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/

Zendy Plus

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

Zendy Tools

Zendy Open

Image-Text matching (ITM) is a common task for evaluating the quality ofVision and Language (VL) models. However, existing ITM benchmarks have asignificant limitation. They have many missing correspondences, originatingfrom the data construction process itself. For example, a caption is onlymatched with one image although the caption can be matched with other similarimages and vice versa. To correct the massive false negatives, we construct theExtended COCO Validation (ECCV) Caption dataset by supplying the missingassociations with machine and human annotators. We employ five state-of-the-artITM models with diverse properties for our annotation process. Our datasetprovides x3.6 positive image-to-caption associations and x8.5 caption-to-imageassociations compared to the original MS-COCO. We also propose to use aninformative ranking-based metric mAP@R, rather than the popular Recall@K (R@K).We re-evaluate the existing 25 VL models on existing and proposed benchmarks.Our findings are that the existing benchmarks, such as COCO 1K R@K, COCO 5KR@K, CxC R@1 are highly correlated with each other, while the rankings changewhen we shift to the ECCV mAP@R. Lastly, we delve into the effect of the biasintroduced by the choice of machine annotator. Source code and dataset areavailable at https://github.com/naver-ai/eccv-caption

ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO