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

Image-text retrieval (ITR) is a task to retrieve the relevant images/texts,given the query from another modality. The conventional dense retrievalparadigm relies on encoding images and texts into dense representations usingdual-stream encoders, however, it faces challenges with low retrieval speed inlarge-scale retrieval scenarios. In this work, we propose the lexicon-weightingparadigm, where sparse representations in vocabulary space are learned forimages and texts to take advantage of the bag-of-words models and efficientinverted indexes, resulting in significantly reduced retrieval latency. Acrucial gap arises from the continuous nature of image data, and therequirement for a sparse vocabulary space representation. To bridge this gap,we introduce a novel pre-training framework, Lexicon-BottleneckedLanguage-Image Pre-Training (LexLIP), that learns importance-aware lexiconrepresentations. This framework features lexicon-bottlenecked modules betweenthe dual-stream encoders and weakened text decoders, allowing for constructingcontinuous bag-of-words bottlenecks to learn lexicon-importance distributions.Upon pre-training with same-scale data, our LexLIP achieves state-of-the-artperformance on two benchmark ITR datasets, MSCOCO and Flickr30k. Furthermore,in large-scale retrieval scenarios, LexLIP outperforms CLIP with a 5.5 ~ 221.3Xfaster retrieval speed and 13.2 ~ 48.8X less index storage memory.

LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval