• Documents
  • Authors
  • Tables
  • Log in
  • Sign up
  • MetaCart
  • DMCA
  • Donate

CiteSeerX logo

Advanced Search Include Citations

Tools

Sorted by:
Try your query at:
Semantic Scholar Scholar Academic
Google Bing DBLP
Results 1 - 10 of 2,952
Next 10 →

Video google: A text retrieval approach to object matching in videos

by Josef Sivic, Andrew Zisserman - In ICCV , 2003
"... We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a set of viewpoint invariant region descriptors so that recognition can proceed successfully despite changes in viewpoint, ill ..."
Abstract - Cited by 1636 (42 self) - Add to MetaCart
We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a set of viewpoint invariant region descriptors so that recognition can proceed successfully despite changes in viewpoint

A New Approach to Text Searching

by Ricardo A. Baeza-yates, Blanco Encalada, Gaston H. Gonnet
"... We introduce a family of simple and fast algorithms for solving the classical string matching problem, string matching with classes of symbols, don't care symbols and complement symbols, and multiple patterns. In addition we solve the same problems allowing up to k mismatches. Among the feature ..."
Abstract - Cited by 293 (15 self) - Add to MetaCart
the features of these algorithms are that they don't need to buffer the input, they are real time algorithms (for constant size patterns), and they are suitable to be implemented in hardware. 1 Introduction String searching is a very important component of many problems, including text editing

UNIT SELECTION IN A CONCATENATIVE SPEECH SYNTHESIS SYSTEM USING A LARGE SPEECH DATABASE

by Andrew J. Hunt, Alan W. Black , 1996
"... One approach to the generation of natural-sounding syn-thesized speech waveforms is to select and concatenate units from a large speech database. Units (in the current work, phonemes) are selected to produce a natural realisation of a target phoneme sequence predicted from text which is annotated wi ..."
Abstract - Cited by 425 (27 self) - Add to MetaCart
One approach to the generation of natural-sounding syn-thesized speech waveforms is to select and concatenate units from a large speech database. Units (in the current work, phonemes) are selected to produce a natural realisation of a target phoneme sequence predicted from text which is annotated

Informed Prefetching and Caching

by R. Hugo Patterson, Garth A. Gibson, Eka Ginting, Daniel Stodolsky, Jim Zelenka - In Proceedings of the Fifteenth ACM Symposium on Operating Systems Principles , 1995
"... The underutilization of disk parallelism and file cache buffers by traditional file systems induces I/O stall time that degrades the performance of modern microprocessor-based systems. In this paper, we present aggressive mechanisms that tailor file system resource management to the needs of I/O-int ..."
Abstract - Cited by 402 (10 self) - Add to MetaCart
performance on a 150 MHz Alpha equipped with 15 disks running a range of applications including text search, 3D scientific visualization, relational database queries, speech recognition, and computational chemistry. Informed prefetching reduces the execution time of the first four of these applications by 20

An algorithm for pronominal anaphora resolution

by Herbert J Leass - Computational Linguistics , 1994
"... This paper presents an algorithm for identifying the noun phrase antecedents of third person pronouns and lexical anaphors (reflexives and reciprocals). The algorithm applies to the syntactic representations generated by McCord's Slot Grammar parser, and relies on salience measures derived from ..."
Abstract - Cited by 391 (0 self) - Add to MetaCart
from syntactic structure and a simple dynamic model of attentional state. Like the parser, the algorithm is implemented in Prolog. The authors have tested it extensively on computer manual texts, and conducted a blind test on manual text containing 360 pronoun occurrences. The algorithm successfully

Lightweight Structure in Text

by Robert C. Miller , 2002
"... Pattern matching is heavily used for searching, filtering, and transforming text, but existing pattern languages offer few opportunities for reuse. Lightweight structure is a new approach that solves the reuse problem. Lightweight structure has three parts: a model of text structure as contiguous se ..."
Abstract - Cited by 29 (8 self) - Add to MetaCart
Pattern matching is heavily used for searching, filtering, and transforming text, but existing pattern languages offer few opportunities for reuse. Lightweight structure is a new approach that solves the reuse problem. Lightweight structure has three parts: a model of text structure as contiguous

Lightweight Morphology: A Methodology for Improving Text Search

by Mikaƫl Roussillon, Bradford G. Nickerson, Stephen Green, William A. Woods , 2004
"... Lightweight Morphology is a new approach to morphological analysis, creating morphological variants from sets of rules. The rules are intuitive to define and at the same time, offering expressiveness and control. We defined a grammar for Lightweight Morphology. We defined how to generate English and ..."
Abstract - Add to MetaCart
Lightweight Morphology is a new approach to morphological analysis, creating morphological variants from sets of rules. The rules are intuitive to define and at the same time, offering expressiveness and control. We defined a grammar for Lightweight Morphology. We defined how to generate English

Approaches to Passage Retrieval in Full Text Information Systems

by Gerard Salton, J. Allan, C. Buckley , 1993
"... Large collections of full-text documents are now commonly used in automated information retrieval. When the stored document texts are long, the retrieval of complete documents may not be in the users' best. interest. In such circumstances, efficient and effective retrieval results may be obtain ..."
Abstract - Cited by 193 (5 self) - Add to MetaCart
be obtained by using passage re- trieval strategies designed to retrieve text excerpts of varying size in response to statements of user inerest. New approaches are described in this study for imple- menting selective passage retrieval systems, and identifying text passages responsive to particular user needs

Improving Search Results with Lightweight Semantic Search

by unknown authors
"... The goal of each search service is to yield the most relevant results on a given query. Traditional full-text search is not enough and many approaches to improve search rankings are adopted. In this paper we propose a method of combined search query scoring computation leveraging lightweight semanti ..."
Abstract - Add to MetaCart
The goal of each search service is to yield the most relevant results on a given query. Traditional full-text search is not enough and many approaches to improve search rankings are adopted. In this paper we propose a method of combined search query scoring computation leveraging lightweight

Peer-to-Peer Information Retrieval Using Self-Organizing Semantic Overlay Networks

by Chunqiang Tang, Zhichen Xu, Sandhya Dwarkadas , 2003
"... Content-based full-text search is a challenging problem in Peer-toPeer (P2P) systems. Traditional approaches have either been centralized or use flooding to ensure accuracy of the results returned. In this paper, we present pSearch, a decentralized non-flooding P2P information retrieval system. pSea ..."
Abstract - Cited by 242 (7 self) - Add to MetaCart
Content-based full-text search is a challenging problem in Peer-toPeer (P2P) systems. Traditional approaches have either been centralized or use flooding to ensure accuracy of the results returned. In this paper, we present pSearch, a decentralized non-flooding P2P information retrieval system. pSearch
Next 10 →
Results 1 - 10 of 2,952
Powered by: Apache Solr
  • About CiteSeerX
  • Submit and Index Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2019 The Pennsylvania State University