• 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 920
Next 10 →

Mostly-Unsupervised Statistical Segmentation of Japanese: Applications to Kanji

by Rie Kubota Ando , Lillian Lee , 2000
"... Given the lack of word delimiters in written Japanese, word segmentation is generally considered a crucial first step in processing Japanese texts. Typical Japanese segmentation algorithms rely either on a lexicon and grammar or on pre-segmented data. In contrast, we introduce a novel statistical me ..."
Abstract - Cited by 46 (1 self) - Add to MetaCart
Given the lack of word delimiters in written Japanese, word segmentation is generally considered a crucial first step in processing Japanese texts. Typical Japanese segmentation algorithms rely either on a lexicon and grammar or on pre-segmented data. In contrast, we introduce a novel statistical

Acoustic Confidence Measures For Segmenting Broadcast News

by Barker Williams, J. Barker, G. Williams, S. Renals - In Proceedings of the International Conference on Spoken Language Processing
"... In this paper we define an acoustic confidence measure based on the estimates of local posterior probabilities produced by a HMM/ANN large vocabulary continuous speech recognition system. We use this measure to segment continuous audio into regions where it is and is not appropriate to expend recogn ..."
Abstract - Cited by 5 (5 self) - Add to MetaCart
expect to be supplied with such pre-segmented data. Faced with an unsegmented stream of audio, f...

Pedestrian detection in crowded scenes

by Bastian Leibe, Edgar Seemann, Bernt Schiele - In CVPR , 2005
"... In this paper, we address the problem of detecting pedestri-ans in crowded real-world scenes with severe overlaps. Our basic premise is that this problem is too difficult for any type of model or feature alone. Instead, we present a novel al-gorithm that integrates evidence in multiple iterations an ..."
Abstract - Cited by 270 (27 self) - Add to MetaCart
and from different sources. The core part of our method is the combination of local and global cues via a probabilistic top-down segmentation. Altogether, this approach allows to examine and compare object hypotheses with high pre-cision down to the pixel level. Qualitative and quantitative results on a

Rich feature hierarchies for accurate object detection and semantic segmentation

by Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik
"... Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex en-semble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scala ..."
Abstract - Cited by 251 (23 self) - Add to MetaCart
in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN

Deep Learning of Image Features from Unlabeled Data for Multiple Sclerosis Lesion Segmentation

by Youngjin Yoo, Tom Brosch, Anthony Traboulsee, David K. B. Li, Roger Tam
"... Abstract. A new automatic method for multiple sclerosis (MS) lesion segmentation in multi-channel 3D MR images is presented. The main novelty of the method is that it learns the spatial image features needed for training a supervised classifier entirely from unlabeled data. This is in contrast to ot ..."
Abstract - Add to MetaCart
(pre-segmented data), the feature learning can take advantage of the typically much more available unlabeled data. Our method uses deep learning for feature learning and a random forest for supervised classification, but potentially any supervised classifier can be used. Quantitative validation

Abstract

by Rie Kubota Ando, Lillian Lee , 2008
"... Given the lack of word delimiters in written Japanese, word segmentation is generally considered a crucial first step in processing Japanese texts. Typical Japanese segmentation algorithms rely either on a lexicon and syntactic analysis or on pre-segmented data; but these are laborintensive, and the ..."
Abstract - Add to MetaCart
Given the lack of word delimiters in written Japanese, word segmentation is generally considered a crucial first step in processing Japanese texts. Typical Japanese segmentation algorithms rely either on a lexicon and syntactic analysis or on pre-segmented data; but these are laborintensive

Mostly-Unsupervised Statistical Segmentation of Japanese Kanji Sequences

by Rie Kubota, Ando Lillian Lee
"... Given the lack of word delimiters in written Japanese, word segmentation is generally considered a crucial first step in processing Japanese texts. Typical Japanese segmentation algorithms rely either on a lexicon and syntactic analysis or on pre-segmented data; but these are labor-intensive, and th ..."
Abstract - Add to MetaCart
Given the lack of word delimiters in written Japanese, word segmentation is generally considered a crucial first step in processing Japanese texts. Typical Japanese segmentation algorithms rely either on a lexicon and syntactic analysis or on pre-segmented data; but these are labor

Perception-oriented picking of structures in direct volumetric renderings

by Alexander Wiebel, Frans M. Vos Und, Herausgegeben Vom, Er Wiebel, Frans M. Vos, Hans-christian Hege , 2011
"... Radiologists from all application areas are trained to read slice-based visualizations of 3D medical image data. Despite the numerous examples of sophisticated three-dimensional renderings, especially all variants of direct volume rendering, such methods are often considered not very useful by radio ..."
Abstract - Cited by 4 (1 self) - Add to MetaCart
, in contrast to previous work, does not require pre-segmented data or metadata. The positions picked by our method are solely based on the data itself, the transfer function and, most importantly, on the way the volumet-ric rendering is perceived by viewers. To demonstrate the usefulness of the proposed method

Fera 2015 - second facial expression recognition and analysis challenge

by Michel F Valstar , Timur Almaev , Jeffrey M Girard , Gary Mckeown , Marc Mehu , Lijun Yin , Maja Pantic , Jeffrey F Cohn - in Automatic Face and Gesture Recognition (FG), 2015 11th IEEE International Conference and Workshops on , 2015
"... Abstract-Despite efforts towards evaluation standards in facial expression analysis (e.g. FERA 2011), there is a need for up-to-date standardised evaluation procedures, focusing in particular on current challenges in the field. One of the challenges that is actively being addressed is the automatic ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
conference on Face and Gesture Recognition, May 2015, in Ljubljana, Slovenia. Three sub-challenges are defined: the detection of AU occurrence, the estimation of AU intensity for pre-segmented data, and fully automatic AU intensity estimation. In this work we outline the evaluation protocol, the data used

Automated multi-modality image registration based on information theory

by A. Collignon, F. Maes, D. Delaere, D. Vandermeulen, P. Suetens, G. Marchal - In: Bizais , 1995
"... Abstract.We propose an information theoretic approach to the rigid body registration of 3D multi-modality medical image data. The "mutual infor-mation " of grey-value pairs is proposed as a new matching criterion. The new voxel similarity based (VB) registration algorithm is applied to rea ..."
Abstract - Cited by 179 (1 self) - Add to MetaCart
to real world images of the human head (CT, MR, and PET volumes), and com-pared to stereotactic and 2 other voxel based registration solutions. Our results show that subvoxel accuracy can be obtained completely automati-cally and without any pre-segmentation. 1.
Next 10 →
Results 1 - 10 of 920
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