Multi-modal Score Fusion and Decision Trees for Explainable Automatic Job Candidate Screening from Video CVs

Heysem Kaya; Furkan Gurpinar; Albert Ali Salah

doi:10.1109/CVPRW.2017.210

Multi-modal Score Fusion and Decision Trees for Explainable Automatic Job Candidate Screening from Video CVs

Heysem Kaya, Furkan Gurpinar, Albert Ali Salah

Social and Affective Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

We describe an end-to-end system for explainable automatic job candidate screening from video CVs. In this application, audio, face and scene features are first computed from an input video CV, using rich feature sets. These multiple modalities are fed into modality-specific regressors to predict apparent personality traits and a variable that predicts whether the subject will be invited to the interview. The base learners are stacked to an ensemble of decision trees to produce the outputs of the quantitative stage, and a single decision tree, combined with a rule-based algorithm produces interview decision explanations based on the quantitative results. The proposed system in this work ranks first in both quantitative and qualitative stages of the CVPR 2017 ChaLearn Job Candidate Screening Coopetition.

Original language	English
Title of host publication	Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Publisher	IEEE
Pages	1651-1659
Number of pages	9
Volume	2017-July
ISBN (Electronic)	9781538607336
DOIs	https://doi.org/10.1109/CVPRW.2017.210
Publication status	Published - 22 Aug 2017
Event	30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 - Honolulu, United States Duration: 21 Jul 2017 → 26 Jul 2017

Conference

Conference	30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Country/Territory	United States
City	Honolulu
Period	21/07/17 → 26/07/17

Funding

We thank the ChaLearn organization and other contributors of this challenge. This work is supported by Bog˘azic¸i UniversityProjectBAP 16A01P4andbytheBAGEP Award of the Science Academy.

Access to Document

10.1109/CVPRW.2017.210

Cite this

@inproceedings{5063c60ef2724f5b84fd9137a8f17459,

title = "Multi-modal Score Fusion and Decision Trees for Explainable Automatic Job Candidate Screening from Video CVs",

abstract = "We describe an end-to-end system for explainable automatic job candidate screening from video CVs. In this application, audio, face and scene features are first computed from an input video CV, using rich feature sets. These multiple modalities are fed into modality-specific regressors to predict apparent personality traits and a variable that predicts whether the subject will be invited to the interview. The base learners are stacked to an ensemble of decision trees to produce the outputs of the quantitative stage, and a single decision tree, combined with a rule-based algorithm produces interview decision explanations based on the quantitative results. The proposed system in this work ranks first in both quantitative and qualitative stages of the CVPR 2017 ChaLearn Job Candidate Screening Coopetition.",

author = "Heysem Kaya and Furkan Gurpinar and Salah, {Albert Ali}",

year = "2017",

month = aug,

day = "22",

doi = "10.1109/CVPRW.2017.210",

language = "English",

volume = "2017-July",

pages = "1651--1659",

booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017",

publisher = "IEEE",

address = "United States",

note = "30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 ; Conference date: 21-07-2017 Through 26-07-2017",

}

Kaya, H, Gurpinar, F & Salah, AA 2017, Multi-modal Score Fusion and Decision Trees for Explainable Automatic Job Candidate Screening from Video CVs. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. vol. 2017-July, 8014944, IEEE, pp. 1651-1659, 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017, Honolulu, United States, 21/07/17. https://doi.org/10.1109/CVPRW.2017.210

Multi-modal Score Fusion and Decision Trees for Explainable Automatic Job Candidate Screening from Video CVs. / Kaya, Heysem; Gurpinar, Furkan; Salah, Albert Ali.
Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. Vol. 2017-July IEEE, 2017. p. 1651-1659 8014944.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Multi-modal Score Fusion and Decision Trees for Explainable Automatic Job Candidate Screening from Video CVs

AU - Kaya, Heysem

AU - Gurpinar, Furkan

AU - Salah, Albert Ali

PY - 2017/8/22

Y1 - 2017/8/22

N2 - We describe an end-to-end system for explainable automatic job candidate screening from video CVs. In this application, audio, face and scene features are first computed from an input video CV, using rich feature sets. These multiple modalities are fed into modality-specific regressors to predict apparent personality traits and a variable that predicts whether the subject will be invited to the interview. The base learners are stacked to an ensemble of decision trees to produce the outputs of the quantitative stage, and a single decision tree, combined with a rule-based algorithm produces interview decision explanations based on the quantitative results. The proposed system in this work ranks first in both quantitative and qualitative stages of the CVPR 2017 ChaLearn Job Candidate Screening Coopetition.

AB - We describe an end-to-end system for explainable automatic job candidate screening from video CVs. In this application, audio, face and scene features are first computed from an input video CV, using rich feature sets. These multiple modalities are fed into modality-specific regressors to predict apparent personality traits and a variable that predicts whether the subject will be invited to the interview. The base learners are stacked to an ensemble of decision trees to produce the outputs of the quantitative stage, and a single decision tree, combined with a rule-based algorithm produces interview decision explanations based on the quantitative results. The proposed system in this work ranks first in both quantitative and qualitative stages of the CVPR 2017 ChaLearn Job Candidate Screening Coopetition.

UR - http://www.scopus.com/inward/record.url?scp=85030213298&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2017.210

DO - 10.1109/CVPRW.2017.210

M3 - Conference contribution

AN - SCOPUS:85030213298

VL - 2017-July

SP - 1651

EP - 1659

BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017

PB - IEEE

T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017

Y2 - 21 July 2017 through 26 July 2017

ER -

Multi-modal Score Fusion and Decision Trees for Explainable Automatic Job Candidate Screening from Video CVs

Abstract

Conference

Funding

Access to Document

Other files and links

Fingerprint

Cite this