{"id":"https://openalex.org/W7138012871","doi":"https://doi.org/10.18653/v1/2025.ijcnlp-long.42","title":"Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data","display_name":"Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7138012871","doi":"https://doi.org/10.18653/v1/2025.ijcnlp-long.42"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.ijcnlp-long.42","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-long.42","pdf_url":"https://aclanthology.org/2025.ijcnlp-long.42.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":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.ijcnlp-long.42.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129659624","display_name":"Xinyi Ling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyi Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129748414","display_name":"Hanwen Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanwen Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129689800","display_name":"Bo Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121623626","display_name":"Zhihui Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihui Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129719907","display_name":"Xia Ning","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia Ning","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":0.69630989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"743","last_page":"768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7296000123023987,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7296000123023987,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.09030000120401382,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.03709999844431877,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6486999988555908},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.23280000686645508},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.2303999960422516},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.22789999842643738}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6486999988555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5611000061035156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3481000065803528},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.31380000710487366},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30559998750686646},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.23899999260902405},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.23280000686645508},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2303999960422516},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.22789999842643738}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.ijcnlp-long.42","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-long.42","pdf_url":"https://aclanthology.org/2025.ijcnlp-long.42.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":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.ijcnlp-long.42","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-long.42","pdf_url":"https://aclanthology.org/2025.ijcnlp-long.42.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":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138012871.pdf","grobid_xml":"https://content.openalex.org/works/W7138012871.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Xinyi":[0],"Ling,":[1],"Hanwen":[2],"Du,":[3],"Bo":[4],"Peng,":[5],"Zhihui":[6],"Zhu,":[7],"Xia":[8],"Ning.":[9],"Proceedings":[10],"of":[11,25,29],"the":[12,22,26,30],"14th":[13],"International":[14],"Joint":[15],"Conference":[16,24],"on":[17],"Natural":[18],"Language":[19],"Processing":[20],"and":[21],"4th":[23],"Asia-Pacific":[27],"Chapter":[28],"Association":[31],"for":[32],"Computational":[33],"Linguistics.":[34],"2025.":[35]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}
