1 resultado para infrared spectroscopy,chemometrics,least squares support vector machines
em Digital Peer Publishing
Filtro por publicador
- Repository Napier (1)
- Aberdeen University (1)
- Abertay Research Collections - Abertay University’s repository (1)
- Aberystwyth University Repository - Reino Unido (3)
- Academic Archive On-line (Mid Sweden University; Sweden) (1)
- Academic Archive On-line (Stockholm University; Sweden) (1)
- Acceda, el repositorio institucional de la Universidad de Las Palmas de Gran Canaria. España (3)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (5)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (3)
- Aquatic Commons (1)
- ArchiMeD - Elektronische Publikationen der Universität Mainz - Alemanha (1)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (2)
- Aston University Research Archive (25)
- Biblioteca de Teses e Dissertações da USP (1)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (9)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (17)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (3)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (28)
- Boston University Digital Common (1)
- Brock University, Canada (5)
- Bucknell University Digital Commons - Pensilvania - USA (2)
- Bulgarian Digital Mathematics Library at IMI-BAS (4)
- CaltechTHESIS (1)
- Cambridge University Engineering Department Publications Database (33)
- CentAUR: Central Archive University of Reading - UK (64)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (25)
- CiencIPCA - Instituto Politécnico do Cávado e do Ave, Portugal (1)
- Cochin University of Science & Technology (CUSAT), India (5)
- Coffee Science - Universidade Federal de Lavras (1)
- Collection Of Biostatistics Research Archive (3)
- CORA - Cork Open Research Archive - University College Cork - Ireland (4)
- Corvinus Research Archive - The institutional repository for the Corvinus University of Budapest (4)
- Dalarna University College Electronic Archive (3)
- Deakin Research Online - Australia (63)
- DI-fusion - The institutional repository of Université Libre de Bruxelles (1)
- Digital Commons at Florida International University (6)
- Digital Peer Publishing (1)
- DigitalCommons@The Texas Medical Center (1)
- DigitalCommons@University of Nebraska - Lincoln (1)
- Diposit Digital de la UB - Universidade de Barcelona (1)
- Doria (National Library of Finland DSpace Services) - National Library of Finland, Finland (2)
- Duke University (2)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (29)
- Greenwich Academic Literature Archive - UK (1)
- Helda - Digital Repository of University of Helsinki (8)
- Indian Institute of Science - Bangalore - Índia (75)
- INSTITUTO DE PESQUISAS ENERGÉTICAS E NUCLEARES (IPEN) - Repositório Digital da Produção Técnico Científica - BibliotecaTerezine Arantes Ferra (3)
- Instituto Politécnico do Porto, Portugal (2)
- Massachusetts Institute of Technology (15)
- National Center for Biotechnology Information - NCBI (5)
- Nottingham eTheses (1)
- Open University Netherlands (1)
- Plymouth Marine Science Electronic Archive (PlyMSEA) (1)
- Publishing Network for Geoscientific & Environmental Data (5)
- QSpace: Queen's University - Canada (1)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (54)
- Queensland University of Technology - ePrints Archive (160)
- RDBU - Repositório Digital da Biblioteca da Unisinos (1)
- Repositorio Academico Digital UANL (1)
- Repositório Científico da Universidade de Évora - Portugal (6)
- Repositório Científico do Instituto Politécnico de Lisboa - Portugal (1)
- Repositório digital da Fundação Getúlio Vargas - FGV (1)
- Repositorio Institucional da UFLA (RIUFLA) (1)
- Repositório Institucional da Universidade de Aveiro - Portugal (4)
- Repositório Institucional da Universidade de Brasília (2)
- Repositório Institucional da Universidade Tecnológica Federal do Paraná (RIUT) (2)
- Repositorio Institucional de la Universidad de Málaga (1)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (88)
- RUN (Repositório da Universidade Nova de Lisboa) - FCT (Faculdade de Cienecias e Technologia), Universidade Nova de Lisboa (UNL), Portugal (4)
- SAPIENTIA - Universidade do Algarve - Portugal (5)
- School of Medicine, Washington University, United States (1)
- SerWisS - Server für Wissenschaftliche Schriften der Fachhochschule Hannover (1)
- Universidad de Alicante (4)
- Universidad del Rosario, Colombia (2)
- Universidad Politécnica de Madrid (19)
- Universidade Complutense de Madrid (1)
- Universidade de Lisboa - Repositório Aberto (3)
- Universidade Federal de Uberlândia (2)
- Universidade Federal do Pará (1)
- Universidade Federal do Rio Grande do Norte (UFRN) (13)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (1)
- Université de Lausanne, Switzerland (2)
- Université de Montréal, Canada (5)
- University of Canberra Research Repository - Australia (7)
- University of Michigan (11)
- University of Queensland eSpace - Australia (26)
- WestminsterResearch - UK (1)
Resumo:
Audio-visual documents obtained from German TV news are classified according to the IPTC topic categorization scheme. To this end usual text classification techniques are adapted to speech, video, and non-speech audio. For each of the three modalities word analogues are generated: sequences of syllables for speech, “video words” based on low level color features (color moments, color correlogram and color wavelet), and “audio words” based on low-level spectral features (spectral envelope and spectral flatness) for non-speech audio. Such audio and video words provide a means to represent the different modalities in a uniform way. The frequencies of the word analogues represent audio-visual documents: the standard bag-of-words approach. Support vector machines are used for supervised classification in a 1 vs. n setting. Classification based on speech outperforms all other single modalities. Combining speech with non-speech audio improves classification. Classification is further improved by supplementing speech and non-speech audio with video words. Optimal F-scores range between 62% and 94% corresponding to 50% - 84% above chance. The optimal combination of modalities depends on the category to be recognized. The construction of audio and video words from low-level features provide a good basis for the integration of speech, non-speech audio and video.