2022
DOI: 10.1515/lingvan-2022-0017
|View full text |Cite
|
Sign up to set email alerts
|

The Red Hen Anonymizer and the Red Hen Protocol for de-identifying audiovisual recordings

Abstract: Scientists of multimodal communication have no established policy or default tool for sharing de-identified audiovisual recordings. Recently, new technology has been developed that enables researchers to de-identify voice and appearance. These software tools can produce output in JSON format that specifies bodypose and face and hand keypoints in numerical form, suitable for computer search, machine learning, and sharing. The Red Hen Anonymizer is a new tool for de-identification. This article presents the Red … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
1
1
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(2 citation statements)
references
References 12 publications
0
2
0
Order By: Relevance
“…For instance, emotion drives most everything we do, so it is worthwhile to better understand its role in communication and language (Citron and Goldberg 2014;Foolen 2012). We also need to incorporate constraints and implications of communicative gestures (Congdon et al 2018;Khasbage et al 2022;Steen and Turner 2012;Willems and Hagoort 2007), and conversational dynamics to more accurately understand natural language (Du Bois, Kumpf, and Ashby 2003;Hopper and Thompson 1980;Stephens, Silbert, and Hasson 2010).…”
Section: Gpt-4 Appropriately Characterizes Conceptual Metaphorsmentioning
confidence: 99%
“…For instance, emotion drives most everything we do, so it is worthwhile to better understand its role in communication and language (Citron and Goldberg 2014;Foolen 2012). We also need to incorporate constraints and implications of communicative gestures (Congdon et al 2018;Khasbage et al 2022;Steen and Turner 2012;Willems and Hagoort 2007), and conversational dynamics to more accurately understand natural language (Du Bois, Kumpf, and Ashby 2003;Hopper and Thompson 1980;Stephens, Silbert, and Hasson 2010).…”
Section: Gpt-4 Appropriately Characterizes Conceptual Metaphorsmentioning
confidence: 99%
“…Indeed, especially in multimodal communication research on humans, original data that support one's analyses are often not openly shared, because they often consist of audiovisual recordings of identifiable people. There is, however, an increasing number of tools that allow to partially mask the identities from video and audio automatically, while still extracting non-identifiable information that can support analyses, such as facial, hand, and body pose information [82,133,156]. It is important to note that these tools do not count as anonymization tools, because either the transformed sound is still re-transformable to its original (thereby allowing identification in principle) or is still present next to a bodily mask.…”
Section: Factors That Can Accelerate Integration Between Disciplinesmentioning
confidence: 99%