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

Hateful meme detection is a challenging multimodal task that requirescomprehension of both vision and language, as well as cross-modal interactions.Recent studies have tried to fine-tune pre-trained vision-language models(PVLMs) for this task. However, with increasing model sizes, it becomesimportant to leverage powerful PVLMs more efficiently, rather than simplyfine-tuning them. Recently, researchers have attempted to convert meme imagesinto textual captions and prompt language models for predictions. This approachhas shown good performance but suffers from non-informative image captions.Considering the two factors mentioned above, we propose a probing-basedcaptioning approach to leverage PVLMs in a zero-shot visual question answering(VQA) manner. Specifically, we prompt a frozen PVLM by asking hatefulcontent-related questions and use the answers as image captions (which we callPro-Cap), so that the captions contain information critical for hateful contentdetection. The good performance of models with Pro-Cap on three benchmarksvalidates the effectiveness and generalization of the proposed method.

Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection