CoChat

Towards Measuring Fairness in AI: The Casual Conversations Dataset

Open access
Hazirbas, Caner, Bitton, Joanna, Dolhansky, Brian, Pan, Jacqueline, Gordo, Albert, Ferrer, Cristian Canton · 2022 · IEEE Transactions on Biometrics, Behavior, and Identity Science

The DOI matches its Crossref record; 33 of the 35 references it cites were found in a registry or an index.

Abstract

This paper introduces a novel dataset to help researchers evaluate their computer vision and audio models for accuracy across a diverse set of age, genders, apparent skin tones and ambient lighting conditions. Our dataset is composed of 3,011 subjects and contains over 45,000 videos, with an average of 15 videos per person. The videos were recorded in multiple U.S. states with a diverse set of adults in various age, gender and apparent skin tone groups. A key feature is that each subject agreed to participate for their likenesses to be used. Additionally, our age and gender annotations are provided by the subjects themselves. A group of trained annotators labeled the subjects’ apparent skin tone using the Fitzpatrick skin type scale. Moreover, annotations for videos recorded in low ambient lighting are also provided. As an application to measure robustness of predictions across certain attributes, we provide a comprehensive study on the top five winners of the DeepFake Detection Challenge (DFDC). Experimental evaluation shows that the winning models are less performant on some specific groups of people, such as subjects with darker skin tones and thus may not generalize to all people. In addition, we also evaluate the state-of-the-art apparent age and gender classification methods. Our experiments provides a thorough analysis on these models in terms of fair treatment of people from various backgrounds.

Overview

Integrity signals

Registry

Crossref · 10.1109/tbiom.2021.3132237

Cites

33 of 33 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 33 references

Research works printed but not linked: 9

  1. 10.1145/1577069.1755843 · doi:10.1145/1577069.1755843
  2. Seferbekov, 2021, DeepFake Detection Challenge (DFDC) Solution
  3. Zhao, 2021, DeepFake Detection Challenge (DFDC) Solution
  4. Davletshin, 2021, DeepFake Detection Challenge (DFDC) Solution
  5. Shao, 2021, DeepFake Detection Challenge (DFDC) Solution
  6. Howard, 2021, DeepFake Detection Challenge (DFDC) Solution
  7. Fitzpatrick, 1975, Soleil et peau’ [Sun and skin], J. Med. Esthétique, 2, 33
  8. Barocas, 2019, Fairness and Machine Learning
  9. 10.1145/1577069.1755843 · doi:10.1145/1577069.1755843

Cited by

See all 144

Metadata

Authors
Hazirbas, C., Bitton, J., Dolhansky, B., Pan, J., Gordo, A., & Ferrer, C. C.
Affiliations
  • Meta AI, AI Integrity, Seattle, WA, USA
  • Meta (United States) (US)
Venue
IEEE Transactions on Biometrics, Behavior, and Identity Science
Published
2022-07
Volume
4
Issue
3
Pages
324-332
ISSN
2637-6407 (ISSN-L)
OpenAlex
W3140832216
Cited by
79
References
35
Citations by year
2026: 8 · 2025: 23 · 2024: 14 · 2023: 15 · 2022: 12
FWCI
4.32
Type
journal article
Language
en
Open access
Locations
  • IEEE Transactions on Biometrics Behavior and Identity Science (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
  • Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
Keywords
algorithmic fairness, age estimation, gender classification, ambient lighting, deepfake detection, DFDC, algorithmic bias, Fitzpatrick skin type

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Towards Measuring Fairness in AI: The Casual Conversations Dataset. https://app.cochat.ai/papers/10.1109/tbiom.2021.3132237
The paper
Hazirbas, C., Bitton, J., Dolhansky, B., Pan, J., Gordo, A., & Ferrer, C. C. (2022). Towards Measuring Fairness in AI: The Casual Conversations Dataset. IEEE Transactions on Biometrics, Behavior, and Identity Science. https://doi.org/10.1109/tbiom.2021.3132237

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.