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

Most approaches to cross-modal retrieval (CMR) focus either on object-centricdatasets, meaning that each document depicts or describes a single object, oron scene-centric datasets, meaning that each image depicts or describes acomplex scene that involves multiple objects and relations between them. Weposit that a robust CMR model should generalize well across both dataset types.Despite recent advances in CMR, the reproducibility of the results and theirgeneralizability across different dataset types has not been studied before. Weaddress this gap and focus on the reproducibility of the state-of-the-art CMRresults when evaluated on object-centric and scene-centric datasets. We selecttwo state-of-the-art CMR models with different architectures: (i) CLIP; and(ii) X-VLM. Additionally, we select two scene-centric datasets, and threeobject-centric datasets, and determine the relative performance of the selectedmodels on these datasets. We focus on reproducibility, replicability, andgeneralizability of the outcomes of previously published CMR experiments. Wediscover that the experiments are not fully reproducible and replicable.Besides, the relative performance results partially generalize acrossobject-centric and scene-centric datasets. On top of that, the scores obtainedon object-centric datasets are much lower than the scores obtained onscene-centric datasets. For reproducibility and transparency we make our sourcecode and the trained models publicly available.

Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study