240,159 Hits in 5.7 sec

Evaluating Content-Independent Features for Personality Recognition

Ben Verhoeven, Juan Soler Company, Walter Daelemans
2014 Proceedings of the 2014 ACM Multi Media on Workshop on Computational Personality Recognition - WCPR '14  
We have investigated whether the features proposed by Soler and Wanner [10] for gender prediction might also be useful in personality recognition.  ...  This paper describes our submission for the WCPR14 shared task on computational personality recognition.  ...  This research was funded by the Flemish government agency for Innovation by Science and Technology (IWT) through SBO (Strategic Basic Research) project AMiCA.  ... 
doi:10.1145/2659522.2659527 dblp:conf/mm/VerhoevenCD14 fatcat:bph4vb647rcgfaubu6mnq2uney

Singing voice conversion with non-parallel data [article]

Xin Chen, Wei Chu, Jinxi Guo, Ning Xu
2019 arXiv   pre-print
Then, a trained Recurrent Neural Network (RNN) with a Deep Bidirectional Long Short Term Memory (DBLSTM) structure is used to model the mapping from person-independent content to the acoustic features  ...  A phonetic posterior feature is first generated by decoding singing voices through a robust Automatic Speech Recognition Engine (ASR).  ...  As a result, this process builds a mapping from the person-independent phonetic posteriors to acoustic features that contain both person-dependent and person-independent content.  ... 
arXiv:1903.04124v1 fatcat:aod6nryvwzf6fby2sp6pnnbp6e

Context-Aware Person Identification in Personal Photo Collections

Neil O'Hare, Alan F. Smeaton
2009 IEEE transactions on multimedia  
We propose language modelling and nearest neighbor approaches to context-based person identification, in addition to novel face color and image color content-based features (used alongside face recognition  ...  Index Terms-Context and content, person identification, personal photo management.  ...  Fig. 4 . 4 Content-based features for person classification and recognition. Fig. 5 . 5 Results for Context-based person classification.  ... 
doi:10.1109/tmm.2008.2009679 fatcat:k45tkigy6fekrfk5mbn2byte64

Dynamic Bayesian Networks for Audio-Visual Speaker Recognition [chapter]

Dongdong Li, Yingchun Yang, Zhaohui Wu
2005 Lecture Notes in Computer Science  
We demonstrate that the performance of multimodal systems can be further improved by modeling the correlation of between the speech features and the face features appropriately.  ...  Audio-Visual speaker recognition promises higher performance than any single modal biometric systems.  ...  In the baseline strategy, the speaker recognition expert and face recognition expert are evaluated.  ... 
doi:10.1007/11608288_72 fatcat:v7whba2xwbg5lg6bxudxepxi5i

Automatic Text Searching For Personal Photos

Neil O'Hare, Hyowon Lee, Saman Cooray, Cathal Gurrin, Gareth J. F. Jones, Jovanka Malobabic, Noel E. O'Connor, Alan F. Smeaton, Bartlomiej Uscilowski
2006 International Conference on Semantics and Digital Media Technologies  
This demonstration presents the MediAssist prototype system for organisation of personal digital photo collections based on contextual information, such as time and location of image capture, and content-based  ...  analysis, such as face detection and recognition.  ...  The system uses a body patch feature (i.e. a feature modeling the clothes worn by a person) combined with a face recognition feature to suggest names for detected faces: the suggested name for an unknown  ... 
dblp:conf/samt/OHareLCGJMOSU06 fatcat:swxvwvcedjbjrjxz4ecapxox2y

International Standardization on Face Recognition Technology [chapter]

Wonjun Hwang, Seok Cheol Kee
2004 Lecture Notes in Computer Science  
This paper details the international standard works on biometrics, especially face recognition, for example, which groups have an interest, what kind of works has been done, and why the standard works  ...  Moreover, the history of MPEG-7 Advanced Face Recognition descriptor and current situations are described.  ...  Conclusions This paper presents an introduction of international standardization organization related to biometrics and standard works for facial template, especially MPEG-7 Advanced Face Recognition.  ... 
doi:10.1007/978-3-540-30548-4_40 fatcat:oahpumkz6vadtl7fdlevuurtpm

Evaluating strategies and systems for content based indexing of person images on the Web

Yuksel Alp Aslandogan, Clement T. Yu
2000 Proceedings of the eighth ACM international conference on Multimedia - MULTIMEDIA '00  
In particular, we e~Amine different methods of combining evidences due to face detection, Text/HTML analysis and face recognition for identifying person images.  ...  In this paper, we examine ways of combining visual and textual information for content based indexing of multimedia on the web.  ...  Rowley(CMU) for making sot~vare available for this project.  ... 
doi:10.1145/354384.354514 dblp:conf/mm/AslandoganY00 fatcat:4fwv24d625gp3lksndwkzhil5y

Human activity recognition for a content search system considering situations of smartphone users

Tomohiro Mashita, Kentaro Shimatani, Mayu Iwata, Hiroki Miyamoto, Daijiro Komaki, Takahiro Hara, Kiyoshi Kiyokawa, Haruo Takemura, Shojiro Nishio
2012 2012 IEEE Virtual Reality (VR)  
We use a Support Vector Machine for the context classification and compare four types of feature values consisting of FFT and 3 types of Wavelet Transforms.  ...  In this paper we describe our context recognition mechanism for this system. This mechanism estimates user context from sensors embedded in a smart-phone.  ...  Recognition Mechanism The human body is bouncing in a cycle when a person is walking or running. We applied frequency analysis to obtain the feature values for the activity recognition.  ... 
doi:10.1109/vr.2012.6180847 dblp:conf/vr/MashitaSIMKHKTN12 fatcat:fstlggzktrd2pcuoditeer4jsm

Emotion Recognition Using Voice Based on Emotion-Sensitive Frequency Ranges [chapter]

Kyung Hak Hyun, Eun Ho Kim, Yoon Keun Kwak
2007 Studies in Computational Intelligence  
From these results, we designed a personal filter bank and extracted emotional speech features using this filter bank.  ...  Therefore, in the present work we considered the personal characteristics of speech.  ...  The subjective evaluation tests for all corpora were performed. Subjective Evaluation Test Subjective evaluation tests were made for the database.  ... 
doi:10.1007/978-3-540-73424-6_25 fatcat:5a4cobasezgptpdts4j3hflezm

Voice Activated E-Learning System for the Visually Impaired

S. Asha, C. Chellappan
2011 International Journal of Computer Applications  
In the speaker verification subsystem, Mel-Frequency Cepstral Coefficients (MFCC) is used for Feature extraction and Vector Quantization (VQ) algorithm is used for codebook generation.  ...  E-learning has become an important tool for learners to acquire information and knowledge.  ...  In the User Verification subsystem 2 tests are evaluated: Test 1 for evaluating the true input and Test 2 for evaluating the false input Figure 3 shows the result of the true negative and false positive  ... 
doi:10.5120/1892-2514 fatcat:qxn7uwqrtbfataq5b2ueow4yqy

Combining dynamic features with MFCC for text-independent speaker identification

Amol Chaudhari, Amol Rahulkar, S. B. Dhonde
2015 2015 International Conference on Information Processing (ICIP)  
We start with the fundamentals of automatic speaker recognition, concerning feature extraction and speaker modeling.  ...  In this gives an overview of automatic speaker recognition technology, with an emphasis on textindependent recognition. Speaker recognition has been studied actively for several decades.  ...  Using a statistical model like Gaussian mixture model (GMM) and features extracted from those speech signals we build a unique identity for each person who enrolled for speaker recognition Gaussian mixture  ... 
doi:10.1109/infop.2015.7489370 fatcat:w2uqfyafm5a6netwm3dk7bt2p4

VidCat: an image and video analysis service for personal media management

Lee Begeja, Eric Zavesky, Zhu Liu, David Gibbon, Raghuraman Gopalan, Behzad Shahraray, Cees G. M. Snoek, Lyndon S. Kennedy, Reiner Creutzburg, David Akopian, Dietmar Wüller, Kevin J. Matherson (+2 others)
2013 Multimedia Content and Mobile Devices  
Evaluations for the effectiveness of the copy detection and face recognition algorithms on standard datasets are also discussed.  ...  Cloud-based storage and consumption of personal photos and videos provides increased accessibility, functionality, and satisfaction for mobile users.  ...  While processing the new media queue, each new piece of content is independently analyzed in a serial fashion.  ... 
doi:10.1117/12.2008528 fatcat:wbh733alifgcvalphrctrpfjqa

Action Unit recognition in still images using graph-based feature selection

Teodora Sechkova, Krasimir Tonchev, Agata Manolova
2016 2016 IEEE 8th International Conference on Intelligent Systems (IS)  
Using leave one person out evaluation methodology we achieve average accuracy of 90.1% for unsupervised and 92.7% for supervised feature selection on 12 Action Units.  ...  In this paper, we propose a Facial Action Unit recognition algorithm using graph-based feature selection in unsupervised and supervised setting.  ...  The authors of [8] incorporated spatial-independent feature extraction and statistical spatial shape and texture information.  ... 
doi:10.1109/is.2016.7737496 dblp:conf/is/SechkovaTM16 fatcat:sznzealqsfco3ouimfoco6vgsa

Method for Recognition of the Physical Activity of Human Being Using a Wearable Accelerometer

R. Adaskevicius
2014 Elektronika ir Elektrotechnika  
The extraction of orientation independent acceleration data has positive effect on recognition accuracy of k-nearest neighbour classification scheme used for classification task.  ...  For people who forget about a break or truly are focused on their direct work need help from special equipment for evaluation of real physical activity of computer user.  ...  CONCLUSIONS The proposed activity recognition method and equipment can be used for human activity evaluation.  ... 
doi:10.5755/j01.eee.20.5.7113 fatcat:57lr5eztkvc4tf3noccadxvriy

Content based Feature Combination Method for Face Image Retrieval using Neural Network and SVM Classifier for Face Recognition

Ningthoujam Sunita Devi, K. Hemachandran
2017 Indian Journal of Science and Technology  
The experimental results indicate that the fusion of PCA, WT and GW features as a feature vector performs reasonably well for retrieval and recognition process.  ...  For the face image retrieval purpose, Artificial Neural Network (ANN) is adopted and its performance on the retrieval process is evaluated with PCA, WT, GW and their fusion as a feature vector.  ...  UFI (Unconstrained Facial Images) and ORL (Oracle Research Laboratory) were used for evaluation of the proposed recognition system.  ... 
doi:10.17485/ijst/2017/v10i24/111123 fatcat:zi2wx52igbe6boaqsgnvn5jc3y
« Previous Showing results 1 — 15 out of 240,159 results