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

Impressive image captioning results are achieved in domains with plenty oftraining image and sentence pairs (e.g., MSCOCO). However, transferring to atarget domain with significant domain shifts but no paired training data(referred to as cross-domain image captioning) remains largely unexplored. Wepropose a novel adversarial training procedure to leverage unpaired data in thetarget domain. Two critic networks are introduced to guide the captioner,namely domain critic and multi-modal critic. The domain critic assesses whetherthe generated sentences are indistinguishable from sentences in the targetdomain. The multi-modal critic assesses whether an image and its generatedsentence are a valid pair. During training, the critics and captioner act asadversaries -- captioner aims to generate indistinguishable sentences, whereascritics aim at distinguishing them. The assessment improves the captionerthrough policy gradient updates. During inference, we further propose a novelcritic-based planning method to select high-quality sentences withoutadditional supervision (e.g., tags). To evaluate, we use MSCOCO as the sourcedomain and four other datasets (CUB-200-2011, Oxford-102, TGIF, and Flickr30k)as the target domains. Our method consistently performs well on all datasets.In particular, on CUB-200-2011, we achieve 21.8% CIDEr-D improvement afteradaptation. Utilizing critics during inference further gives another 4.5%boost.

Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner