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

Egocentric vision holds great promises for increasing access to visualinformation and improving the quality of life for people with visualimpairments, with object recognition being one of the daily challenges for thispopulation. While we strive to improve recognition performance, it remainsdifficult to identify which object is of interest to the user; the object maynot even be included in the frame due to challenges in camera aiming withoutvisual feedback. Also, gaze information, commonly used to infer the area ofinterest in egocentric vision, is often not dependable. However, blind usersoften tend to include their hand either interacting with the object that theywish to recognize or simply placing it in proximity for better camera aiming.We propose localization models that leverage the presence of the hand as thecontextual information for priming the center area of the object of interest.In our approach, hand segmentation is fed to either the entire localizationnetwork or its last convolutional layers. Using egocentric datasets fromsighted and blind individuals, we show that the hand-priming achieves higherprecision than other approaches, such as fine-tuning, multi-class, andmulti-task learning, which also encode hand-object interactions inlocalization.

Hand-Priming in Object Localization for Assistive Egocentric Vision