Fashion Image-to-Image Translation for Complementary Item Retrieval
The increasing demand for online fashion retail has boosted research in fashion compatibility modeling and item retrieval, focusing on matching user queries (textual descriptions or reference images) with compatible fashion items. A key challenge is top-bottom retrieval, where precise compatibility...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-09 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Attimonelli, Matteo Pomo, Claudio Jannach, Dietmar Tommaso Di Noia |
description | The increasing demand for online fashion retail has boosted research in fashion compatibility modeling and item retrieval, focusing on matching user queries (textual descriptions or reference images) with compatible fashion items. A key challenge is top-bottom retrieval, where precise compatibility modeling is essential. Traditional methods, often based on Bayesian Personalized Ranking (BPR), have shown limited performance. Recent efforts have explored using generative models in compatibility modeling and item retrieval, where generated images serve as additional inputs. However, these approaches often overlook the quality of generated images, which could be crucial for model performance. Additionally, generative models typically require large datasets, posing challenges when such data is scarce. To address these issues, we introduce the Generative Compatibility Model (GeCo), a two-stage approach that improves fashion image retrieval through paired image-to-image translation. First, the Complementary Item Generation Model (CIGM), built on Conditional Generative Adversarial Networks (GANs), generates target item images (e.g., bottoms) from seed items (e.g., tops), offering conditioning signals for retrieval. These generated samples are then integrated into GeCo, enhancing compatibility modeling and retrieval accuracy. Evaluations on three datasets show that GeCo outperforms state-of-the-art baselines. Key contributions include: (i) the GeCo model utilizing paired image-to-image translation within the Composed Image Retrieval framework, (ii) comprehensive evaluations on benchmark datasets, and (iii) the release of a new Fashion Taobao dataset designed for top-bottom retrieval, promoting further research. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3094925208</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3094925208</sourcerecordid><originalsourceid>FETCH-proquest_journals_30949252083</originalsourceid><addsrcrecordid>eNqNissKgkAUQIcgSMp_GGg9MN3R0rUkuQ33chdXU-ZhM2PQ3_egD2h1DpyzYgkodRBFBrBhaQiTlBKOJ8hzlbCqxnAbneWNwYFEdOIrvPVog8b4Sb3zvHJm1mTIRvRP3kQy_ErRj_RAvWPrHnWg9Mct29fntrqI2bv7QiF2k1u8fadOyTIrIQdZqP-uF-UbOho</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3094925208</pqid></control><display><type>article</type><title>Fashion Image-to-Image Translation for Complementary Item Retrieval</title><source>Free E- Journals</source><creator>Attimonelli, Matteo ; Pomo, Claudio ; Jannach, Dietmar ; Tommaso Di Noia</creator><creatorcontrib>Attimonelli, Matteo ; Pomo, Claudio ; Jannach, Dietmar ; Tommaso Di Noia</creatorcontrib><description>The increasing demand for online fashion retail has boosted research in fashion compatibility modeling and item retrieval, focusing on matching user queries (textual descriptions or reference images) with compatible fashion items. A key challenge is top-bottom retrieval, where precise compatibility modeling is essential. Traditional methods, often based on Bayesian Personalized Ranking (BPR), have shown limited performance. Recent efforts have explored using generative models in compatibility modeling and item retrieval, where generated images serve as additional inputs. However, these approaches often overlook the quality of generated images, which could be crucial for model performance. Additionally, generative models typically require large datasets, posing challenges when such data is scarce. To address these issues, we introduce the Generative Compatibility Model (GeCo), a two-stage approach that improves fashion image retrieval through paired image-to-image translation. First, the Complementary Item Generation Model (CIGM), built on Conditional Generative Adversarial Networks (GANs), generates target item images (e.g., bottoms) from seed items (e.g., tops), offering conditioning signals for retrieval. These generated samples are then integrated into GeCo, enhancing compatibility modeling and retrieval accuracy. Evaluations on three datasets show that GeCo outperforms state-of-the-art baselines. Key contributions include: (i) the GeCo model utilizing paired image-to-image translation within the Composed Image Retrieval framework, (ii) comprehensive evaluations on benchmark datasets, and (iii) the release of a new Fashion Taobao dataset designed for top-bottom retrieval, promoting further research.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Compatibility ; Datasets ; Fashion goods ; Fashion models ; Generative adversarial networks ; Image enhancement ; Image quality ; Image retrieval ; Modelling ; Retrieval ; State-of-the-art reviews</subject><ispartof>arXiv.org, 2024-09</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Attimonelli, Matteo</creatorcontrib><creatorcontrib>Pomo, Claudio</creatorcontrib><creatorcontrib>Jannach, Dietmar</creatorcontrib><creatorcontrib>Tommaso Di Noia</creatorcontrib><title>Fashion Image-to-Image Translation for Complementary Item Retrieval</title><title>arXiv.org</title><description>The increasing demand for online fashion retail has boosted research in fashion compatibility modeling and item retrieval, focusing on matching user queries (textual descriptions or reference images) with compatible fashion items. A key challenge is top-bottom retrieval, where precise compatibility modeling is essential. Traditional methods, often based on Bayesian Personalized Ranking (BPR), have shown limited performance. Recent efforts have explored using generative models in compatibility modeling and item retrieval, where generated images serve as additional inputs. However, these approaches often overlook the quality of generated images, which could be crucial for model performance. Additionally, generative models typically require large datasets, posing challenges when such data is scarce. To address these issues, we introduce the Generative Compatibility Model (GeCo), a two-stage approach that improves fashion image retrieval through paired image-to-image translation. First, the Complementary Item Generation Model (CIGM), built on Conditional Generative Adversarial Networks (GANs), generates target item images (e.g., bottoms) from seed items (e.g., tops), offering conditioning signals for retrieval. These generated samples are then integrated into GeCo, enhancing compatibility modeling and retrieval accuracy. Evaluations on three datasets show that GeCo outperforms state-of-the-art baselines. Key contributions include: (i) the GeCo model utilizing paired image-to-image translation within the Composed Image Retrieval framework, (ii) comprehensive evaluations on benchmark datasets, and (iii) the release of a new Fashion Taobao dataset designed for top-bottom retrieval, promoting further research.</description><subject>Compatibility</subject><subject>Datasets</subject><subject>Fashion goods</subject><subject>Fashion models</subject><subject>Generative adversarial networks</subject><subject>Image enhancement</subject><subject>Image quality</subject><subject>Image retrieval</subject><subject>Modelling</subject><subject>Retrieval</subject><subject>State-of-the-art reviews</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNissKgkAUQIcgSMp_GGg9MN3R0rUkuQ33chdXU-ZhM2PQ3_egD2h1DpyzYgkodRBFBrBhaQiTlBKOJ8hzlbCqxnAbneWNwYFEdOIrvPVog8b4Sb3zvHJm1mTIRvRP3kQy_ErRj_RAvWPrHnWg9Mct29fntrqI2bv7QiF2k1u8fadOyTIrIQdZqP-uF-UbOho</recordid><startdate>20240924</startdate><enddate>20240924</enddate><creator>Attimonelli, Matteo</creator><creator>Pomo, Claudio</creator><creator>Jannach, Dietmar</creator><creator>Tommaso Di Noia</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240924</creationdate><title>Fashion Image-to-Image Translation for Complementary Item Retrieval</title><author>Attimonelli, Matteo ; Pomo, Claudio ; Jannach, Dietmar ; Tommaso Di Noia</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_30949252083</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Compatibility</topic><topic>Datasets</topic><topic>Fashion goods</topic><topic>Fashion models</topic><topic>Generative adversarial networks</topic><topic>Image enhancement</topic><topic>Image quality</topic><topic>Image retrieval</topic><topic>Modelling</topic><topic>Retrieval</topic><topic>State-of-the-art reviews</topic><toplevel>online_resources</toplevel><creatorcontrib>Attimonelli, Matteo</creatorcontrib><creatorcontrib>Pomo, Claudio</creatorcontrib><creatorcontrib>Jannach, Dietmar</creatorcontrib><creatorcontrib>Tommaso Di Noia</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Attimonelli, Matteo</au><au>Pomo, Claudio</au><au>Jannach, Dietmar</au><au>Tommaso Di Noia</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Fashion Image-to-Image Translation for Complementary Item Retrieval</atitle><jtitle>arXiv.org</jtitle><date>2024-09-24</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>The increasing demand for online fashion retail has boosted research in fashion compatibility modeling and item retrieval, focusing on matching user queries (textual descriptions or reference images) with compatible fashion items. A key challenge is top-bottom retrieval, where precise compatibility modeling is essential. Traditional methods, often based on Bayesian Personalized Ranking (BPR), have shown limited performance. Recent efforts have explored using generative models in compatibility modeling and item retrieval, where generated images serve as additional inputs. However, these approaches often overlook the quality of generated images, which could be crucial for model performance. Additionally, generative models typically require large datasets, posing challenges when such data is scarce. To address these issues, we introduce the Generative Compatibility Model (GeCo), a two-stage approach that improves fashion image retrieval through paired image-to-image translation. First, the Complementary Item Generation Model (CIGM), built on Conditional Generative Adversarial Networks (GANs), generates target item images (e.g., bottoms) from seed items (e.g., tops), offering conditioning signals for retrieval. These generated samples are then integrated into GeCo, enhancing compatibility modeling and retrieval accuracy. Evaluations on three datasets show that GeCo outperforms state-of-the-art baselines. Key contributions include: (i) the GeCo model utilizing paired image-to-image translation within the Composed Image Retrieval framework, (ii) comprehensive evaluations on benchmark datasets, and (iii) the release of a new Fashion Taobao dataset designed for top-bottom retrieval, promoting further research.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2024-09 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_3094925208 |
source | Free E- Journals |
subjects | Compatibility Datasets Fashion goods Fashion models Generative adversarial networks Image enhancement Image quality Image retrieval Modelling Retrieval State-of-the-art reviews |
title | Fashion Image-to-Image Translation for Complementary Item Retrieval |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-20T19%3A08%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Fashion%20Image-to-Image%20Translation%20for%20Complementary%20Item%20Retrieval&rft.jtitle=arXiv.org&rft.au=Attimonelli,%20Matteo&rft.date=2024-09-24&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3094925208%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3094925208&rft_id=info:pmid/&rfr_iscdi=true |