Ergebnisse für *

Es wurden 2 Ergebnisse gefunden.

Zeige Ergebnisse 1 bis 2 von 2.

Sortieren

  1. Syntactic wordclass tagging
    Autor*in:
    Erschienen: 1999
    Verlag:  Kluwer, Dordrecht [u.a.]

    Hessisches BibliotheksInformationsSystem HeBIS
    keine Fernleihe
    Universitätsbibliothek J. C. Senckenberg, Zentralbibliothek (ZB)
    13.020.53
    uneingeschränkte Fernleihe, Kopie und Ausleihe
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Hinweise zum Inhalt
    Quelle: Verbundkataloge
    Beteiligt: Halteren, Hans van (Hrsg.); Voutilainen, Atro (Mitarb.); Leech, Geoffrey N. (Mitarb.); Smith, Nicholas (Mitarb.); Cloeren, Jan (Mitarb.); Wilson, Andrew (Mitarb.); Grefenstette, Gregory (Mitarb.); Schiller, Anne (Mitarb.); Karttunen, Lauri (Mitarb.); Monachini, Monica (Mitarb.); Calzolari, Nicoletta (Mitarb.); Oflazer, Kemal (Mitarb.); Brill, Eric (Mitarb.); El-Bèze, Marc (Mitarb.); Merialdo, Bernard (Mitarb.); Daelemans, Walter (Mitarb.)
    Sprache: Englisch
    Medientyp: Buch (Monographie)
    Format: Druck
    ISBN: 0792358961
    RVK Klassifikation: ET 705 ; ES 940
    Schriftenreihe: Text, speech and language technology ; 9
    Schlagworte: Computerlinguistik; Wortart; Morphosyntax; Disambiguierung
    Umfang: XVII, 334 S., graph. Darst.
    Bemerkung(en):

    Literaturverz. S. 311 - 326

  2. IRIM at TRECVID 2012: Semantic Indexing and Instance Search

    International audience ; The IRIM group is a consortium of French teams work- ing on Multimedia Indexing and Retrieval. This paper describes its participation to the TRECVID 2012 se- mantic indexing and instance search tasks. For the semantic... mehr

     

    International audience ; The IRIM group is a consortium of French teams work- ing on Multimedia Indexing and Retrieval. This paper describes its participation to the TRECVID 2012 se- mantic indexing and instance search tasks. For the semantic indexing task, our approach uses a six-stages processing pipelines for computing scores for the likeli- hood of a video shot to contain a target concept. These scores are then used for producing a ranked list of im- ages or shots that are the most likely to contain the tar- get concept. The pipeline is composed of the following steps: descriptor extraction, descriptor optimization, classi cation, fusion of descriptor variants, higher-level fusion, and re-ranking. We evaluated a number of dif- ferent descriptors and tried di erent fusion strategies. The best IRIM run has a Mean Inferred Average Pre- cision of 0.2378, which ranked us 4th out of 16 partici- pants. For the instance search task, our approach uses two steps. First individual methods of participants are used to compute similrity between an example image of in- stance and keyframes of a video clip. Then a two-step fusion method is used to combine these individual re- sults and obtain a score for the likelihood of an instance to appear in a video clip. These scores are used to ob- tain a ranked list of clips the most likely to contain the queried instance. The best IRIM run has a MAP of 0.1192, which ranked us 29th on 79 fully automatic runs.

     

    Export in Literaturverwaltung
    Quelle: BASE Fachausschnitt Germanistik
    Sprache: Englisch
    Medientyp: Konferenzveröffentlichung
    Format: Online
    Übergeordneter Titel: TRECVID - TREC Video Retrieval Evaluation workshop ; https://hal.science/hal-00770258 ; TRECVID - TREC Video Retrieval Evaluation workshop, Nov 2012, Gaithersburg, MD, United States. 12p
    Schlagworte: [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR]
    Lizenz:

    info:eu-repo/semantics/OpenAccess