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

Learning fine-grained interplay between vision and language allows to a moreaccurate understanding for VisionLanguage tasks. However, it remainschallenging to extract key image regions according to the texts for semanticalignments. Most existing works are either limited by textagnostic andredundant regions obtained with the frozen detectors, or failing to scalefurther due to its heavy reliance on scarce grounding (gold) data to pre-traindetectors. To solve these problems, we propose Self-Locator Aided Network(SLAN) for cross-modal understanding tasks without any extra gold data. SLANconsists of a region filter and a region adaptor to localize regions ofinterest conditioned on different texts. By aggregating cross-modalinformation, the region filter selects key regions and the region adaptorupdates their coordinates with text guidance. With detailed region-wordalignments, SLAN can be easily generalized to many downstream tasks. Itachieves fairly competitive results on five cross-modal understanding tasks(e.g., 85.7% and 69.2% on COCO image-to-text and text-to-image retrieval,surpassing previous SOTA methods). SLAN also demonstrates strong zero-shot andfine-tuned transferability to two localization tasks.

SLAN: Self-Locator Aided Network for Cross-Modal Understanding