{"id":"https://openalex.org/W4321485547","doi":"https://doi.org/10.1145/3539597.3570423","title":"Multimodal Pre-Training with Self-Distillation for Product Understanding in E-Commerce","display_name":"Multimodal Pre-Training with Self-Distillation for Product Understanding in E-Commerce","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4321485547","doi":"https://doi.org/10.1145/3539597.3570423"},"language":"en","primary_location":{"id":"doi:10.1145/3539597.3570423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100690917","display_name":"Shilei Liu","orcid":"https://orcid.org/0000-0003-2976-6256"},"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":"Shilei Liu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2976-6256","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006376791","display_name":"Lin Li","orcid":"https://orcid.org/0000-0001-6606-8831"},"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":"Lin Li","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6606-8831","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032962654","display_name":"Jun Song","orcid":"https://orcid.org/0000-0001-5778-6452"},"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":"Jun Song","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5778-6452","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006759116","display_name":"Yonghua Yang","orcid":"https://orcid.org/0000-0002-3853-066X"},"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":"Yonghua Yang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3853-066X","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082008486","display_name":"Xiaoyi Zeng","orcid":"https://orcid.org/0000-0002-3742-4910"},"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":"Xiaoyi Zeng","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3742-4910","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1039","last_page":"1047"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9918000102043152,"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":0.987500011920929,"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/computer-science","display_name":"Computer science","score":0.8552684783935547},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6721556186676025},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5558710694313049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5082118511199951},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5016660690307617},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49309155344963074},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4253287613391876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42043158411979675},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35271304845809937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8552684783935547},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6721556186676025},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5558710694313049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5082118511199951},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5016660690307617},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49309155344963074},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4253287613391876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42043158411979675},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35271304845809937},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539597.3570423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539597.3570423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2745461083","https://openalex.org/W2905544595","https://openalex.org/W2911988918","https://openalex.org/W2970231061","https://openalex.org/W3035333188","https://openalex.org/W3035485997","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3133376386","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W3165938948","https://openalex.org/W3170767867","https://openalex.org/W3196591432","https://openalex.org/W3202384916","https://openalex.org/W4224919569","https://openalex.org/W4312639100","https://openalex.org/W4312877428"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Product":[0],"understanding":[1,158],"refers":[2],"to":[3,96,102,133,140],"a":[4,47,60,71,78,98,129],"series":[5],"of":[6,21,24,57,77,164],"product-centric":[7],"tasks,":[8],"such":[9],"as":[10],"classification,":[11],"alignment":[12],"and":[13,35,38],"attribute":[14],"values":[15],"prediction,":[16],"which":[17,51,85,119],"requires":[18],"fine-grained":[19],"fusion":[20],"various":[22],"modalities":[23],"products.":[25],"Excellent":[26],"product":[27,58,157],"modeling":[28],"ability":[29],"will":[30,120],"enhance":[31],"the":[32,54,135,162,167],"user":[33,93],"experience":[34],"benefit":[36],"search":[37],"recommendation":[39],"systems.":[40],"In":[41,108],"this":[42,125],"paper,":[43],"we":[44,90,127],"propose":[45,128],"MBSD,":[46],"pre-trained":[48],"vision-and-language":[49],"model":[50],"can":[52,147],"integrate":[53],"heterogeneous":[55],"information":[56],"in":[59,116,137],"single":[61],"stream":[62],"BERT-style":[63],"architecture.":[64],"Compared":[65],"with":[66],"current":[67],"approaches,":[68],"MBSD":[69,165],"uses":[70],"lightweight":[72],"convolutional":[73],"neural":[74],"network":[75],"instead":[76],"heavy":[79],"feature":[80],"extractor":[81],"for":[82],"image":[83],"encoding,":[84],"has":[86],"lower":[87],"latency.":[88],"Besides,":[89],"cleverly":[91],"utilize":[92],"behavior":[94],"data":[95],"design":[97],"two-stage":[99],"pre-training":[100],"task":[101],"understand":[103],"products":[104],"from":[105],"different":[106],"perspectives.":[107],"addition,":[109],"there":[110],"is":[111],"an":[112],"underlying":[113],"imbalanced":[114],"problem":[115],"multimodal":[117],"pre-training,":[118],"impairs":[121],"downstream":[122],"tasks.":[123],"To":[124],"end,":[126],"novel":[130],"self-distillation":[131],"strategy":[132],"transfer":[134],"knowledge":[136],"dominated":[138],"modality":[139,146],"weaker":[141],"modality,":[142],"so":[143],"that":[144,161],"each":[145],"be":[148],"fully":[149],"tapped":[150],"during":[151],"pre-training.":[152],"Experimental":[153],"results":[154],"on":[155],"several":[156],"tasks":[159],"demonstrate":[160],"performance":[163],"outperforms":[166],"competitive":[168],"baselines.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}