Image Captioning-Based Image Search Engine: An Alternative to Retrieval by Metadata

Iyer, Sethurathienam; Chaturvedi, Shubham; Dash, Tirtharaj

doi:10.1007/978-981-13-1595-4_14

Cited by 9 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2.1.6 Applications. Applications of image captioning systems include indexing search results [34], describing images using virtual assistants [5], and helping non-experts interpret domain-specific images (e.g., a medical X-ray) [6]. However, by far the most commonly mentioned application is generating image descriptions for blind and low-vision users.…”

Section: Discussionmentioning

confidence: 99%

Measuring Representational Harms in Image Captioning

Wang

Barocas

Laird

et al. 2022

2022 ACM Conference on Fairness, Accountability, and Transparency

View full text Add to dashboard Cite

Previous work has largely considered the fairness of image captioning systems through the underspecified lens of "bias. " In contrast, we present a set of techniques for measuring five types of representational harms, as well as the resulting measurements obtained for two of the most popular image captioning datasets using a state-of-the-art image captioning system. Our goal was not to audit this image captioning system, but rather to develop normatively grounded measurement techniques, in turn providing an opportunity to reflect on the many challenges involved. We propose multiple measurement techniques for each type of harm. We argue that by doing so, we are better able to capture the multi-faceted nature of each type of harm, in turn improving the (collective) validity of the resulting measurements. Throughout, we discuss the assumptions underlying our measurement approach and point out when they do not hold. CCS Concepts: • Social and professional topics → User characteristics; • Computing methodologies → Computer vision problems; Natural language processing.

show abstract

Section: Discussionmentioning

confidence: 99%