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

Object detection plays an important role in current solutions to vision andlanguage tasks like image captioning and visual question answering. However,popular models like Faster R-CNN rely on a costly process of annotatingground-truths for both the bounding boxes and their corresponding semanticlabels, making it less amenable as a primitive task for transfer learning. Inthis paper, we examine the effect of decoupling box proposal and featurizationfor down-stream tasks. The key insight is that this allows us to leverage alarge amount of labeled annotations that were previously unavailable forstandard object detection benchmarks. Empirically, we demonstrate that thisleads to effective transfer learning and improved image captioning and visualquestion answering models, as measured on publicly available benchmarks.

Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering