English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The advent of data-driven technology solutions is accompanied by anincreasing concern with data privacy. This is of particular importance forhuman-centered image recognition tasks, such as pedestrian detection,re-identification, and tracking. To highlight the importance of privacy issuesand motivate future research, we motivate and introduce the Pedestrian DatasetDe-Identification (PDI) task. PDI evaluates the degree of de-identification anddownstream task training performance for a given de-identification method. As afirst baseline, we propose IncogniMOT, a two-stage full-body de-identificationpipeline based on image synthesis via generative adversarial networks. Thefirst stage replaces target pedestrians with synthetic identities. To improvedownstream task performance, we then apply stage two, which blends and adaptsthe synthetic image parts into the data. To demonstrate the effectiveness ofIncogniMOT, we generate a fully de-identified version of the MOT17 pedestriantracking dataset and analyze its application as training data for pedestrianre-identification, detection, and tracking models. Furthermore, we show how ourdata is able to narrow the synthetic-to-real performance gap in aprivacy-conscious manner.

Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesis