Conference paper Open Access

# Transformer reasoning network for image-text matching and retrieval

Messina Nicola; Falchi Fabrizio; Esuli Andrea; Amato Giuseppe

### Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:creator>Messina Nicola</dc:creator>
<dc:creator>Falchi Fabrizio</dc:creator>
<dc:creator>Esuli Andrea</dc:creator>
<dc:creator>Amato Giuseppe</dc:creator>
<dc:date>2021-01-10</dc:date>
<dc:description>Image-text matching is an interesting and fascinating task in modern AI research. Despite the evolution of deep-learning-based image and text processing systems, multi-modal matching remains a challenging problem. In this work, we consider the problem of accurate image-text matching for the task of multi-modal large-scale information retrieval. State-of-the-art results in image-text matching are achieved by inter-playing image and text features from the two different processing pipelines, usually using mutual attention mechanisms. However, this invalidates any chance to extract separate visual and textual features needed for later indexing steps in large-scale retrieval systems. In this regard, we introduce the Transformer Encoder Reasoning Network (TERN), an architecture built upon one of the modern relationship-aware self-attentive architectures, the Transformer Encoder (TE). This architecture is able to separately reason on the two different modalities and to enforce a final common abstract concept space by sharing the weights of the deeper transformer layers. Thanks to this design, the implemented network is able to produce compact and very rich visual and textual features available for the successive indexing step. Experiments are conducted on the MS-COCO dataset, and we evaluate the results using a discounted cumulative gain metric with relevance computed exploiting caption similarities, in order to assess possibly non-exact but relevant search results. We demonstrate that on this metric we are able to achieve state-of-the-art results in the image retrieval task. Our code is freely available at https://github.com/mesnico/TERN</dc:description>
<dc:identifier>https://zenodo.org/record/5575446</dc:identifier>
<dc:identifier>10.1109/ICPR48806.2021.9413172</dc:identifier>
<dc:identifier>oai:zenodo.org:5575446</dc:identifier>
<dc:language>akh</dc:language>
<dc:relation>info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - Research and Innovation action/951911/</dc:relation>
<dc:relation>info:eu-repo/grantAgreement/EC/H2020/825619/</dc:relation>
<dc:relation>url:https://zenodo.org/communities/ai4eu</dc:relation>
<dc:relation>url:https://zenodo.org/communities/ai4media</dc:relation>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:subject>cross-modal retrieval</dc:subject>
<dc:subject>artificial intelligence</dc:subject>
<dc:subject>deep learning</dc:subject>
<dc:subject>transformer encoder</dc:subject>
<dc:title>Transformer reasoning network for image-text matching and retrieval</dc:title>
<dc:type>info:eu-repo/semantics/conferencePaper</dc:type>
<dc:type>publication-conferencepaper</dc:type>
</oai_dc:dc>

33
25
views