{"id":"https://openalex.org/W7167935693","doi":"https://doi.org/10.1145/3805712.3808473","title":"COMET: Compatibility-Oriented Multi-modal Embedding Transformer for Visual Recommendations","display_name":"COMET: Compatibility-Oriented Multi-modal Embedding Transformer for Visual Recommendations","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167935693","doi":"https://doi.org/10.1145/3805712.3808473"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808473","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808473","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808473","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078967141","display_name":"Dween Rabius Sanny","orcid":"https://orcid.org/0000-0001-6664-9361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dween Rabius Sanny","raw_affiliation_strings":["Amazon, Bengaluru, Karnataka, India"],"raw_orcid":"https://orcid.org/0000-0001-6664-9361","affiliations":[{"raw_affiliation_string":"Amazon, Bengaluru, Karnataka, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017163111","display_name":"Prateek Sircar","orcid":null},"institutions":[{"id":"https://openalex.org/I3130021832","display_name":"Shree Guru Gobind Singh Tricentenary University","ror":"https://ror.org/04kf25f32","country_code":"IN","type":"education","lineage":["https://openalex.org/I3130021832"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prateek Sircar","raw_affiliation_strings":["Amazon, Gurugram, Haryana, India"],"raw_orcid":"https://orcid.org/0000-0002-9152-9238","affiliations":[{"raw_affiliation_string":"Amazon, Gurugram, Haryana, India","institution_ids":["https://openalex.org/I3130021832"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101734268","display_name":"Deepak Gupta","orcid":"https://orcid.org/0000-0003-0972-1317"},"institutions":[{"id":"https://openalex.org/I3130021832","display_name":"Shree Guru Gobind Singh Tricentenary University","ror":"https://ror.org/04kf25f32","country_code":"IN","type":"education","lineage":["https://openalex.org/I3130021832"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Deepak Gupta","raw_affiliation_strings":["Amazon, Gurugram, Haryana, India"],"raw_orcid":"https://orcid.org/0000-0003-0972-1317","affiliations":[{"raw_affiliation_string":"Amazon, Gurugram, Haryana, India","institution_ids":["https://openalex.org/I3130021832"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94856671,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4854","last_page":"4858"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.16680000722408295,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.16680000722408295,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.16019999980926514,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.10480000078678131,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/compatibility","display_name":"Compatibility (geochemistry)","score":0.5670999884605408},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5171999931335449},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.4666999876499176},{"id":"https://openalex.org/keywords/comet","display_name":"Comet","score":0.45829999446868896},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.3880000114440918},{"id":"https://openalex.org/keywords/framing","display_name":"Framing (construction)","score":0.37400001287460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6237000226974487},{"id":"https://openalex.org/C2778648169","wikidata":"https://www.wikidata.org/wiki/Q967768","display_name":"Compatibility (geochemistry)","level":2,"score":0.5670999884605408},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C94081185","wikidata":"https://www.wikidata.org/wiki/Q3559","display_name":"Comet","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40560001134872437},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.314300000667572},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31380000710487366},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C2779332521","wikidata":"https://www.wikidata.org/wiki/Q1820694","display_name":"Legibility","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3808473","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808473","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808473","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808473","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.507066011428833,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2737102415","https://openalex.org/W2795117763","https://openalex.org/W2912053445","https://openalex.org/W3010209648","https://openalex.org/W3034902834","https://openalex.org/W4292793877","https://openalex.org/W4385571705","https://openalex.org/W4385574358","https://openalex.org/W4385800890","https://openalex.org/W4403577395","https://openalex.org/W4407953194","https://openalex.org/W4411120585"],"related_works":[],"abstract_inverted_index":{"Recommending":[0],"visually":[1,137],"compatible":[2,158],"products":[3],"in":[4,177],"fashion":[5,171],"and":[6,19,42,102,159,173],"interior":[7],"design":[8],"is":[9,143],"a":[10,68,88,94,115,146],"significant":[11],"challenge,":[12],"as":[13,87],"compatibility":[14,36,86,96],"rules":[15,37],"are":[16,111],"nuanced,":[17],"context-dependent,":[18],"reliant":[20],"on":[21,45,166],"fine-grained":[22],"details":[23],"that":[24,98],"traditional":[25],"models":[26],"fail":[27],"to":[28,125,135,154,179],"capture.":[29],"Existing":[30],"methods":[31],"often":[32],"struggle":[33],"with":[34,80,149],"heterogeneous":[35],"(e.g.,":[38,129],"sofa-table":[39],"vs.":[40],"sofa-curtain)":[41],"an":[43,81],"over-reliance":[44],"global":[46],"visual":[47,73,109],"features,":[48],"missing":[49],"critical":[50],"textual":[51,95],"cues":[52],"like":[53],"style":[54],"or":[55,132],"material.":[56],"To":[57],"address":[58],"these":[59],"limitations,":[60],"we":[61],"introduce":[62],"COMET":[63,75,105,163],"(Compatibility-Oriented":[64],"Multi-modal":[65],"Embedding":[66],"Transformer),":[67],"scalable,":[69],"vision-language":[70],"framework":[71],"for":[72,169],"recommendations.":[74],"replaces":[76],"rigid,":[77],"category-specific":[78],"subspaces":[79],"attribute-conditioned":[82],"cross-attention":[83],"mechanism,":[84],"reframing":[85],"conditional":[89],"retrieval":[90],"problem.":[91],"By":[92],"formulating":[93],"prompt":[97],"encodes":[99],"relational":[100],"context":[101],"structured":[103],"attributes,":[104],"dynamically":[106],"conditions":[107],"which":[108],"features":[110],"attended":[112],"to,":[113],"producing":[114],"joint,":[116],"context-aware":[117],"representation.":[118],"This":[119],"multi-modal":[120],"approach":[121],"allows":[122],"the":[123],"model":[124,142],"leverage":[126],"descriptive":[127],"text":[128],"''mid-century":[130],"modern''":[131],"''oak":[133],"finish'')":[134],"understand":[136],"ambiguous":[138],"stylistic":[139],"nuances.":[140],"The":[141],"trained":[144],"using":[145],"triplet":[147],"loss":[148],"hard":[150],"negative":[151],"sample":[152],"strategy":[153],"effectively":[155],"distinguish":[156],"between":[157],"incompatible":[160],"item":[161],"pairs.":[162],"was":[164],"evaluated":[165],"established":[167],"benchmarks":[168],"both":[170],"(Polyvore)":[172],"furniture":[174],"(Bonn":[175],"Furniture),":[176],"addition":[178],"our":[180],"in-house":[181],"datasets.":[182]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-11T00:00:00"}