 62(1):75-110. Springer, 2013.
    • Tomas Skopal, Jakub Lokoc, and Benjamin Bustos. D-cache: universal distance cache for metric access methods. IEEE Transactions on Knowledge and Data Engineering, 24(5):868-881. IEEE Computer Society, 2012.
    • Benjamin Bustos, Sebastian Kreft, and Tomas Skopal. Adapting metric indexes for searching in multi-metric spaces. Multimedia Tools and Applications, 58(3):467-496. Springer, 2012.
    • I. Bordino, D. Donato, B. Poblete: Extracting interesting association rules from toolbar data. In Proceedings of the 21st ACM international conference on Information and knowledge management 2012, Maui, HI, USA.
    • Tomas Skopal and Benjamin Bustos. On nonmetric similarity search problems in complex domains. ACM Computing Surveys, 43(4):34:1-34:50. ACM, 2011.
    • B. Poblete, R. Garcia, M. Mendoza and A. Jaimes. Do All Birds Tweet the Same? Characterizing Twitter Around the World. In proceedings of CIKM'11. Glasgow,UK.
    • Castillo, C., Mendoza, M., Poblete, B.: "Information Credibility on Twitter". In The World Wide Web Conference (WWW), Hyderabad, India. 2011.
    • Barbara Poblete, Benjamin Bustos, Marcelo Mendoza, and Juan Manuel Barrios. Visual-semantic graphs: using queries to reduce the semantic gap in Web image retrieval. In Proc. 19th ACM International Conference on Information and Knowledge Management (CIKM'10), pages 1553-1556. ACM, 2010. Short paper.
    Subir
    Compartir:
    https://uchile.cl/i92398
    Copiar