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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In the fashion domain, there exists a variety of vision-and-language (V+L)tasks, including cross-modal retrieval, text-guided image retrieval,multi-modal classification, and image captioning. They differ drastically ineach individual input/output format and dataset size. It has been common todesign a task-specific model and fine-tune it independently from a pre-trainedV+L model (e.g., CLIP). This results in parameter inefficiency and inability toexploit inter-task relatedness. To address such issues, we propose a novelFAshion-focused Multi-task Efficient learning method for Vision-and-Languagetasks (FAME-ViL) in this work. Compared with existing approaches, FAME-ViLapplies a single model for multiple heterogeneous fashion tasks, thereforebeing much more parameter-efficient. It is enabled by two novel components: (1)a task-versatile architecture with cross-attention adapters and task-specificadapters integrated into a unified V+L model, and (2) a stable and effectivemulti-task training strategy that supports learning from heterogeneous data andprevents negative transfer. Extensive experiments on four fashion tasks showthat our FAME-ViL can save 61.5% of parameters over alternatives, whilesignificantly outperforming the conventional independently trained single-taskmodels. Code is available at https://github.com/BrandonHanx/FAME-ViL.

FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks