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

Recently, automatic image caption generation has been an important focus ofthe work on multimodal translation task. Existing approaches can be roughlycategorized into two classes, i.e., top-down and bottom-up, the formertransfers the image information (called as visual-level feature) directly intoa caption, and the later uses the extracted words (called as semanticlevelattribute) to generate a description. However, previous methods either aretypically based one-stage decoder or partially utilize part of visual-level orsemantic-level information for image caption generation. In this paper, weaddress the problem and propose an innovative multi-stage architecture (calledas Stack-VS) for rich fine-gained image caption generation, via combiningbottom-up and top-down attention models to effectively handle both visual-leveland semantic-level information of an input image. Specifically, we also proposea novel well-designed stack decoder model, which is constituted by a sequenceof decoder cells, each of which contains two LSTM-layers work interactively tore-optimize attention weights on both visual-level feature vectors andsemantic-level attribute embeddings for generating a fine-gained image caption.Extensive experiments on the popular benchmark dataset MSCOCO show thesignificant improvements on different evaluation metrics, i.e., theimprovements on BLEU-4/CIDEr/SPICE scores are 0.372, 1.226 and 0.216,respectively, as compared to the state-of-the-arts.

Stack-VS: Stacked Visual-Semantic Attention for Image Caption Generation