https://scholars.lib.ntu.edu.tw/handle/123456789/412940
Title: | A latent semantic retrieval and clustering system for personal photos with sparse speech annotation | Authors: | Fu Y.-S. Hsu W.H. LIN-SHAN LEE |
Keywords: | Clustering; Fused speech and image features; Photo retrieval; Probabilistic latent semantic analysis (PLSA) | Issue Date: | 2009 | Start page/Pages: | 39-40 | Source: | 3rd Workshop on Searching Spontaneous Conversational Speech | Abstract: | In this demo we present a user-friendly latent semantic retrieval and clustering system for personal photos with sparse spontaneous speech tags annotated when the photos were taken. Only 10% of the photos need to be annotated by spontaneous speech of a few words regarding one or two semantic categories (e.g. what or where), while all photos can be effectively retrieved using high-level semantic queries in words (e.g. who, what, where, when) and clustered by the semantics as well. We use low-level image features to construct the relationships among photos, but train semantic models using Probabilistic Latent Semantic Analysis (PLSA) based on fused speech and image features to derive the "topics" of the photos. The sparse speech annotations serve as the user interface for the whole personal photo archive, while photos not annotated are automatically related by fused features and semantic topics of PLSA. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/412940 | ISBN: | 9781605587622 | DOI: | 10.1145/1631127.1631134 | SDG/Keyword: | Clustering system; High level semantics; Image features; Latent semantics; Low-level image features; Photo retrieval; Probabilistic latent semantic analysis; Probabilistic latent semantic analysis (PLSA); Semantic category; Semantic Model; Spontaneous speech; Image retrieval; Marine signal systems; Method of moments; Multimedia systems; User interfaces; Semantics |
Appears in Collections: | 資訊工程學系 |
File | Description | Size | Format | |
---|---|---|---|---|
d98922032a.pdf | 2.32 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.