Filters








617,124 Hits in 4.5 sec

Exploring Ratings in Subjective Databases

Sihem Amer-Yahia, Tova Milo, Brit Youngmann
2021 Proceedings of the 2021 International Conference on Management of Data  
Yet, as of today, dedicated tools to explore this data are lacking. In this paper, we develop a framework for Subjective Data Exploration (SDE).  ...  rating maps.  ...  INTRODUCTION Subjective data is characterized by a mix of facts and opinions. With the proliferation of user-generated content, subjective databases have grown in size [39, 52] .  ... 
doi:10.1145/3448016.3457259 fatcat:drd72knddvay7aw6kpa5vfyjye

SubDEx: Exploring Ratings in Subjective Databases

Sihem Amer-Yahia, Tova Milo, Brit Youngmann
2021 2021 IEEE 37th International Conference on Data Engineering (ICDE)  
We demonstrate SubDEx, a dedicated framework for Subjective Data Exploration (SDE).  ...  SubDEx enables the joint exploration of items, people, and people's opinions on items, in a guided multi-step process where each step aggregates the most useful and diverse trends in the form of rating  ...  Introduction Subjective data is characterized by a mix of facts and opinions. With the proliferation of user-generated content, subjective databases have grown in size [1] .  ... 
doi:10.1109/icde51399.2021.00296 fatcat:5cjmlpwkabeaha3zp43babtcdm

Does inter-subject variability depend on test material?

Stefan Winkler
2014 2014 Sixth International Workshop on Quality of Multimedia Experience (QoMEX)  
Quality of experience (QoE) research usually focuses on measuring or predicting mean opinion score (MOS), i.e. the average of ratings across subjects.  ...  Here we focus instead on the variability among subjects and explore questions such as: What factors does it depend on? Are these factors consistent across different experiments?  ...  INTRODUCTION A number of papers have explored the properties of data gathered in subjective experiments.  ... 
doi:10.1109/qomex.2014.6982283 dblp:conf/qomex/Winkler14 fatcat:dzyw27d6yrgczl7hkf6lwdhfze

Deep Neural Networks for Blind Image Quality Assessment: Addressing the Data Challenge [article]

Shahrukh Athar, Zhongling Wang, Zhou Wang
2021 arXiv   pre-print
We construct a DNN-based BIQA model called EONSS, train it on Waterloo Exploration-II, and test it on nine subject-rated IQA datasets, without any retraining or fine-tuning.  ...  (Note: Since this is an ongoing project, the final versions of Waterloo Exploration-II database, quality annotations, and EONSS, will be made publicly available in the future when it culminates.)  ...  ACKNOWLEDGMENT This work was supported in part by the Natural Sciences and Engineering Research Council (NSERC) of Canada.  ... 
arXiv:2109.12161v1 fatcat:5xmto4iys5avhjg4z6hsqccpoy

Semantic Face Signatures: Recognizing and Retrieving Faces by Verbal Descriptions

Nawaf Yousef Almudhahka, Mark S. Nixon, Jonathon S. Hare
2018 IEEE Transactions on Information Forensics and Security  
Furthermore, modelling of face image features in the semantic space can achieve an equal error rate of 12.71%.  ...  In this paper, we explore unconstrained human face identification with semantic face attributes derived automatically from images.  ...  In addition, we explore the semantic gap between humans and machines in rating facial attributes.  ... 
doi:10.1109/tifs.2017.2765519 fatcat:6ux4xbekvzb23i7gag34oavox4

Automatic Semantic Face Recognition

Nawaf Yousef Almudhahka, Mark S. Nixon, Jonathon S. Hare
2017 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)  
Recent expansion in surveillance systems has motivated research in soft biometrics that enable the unconstrained recognition of human faces.  ...  In this paper, we propose an approach for the automatic comparative labelling of facial soft biometrics.  ...  In [9] , 46 categorical facial attributes were defined, and identification was explored with 1196 subjects from the FERET database achieving rank-1 retrieval rate of 19% using human probe in automatic  ... 
doi:10.1109/fg.2017.31 dblp:conf/fgr/AlmudhahkaNH17 fatcat:wddlovgeenfo3i5lkfltgwonpa

Page 130 of British Journal of Clinical Pharmacology Vol. 57, Issue 2 [page]

2004 British Journal of Clinical Pharmacology  
USA and the Ontario provincial databases, contain data on millions of subjects and may also be used as a source for data mining.  ...  Data mining has been used to explore cardiovascular clinical trial databases [29], the US Vaccine Adverse Event Reporting System [30] and a large prescription database [31].  ... 

ColorNet – Estimating Colorfulness in Natural Images [article]

Emin Zerman, Aakanksha Rana, Aljosa Smolic
2019 arXiv   pre-print
Additionally, we propose to overcome the lack of adequate annotated dataset problem by combining/aligning two publicly available colorfulness databases using the results of a new subjective test which  ...  employs a common subset of both databases.  ...  SUBJECTIVE DATA In this study, we use the subjective colorfulness scores collected from participants for two different colorfulness databases: EPFL Dataset [5] with 84 images and UCL Dataset 1 [19]  ... 
arXiv:1908.08505v1 fatcat:zvgcaudbvbchfgvsoixddwmblq

Perceptual Quality Assessment of Omnidirectional Images as Moving Camera Videos [article]

Xiangjie Sui, Kede Ma, Yiru Yao, Yuming Fang
2021 arXiv   pre-print
point and the exploration time.  ...  We construct a set of specific quality measures within the proposed framework, and demonstrate their promises on three VR quality databases.  ...  Evaluation Protocols We used two subject-rated VR datasets -the omnidirectional IQA database [14] and the LIVE 3D VR IQA database [15] to conduct the comparison experiments.  ... 
arXiv:2005.10547v2 fatcat:a2ccgnsydnblnd22lckgfjzuiy

Subjective Assessment of H.264 Compressed Stereoscopic Video [article]

Manasa K, Balasubramanyam Appina, Sumohana S. Channappayya
2016 arXiv   pre-print
Further, 19 subjects participated in the subjective assessment task.  ...  Based on the subjective study, we have formulated a relation between the 2D and stereoscopic subjective scores as a function of compression rate and depth range.  ...  , b) a study of the relationship between the stereoscopic subjective scores and 2D subjective scores, c) a performance evaluation of popular 2D and 3D I/VQA algorithms on our database, and d) an exploration  ... 
arXiv:1604.07519v1 fatcat:7nnbg5lbt5da7aofrgptvujocy

A Comparison of Minimally Invasive Video-Assisted Parathyroidectomy and Traditional Parathyroidectomy for Parathyroid Adenoma

Paolo Del Rio, Diego Vicente, Umberto Maestroni, Anna Totaro, Gian Maria Casoni Pattacini, Itzhak Avital, Alexander Stojadinovic, Mario Sianesi
2013 Journal of Cancer  
In this study, most subjects returned to normal serum calcium at this time point with low relapse rates in both group A (3.7%) and group B (2.6%) subjects.  ...  Subject characteristics including age, gender, imaging and laboratory data were collected pre-operatively in our prospective database.  ... 
doi:10.7150/jca.6755 pmid:23901344 pmcid:PMC3726706 fatcat:gfr2omc4znbbrd5vx7afmxbcby

Improved Time-Frequency Features and Electrode Placement for EEG-Based Biometric Person Recognition

Su Yang, Sanaul Hoque, Farzin Deravi
2019 IEEE Access  
A multi-session analysis is simulated using with eyes open and eyes closed recordings from the MM/I database.  ...  The effectiveness of the proposed feature was investigated in both identification and verification scenarios.  ...  Tested using a population of 20 subjects (subset of a public database of 122 subjects), 92.8% identification rate was achieved using data from eight electrodes.  ... 
doi:10.1109/access.2019.2910752 fatcat:hw7kspgas5hszhl3pl5rsvz6ga

Empirical evaluation of full-reference image quality metrics on MDID database [article]

Domonkos Varga
2019 arXiv   pre-print
In this study, our goal is to give a comprehensive evaluation of 32 state-of-the-art FR-IQA metrics using the recently published MDID.  ...  This database contains distorted images derived from a set of reference, pristine images using random types and levels of distortions.  ...  The database contains 5,000 subjective ratings from 35 different -both male and female -observers. Quality score ratings (0 to 1) are provided in the form of DMOS.  ... 
arXiv:1910.01050v2 fatcat:62zl5ovsgzgllmyvi7n327wodm

A Database for Perceived Quality Assessment of User-Generated VR Videos [article]

Yuming Fang, Yiru Yao, Xiangjie Sui, Kede Ma
2022 arXiv   pre-print
In this paper, we establish one of the largest 360^∘ video databases, containing 502 user-generated videos with rich content and distortion diversities.  ...  We have made the dataset and code available at https://github.com/Yao-Yiru/VR-Video-Database.  ...  We employ the wellestablished rating strategy in [19, 45] to collect MOSs for different exploration periods.  ... 
arXiv:2206.08751v1 fatcat:l2jlzpurj5g2be5nnicse2xnci

A Novel Interface for Information Exploration and Visualisation

Max North, Sarah North, Nazir Warsi
1994 Australasian Journal of Information Systems  
This prototype information exploration and visualization interface allows users to explore a database with graphical widgets such as a novel dynamic slider.  ...  The dynamic slider and other widgets are utilized to assist users in mental visualization and representation of objects and actions.  ...  Army Center of Excellence in Information Science (Contract Number DAAL03-92-6-0377) and David and Lucile Packard Foundation.  ... 
doi:10.3127/ajis.v2i1.415 fatcat:27bidfq7kfhd5eloi7dufvlify
« Previous Showing results 1 — 15 out of 617,124 results