{"id":"https://openalex.org/W4388191759","doi":"https://doi.org/10.1145/3581783.3612411","title":"Multi-Granularity Interactive Transformer Hashing for Cross-modal Retrieval","display_name":"Multi-Granularity Interactive Transformer Hashing for Cross-modal Retrieval","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388191759","doi":"https://doi.org/10.1145/3581783.3612411"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612411","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5013975825","display_name":"Yishu Liu","orcid":"https://orcid.org/0009-0004-7924-4039"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yishu Liu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-7924-4039","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027485596","display_name":"WU Qing-peng","orcid":"https://orcid.org/0009-0008-1334-2663"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingpeng Wu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-1334-2663","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459168","display_name":"Zheng Zhang","orcid":"https://orcid.org/0000-0003-1470-6998"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["Harbin Institute of Technology and Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1470-6998","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075847982","display_name":"Jingyi Zhang","orcid":"https://orcid.org/0000-0003-1909-6332"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyi Zhang","raw_affiliation_strings":["Huawei Technologies Company Ltd, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1909-6332","affiliations":[{"raw_affiliation_string":"Huawei Technologies Company Ltd, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030843117","display_name":"Guangming Lu","orcid":"https://orcid.org/0000-0003-1578-2634"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Lu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1578-2634","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"893","last_page":"902"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"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":0.9979000091552734,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.7766224145889282},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6532500386238098},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6314868927001953},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5475947260856628},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49187707901000977},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46836769580841064},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44980987906455994},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4335514307022095},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.42476707696914673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36827725172042847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766224145889282},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6532500386238098},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6314868927001953},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5475947260856628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49187707901000977},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46836769580841064},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44980987906455994},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4335514307022095},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.42476707696914673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36827725172042847},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612411","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1976258951","https://openalex.org/W2007972815","https://openalex.org/W2138621090","https://openalex.org/W2155803963","https://openalex.org/W2266728343","https://openalex.org/W2556967412","https://openalex.org/W2591669147","https://openalex.org/W2765440071","https://openalex.org/W2798991696","https://openalex.org/W2799150641","https://openalex.org/W2807912816","https://openalex.org/W2894874917","https://openalex.org/W2944466654","https://openalex.org/W2949588459","https://openalex.org/W2949846184","https://openalex.org/W2963140444","https://openalex.org/W2963187862","https://openalex.org/W2963288100","https://openalex.org/W2965509144","https://openalex.org/W2966146145","https://openalex.org/W2970971581","https://openalex.org/W2979579363","https://openalex.org/W2982905682","https://openalex.org/W2988823324","https://openalex.org/W2999606372","https://openalex.org/W3003460937","https://openalex.org/W3003735286","https://openalex.org/W3030772386","https://openalex.org/W3033799362","https://openalex.org/W3034890701","https://openalex.org/W3035060554","https://openalex.org/W3035485997","https://openalex.org/W3035524453","https://openalex.org/W3086725547","https://openalex.org/W3105676814","https://openalex.org/W3159481202","https://openalex.org/W3175740157","https://openalex.org/W3197447668","https://openalex.org/W3198047460","https://openalex.org/W3213100861","https://openalex.org/W4210593721","https://openalex.org/W4221144351","https://openalex.org/W4226426325","https://openalex.org/W4282937884","https://openalex.org/W4283389356","https://openalex.org/W4292828483","https://openalex.org/W4295312788","https://openalex.org/W4304092731","https://openalex.org/W4306317671","https://openalex.org/W4312229698","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6839503575"],"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/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"With":[0],"the":[1,35,77,84,111,147,172,178],"powerful":[2],"representation":[3],"ability":[4],"and":[5,41,64,134,149],"privileged":[6],"efficiency,":[7],"deep":[8],"cross-modal":[9,90,169],"hashing":[10],"(DCMH)":[11],"has":[12],"become":[13],"an":[14],"emerging":[15],"fast":[16],"similarity":[17,66],"search":[18],"technique.":[19],"Prior":[20],"studies":[21],"primarily":[22],"focus":[23],"on":[24,166],"exploring":[25],"pairwise":[26],"similarities":[27],"across":[28,68],"modalities,":[29],"but":[30],"fail":[31],"to":[32,101,126],"comprehensively":[33],"capture":[34],"multi-grained":[36],"semantic":[37,129,150],"correlations":[38],"during":[39],"intra-":[40],"inter-modal":[42,123],"negotiation.":[43],"To":[44,76],"tackle":[45],"this":[46,48,82],"issue,":[47],"paper":[49],"proposes":[50],"a":[51,93,121,140,156],"novel":[52],"Multi-granularity":[53],"Interactive":[54],"Transformer":[55],"Hashing":[56],"(MITH)":[57],"network,":[58],"which":[59],"hierarchically":[60],"considers":[61],"both":[62],"coarse-":[63],"fine-grained":[65],"measurements":[67],"different":[69,153],"modalities":[70,154],"in":[71],"one":[72],"unified":[73],"transformer-based":[74,89],"framework.":[75],"best":[78],"of":[79,113,175],"our":[80],"knowledge,":[81],"is":[83,99],"first":[85],"attempt":[86],"for":[87],"multi-granularity":[88,157],"hashing.":[91],"Specifically,":[92],"well-designed":[94],"distilled":[95],"intra-modal":[96],"interaction":[97],"module":[98,125],"deployed":[100],"excavate":[102],"modality-specific":[103],"concept":[104,130],"knowledge":[105,108],"with":[106,132],"global-local":[107],"distillation":[109],"under":[110],"guidance":[112],"implicit":[114],"conceptual":[115],"category-level":[116],"representations.":[117],"Moreover,":[118],"we":[119],"construct":[120],"contrastive":[122,136],"alignment":[124],"mine":[127],"modality-independent":[128],"correspondences":[131],"instance-":[133],"token-wise":[135],"learning,":[137],"respectively.":[138],"Such":[139],"collaborative":[141],"learning":[142],"paradigm":[143],"can":[144],"jointly":[145],"alleviate":[146],"heterogeneity":[148],"gaps":[151],"among":[152],"from":[155],"perspective,":[158],"yielding":[159],"discriminative":[160],"modality-invariant":[161],"hash":[162],"codes.":[163],"Extensive":[164],"experiments":[165],"multiple":[167],"representative":[168],"datasets":[170],"demonstrate":[171],"consistent":[173],"superiority":[174],"MITH":[176],"over":[177],"existing":[179],"state-of-the-art":[180],"baselines.":[181],"The":[182],"codes":[183],"are":[184],"available":[185],"at":[186],"https://github.com/DarrenZZhang/MITH.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":12}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}