{"id":"https://openalex.org/W4415537389","doi":"https://doi.org/10.1145/3746027.3754835","title":"SaP-Bot: A Multimodal Large-Language Model for End-to-End Same-Product Identification","display_name":"SaP-Bot: A Multimodal Large-Language Model for End-to-End Same-Product Identification","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537389","doi":"https://doi.org/10.1145/3746027.3754835"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754835","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754835","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103142223","display_name":"Yixuan Zhou","orcid":"https://orcid.org/0000-0003-1397-9396"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Zhou","raw_affiliation_strings":["Alipay, Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1397-9396","affiliations":[{"raw_affiliation_string":"Alipay, Ant Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014294835","display_name":"Yulu Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulu Tian","raw_affiliation_strings":["Alipay, Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-9104-5027","affiliations":[{"raw_affiliation_string":"Alipay, Ant Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002597419","display_name":"Wenliang Zhong","orcid":"https://orcid.org/0009-0006-8861-9503"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenliang Zhong","raw_affiliation_strings":["Alipay, Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-8861-9503","affiliations":[{"raw_affiliation_string":"Alipay, Ant Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109756279","display_name":"Xingbin Yu","orcid":"https://orcid.org/0009-0006-7522-5900"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingbin Yu","raw_affiliation_strings":["Alipay, Ant Group, Hangzhou, Alipay, China"],"raw_orcid":"https://orcid.org/0009-0006-7522-5900","affiliations":[{"raw_affiliation_string":"Alipay, Ant Group, Hangzhou, Alipay, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["School of Computer Scicence and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5685-3123","affiliations":[{"raw_affiliation_string":"School of Computer Scicence and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5951","last_page":"5960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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":0.9986000061035156,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9868999719619751,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9857000112533569,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6949999928474426},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6751000285148621},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6061999797821045},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5568000078201294},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5511000156402588},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5493999719619751},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5299000144004822},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5281000137329102},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.5138999819755554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7150999903678894},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6949999928474426},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6751000285148621},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6061999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5694000124931335},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5568000078201294},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5493999719619751},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5314000248908997},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5281000137329102},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5138999819755554},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3910999894142151},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.3874000012874603},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2847000062465668},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C189474733","wikidata":"https://www.wikidata.org/wiki/Q917912","display_name":"Model building","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754835","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754835","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2995278328","https://openalex.org/W3138516171","https://openalex.org/W3153940464","https://openalex.org/W3197545550","https://openalex.org/W4224037412","https://openalex.org/W4384891661","https://openalex.org/W4389267014","https://openalex.org/W4402754238","https://openalex.org/W4403792451"],"related_works":[],"abstract_inverted_index":{"Same-product":[0],"identification":[1,46,65],"serves":[2],"as":[3,22],"a":[4,90,97,143],"critical":[5],"infrastructure":[6],"in":[7,130],"e-commerce":[8],"systems,":[9],"enabling":[10,156],"accurate":[11],"product":[12,50,103,154],"matching":[13],"across":[14,48,83],"heterogeneous":[15],"marketing":[16],"representations":[17],"for":[18],"key":[19],"applications":[20],"such":[21],"price":[23],"comparison":[24],"and":[25,36,52,79,108,137,152,165],"personalized":[26],"recommendation.":[27],"Conventional":[28],"approaches":[29],"typically":[30],"depend":[31],"on":[32,115],"manual":[33],"feature":[34],"engineering":[35],"extensive":[37],"rule":[38],"tuning,":[39],"which":[40,133],"limits":[41],"their":[42],"adaptability":[43],"to":[44,95],"varying":[45],"criteria":[47],"different":[49],"categories":[51],"inconsistent":[53],"business":[54],"scenarios.":[55],"To":[56],"overcome":[57],"these":[58],"challenges,":[59],"we":[60,118,141],"propose":[61],"an":[62],"end-to-end":[63],"same-product":[64],"model":[66],"powered":[67],"by":[68],"multimodal":[69,77,106],"large":[70],"language":[71],"models":[72],"(MLLMs)":[73],"that":[74,160],"inherently":[75],"support":[76],"alignment":[78],"exhibit":[80],"strong":[81,144],"generalization":[82,138],"diverse":[84,102],"real-world":[85],"settings.":[86],"We":[87],"first":[88],"introduce":[89],"novel":[91],"group-wise":[92],"annotation":[93,164],"pipeline":[94],"construct":[96],"high-quality":[98],"dataset,":[99,117],"consisting":[100],"of":[101,126,150],"pairs":[104],"with":[105],"presentations":[107],"labeled":[109],"at":[110],"the":[111,124,147,153],"SKU":[112],"level.":[113],"Building":[114],"this":[116],"incorporate":[119],"task-specific":[120],"training":[121],"recipes":[122],"from":[123],"perspective":[125],"data":[127,163],"augmentation,":[128],"resulting":[129],"our":[131],"SaP-Bot,":[132],"demonstrates":[134],"advanced":[135],"performance":[136],"capabilities.":[139],"Moreover,":[140],"identify":[142],"correlation":[145],"between":[146],"output":[148],"logits":[149],"MLLMs":[151],"similarity,":[155],"interpretable":[157],"confidence":[158],"estimation":[159],"benefits":[161],"both":[162],"downstream":[166],"applications.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}