Grouper: Optimizing Crowdsourced Face Annotations

Adams, Jocelyn; Allen, Kristen; Miller, Tim; Kalka, Nathan D.; Jain, Anil K.

doi:10.1109/cvprw.2016.27

Cited by 6 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another limitation of the annotated dataset made publicly available 5 is the use of a single annotator. It may be interesting additional targeted research towards understanding the factors and implications when having diverse annotators, perhaps through crowd-sourcing [2].…”

Section: Final Discussion and Conclusionmentioning

confidence: 99%

“…It is also logical to see some positive correlations between gender (male: 0; female: 1) and beard or moustache. There is also a moderate correlation between age (0: Baby; 1: Child; 2: Youth; Youth (2) Middle Aged ( 3) Senior ( 4) Asian ( 2) Indian ( 3) Other ( 4) Sunglasses (2) 3: Middle Aged and 4 Senior) and glasses (0: No Glasses; 1: Eye Wear; 2: Sunglasses), giving us the idea that elder people tend to wear more eyewear or sunglasses, which is somewhat intuitive if we think that people lose their vision while growing. Finally there is moderate negative correlation between gender (Male: 0 ; Female: 1) and age (0: Baby; 1: Child; 2: Youth; 3: Middle Aged and 4 Senior), showing us that there are more older male than females.…”

Section: Beardmentioning

confidence: 99%

See 1 more Smart Citation

Facial Soft Biometrics for Recognition in the Wild: Recent Works, Annotation, and COTS Evaluation

Gonzalez-Sosa

Fiérrez

Vera-Rodríguez

et al. 2018

IEEE Trans.Inform.Forensic Secur.

112

View full text Add to dashboard Cite

The role of soft biometrics to enhance person recognition systems in unconstrained scenarios has not been extensively studied. Here, we explore the utility of the following modalities: gender, ethnicity, age, glasses, beard and moustache. We consider two assumptions: i) manual estimation of soft biometrics, and ii) automatic estimation from two Commercial Off-The-Shelf systems (COTS). All experiments are reported using the LFW database. First, we study the discrimination capabilities of soft biometrics standalone. Then, experiments are carried out fusing soft biometrics with two state-of-the-art face recognition systems based on deep learning. We observe that soft biometrics is a valuable complement to the face modality in unconstrained scenarios, with relative improvements up to 40%/15% in the verification performance when using manual/automatic soft biometrics estimation. Results are reproducible as we make public our manual annotations and COTS outputs of soft biometrics over LFW, as well as the face recognition scores.

show abstract

Section: Final Discussion and Conclusionmentioning

confidence: 99%

Section: Beardmentioning

confidence: 99%

Facial Soft Biometrics for Recognition in the Wild: Recent Works, Annotation, and COTS Evaluation

Gonzalez-Sosa

Fiérrez

Vera-Rodríguez

et al. 2018

IEEE Trans.Inform.Forensic Secur.

112

View full text Add to dashboard Cite

show abstract

“…Unconstrained face recognition is of more helpful use that will be nonetheless difficult due to the next components: Present variance, Imbalance, Lighting variance, Phrase variance, Standard blurs. That is used towards the accuracy of face recognition methods depreciates quickly in unconstrained locations [11], [19] [20][21] [22]. This could be recognized to degradations creating by cloud, change in illumination, present, and expression, unfinished occlusions etc.…”

Section: Practical Uses and Its Challengesmentioning

confidence: 99%

Reference Face Based Technique for Unconstrained Face Recognition from Images Gallery

Tyagi¹

2019

IJCG

View full text Add to dashboard Cite

This paper represents the Id Quality of un-constrained face inside an unconstrained environment. It provides capabilities like discrepancy, illumination, and expression difference techniques. It might be useful for both retrieve image (Face) and identification (Recognition). At present plenty of way of top view face recognition can be found. In last few years, for Computer vision, numerous face recognition techniques have been organized. But, actualworld face detection demands a difficult works. The curiosity about unconstrained helpful face recognition keeps growing utilizing the detonation of online press for instance community methods, and video surveillance recording wherever experience analysis is of great importance. In this analysis, it is appeared to handle status inside the scenario of chart assumption. We're in a position to determine a magical experience employing a Varied Technique. This study lights out the choices suggested for unconstrained face recognition quality area and suggesting the solution to be utilized by Reference Face Based Technique (From Gallery Image) centered face recognition. RFG recognition is used in grouping with DCT locality sensitive hashing for efficient recovery to guarantee scalability. Objective of this research is Reference Face Based Technique focused on unconstrained face recognition to enhance the demonstration quality. The Simulation of proposed techniques will be completed through the use of MATLAB.

show abstract

Smoothness Assisted Interactive Face Annotation via Neural Network

Sun

Luo

et al. 2018

Advances in Multimedia Information Processing – PCM 2018

View full text Add to dashboard Cite

Grouper: Optimizing Crowdsourced Face Annotations

Cited by 6 publications

References 7 publications

Facial Soft Biometrics for Recognition in the Wild: Recent Works, Annotation, and COTS Evaluation

Facial Soft Biometrics for Recognition in the Wild: Recent Works, Annotation, and COTS Evaluation

Reference Face Based Technique for Unconstrained Face Recognition from Images Gallery

Smoothness Assisted Interactive Face Annotation via Neural Network

Contact Info

Product

Resources

About