{"id":"https://openalex.org/W7166831635","doi":"https://doi.org/10.18653/v1/2026.findings-acl.704","title":"AFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce","display_name":"AFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166831635","doi":"https://doi.org/10.18653/v1/2026.findings-acl.704"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.704","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.704","pdf_url":"https://aclanthology.org/2026.findings-acl.704.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.704.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139769814","display_name":"Biao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090561833","display_name":"Lixin Chen","orcid":"https://orcid.org/0000-0002-9910-6483"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lixin Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139735803","display_name":"Bin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139730123","display_name":"Wang Zongwei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang Zongwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139748630","display_name":"Tong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139732377","display_name":"Bo Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82157676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14366","last_page":"14379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.08940000087022781,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.08940000087022781,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.08810000121593475,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.0681999996304512,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.40779998898506165},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.30329999327659607},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2935999929904938},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.2700999975204468},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2533999979496002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5838000178337097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5460000038146973},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.40779998898506165},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25029999017715454},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.24979999661445618},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24809999763965607}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.704","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.704","pdf_url":"https://aclanthology.org/2026.findings-acl.704.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.704","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.704","pdf_url":"https://aclanthology.org/2026.findings-acl.704.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166831635.pdf","grobid_xml":"https://content.openalex.org/works/W7166831635.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0,61],"representation":[1,12,77,127,171],"is":[2,29],"crucial":[3],"for":[4,31],"Ecommerce":[5],"tasks":[6],"such":[7],"as":[8,51,132],"identical":[9],"product":[10,48,71],"retrieval.Large":[11],"models":[13,167],"(e.g.,":[14],"VLM2Vec)":[15],"demonstrate":[16,149],"strong":[17],"multimodal":[18,142],"understanding":[19,50],"capabilities,":[20],"yet":[21],"they":[22],"struggle":[23],"with":[24],"fine-grained":[25,49,170],"semantic":[26],"comprehension,":[27],"which":[28,46],"essential":[30],"distinguishing":[32],"highly":[33],"similar":[34],"items.To":[35],"address":[36],"this,":[37],"we":[38],"propose":[39],"Attribute-Enhanced":[40],"Fine-Grained":[41],"Multi-Modal":[42],"Representation":[43],"Learning":[44,87],"(AFMRL),":[45],"defines":[47],"an":[52],"attribute":[53,139],"generation":[54,140],"task.It":[55],"leverages":[56],"the":[57,90,95,100,121,126,162],"generative":[58,166],"power":[59],"of":[60,125,164],"Large":[62],"Language":[63],"Models":[64],"(MLLMs)":[65],"to":[66,106,136,168],"extract":[67],"key":[68,91],"attributes":[69,92],"from":[70],"images":[72],"and":[73,75,110],"text,":[74],"enhances":[76],"learning":[78,103],"through":[79],"a":[80,133],"two-stage":[81],"training":[82,104],"framework:":[83],"1)":[84],"Attribute-Guided":[85],"Contrastive":[86],"(AGCL),":[88],"where":[89,120],"generated":[93],"by":[94],"MLLM":[96],"are":[97],"used":[98],"in":[99],"imagetext":[101],"contrastive":[102],"process":[105],"identify":[107],"hard":[108],"samples":[109],"filter":[111],"out":[112],"noisy":[113],"false":[114],"negatives.2)":[115],"Retrieval-aware":[116],"Attribute":[117],"Reinforcement":[118],"(RAR),":[119],"improved":[122],"retrieval":[123,159],"performance":[124,155],"model":[128],"postattribute":[129],"integration":[130],"serves":[131],"reward":[134],"signal":[135],"enhance":[137],"MLLM's":[138],"during":[141],"fine-tuning.Extensive":[143],"experiments":[144],"on":[145,156],"large-scale":[146],"E-commerce":[147],"datasets":[148],"that":[150],"our":[151],"method":[152],"achieves":[153],"state-of-the-art":[154],"multiple":[157],"downstream":[158],"tasks,":[160],"validating":[161],"effectiveness":[163],"harnessing":[165],"advance":[169],"learning.":[172]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}