{"id":"https://openalex.org/W4408345939","doi":"https://doi.org/10.1109/icassp49660.2025.10889423","title":"Retention Enhanced Cross-modal Attention for Multi-Hop VQA","display_name":"Retention Enhanced Cross-modal Attention for Multi-Hop VQA","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345939","doi":"https://doi.org/10.1109/icassp49660.2025.10889423"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5101706276","display_name":"Zijie Zhu","orcid":"https://orcid.org/0009-0003-3955-2945"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijie Zhu","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626870","display_name":"Feng Ding","orcid":"https://orcid.org/0000-0003-2512-5443"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Ding","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102910551","display_name":"Chenglong Chu","orcid":"https://orcid.org/0009-0004-9401-7627"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Chu","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091207959","display_name":"Fangming Zhong","orcid":"https://orcid.org/0000-0002-2775-8175"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangming Zhong","raw_affiliation_strings":["Dalian University of Technology,School of Software Technology,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Software Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05478012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.944100022315979,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.944100022315979,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9433000087738037,"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/T13731","display_name":"Advanced Computing and Algorithms","score":0.9316999912261963,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7175906896591187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5630697011947632},{"id":"https://openalex.org/keywords/hop","display_name":"Hop (telecommunications)","score":0.46601322293281555},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3373943269252777},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.09116178750991821}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7175906896591187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5630697011947632},{"id":"https://openalex.org/C25906391","wikidata":"https://www.wikidata.org/wiki/Q1432381","display_name":"Hop (telecommunications)","level":2,"score":0.46601322293281555},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3373943269252777},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.09116178750991821},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1801721664","https://openalex.org/W1933349210","https://openalex.org/W2080133951","https://openalex.org/W2094728533","https://openalex.org/W2620998106","https://openalex.org/W2891394954","https://openalex.org/W2963341956","https://openalex.org/W2963518342","https://openalex.org/W2964051877","https://openalex.org/W2964303913","https://openalex.org/W2966317026","https://openalex.org/W2996919866","https://openalex.org/W3034552680","https://openalex.org/W3035520037","https://openalex.org/W4224440661","https://openalex.org/W6638318767","https://openalex.org/W6639346155","https://openalex.org/W6679436768","https://openalex.org/W6690815549","https://openalex.org/W6714351100","https://openalex.org/W6726873649","https://openalex.org/W6732742072","https://openalex.org/W6745779156","https://openalex.org/W6748054437","https://openalex.org/W6752083267","https://openalex.org/W6779099115","https://openalex.org/W6855009501"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2117210722","https://openalex.org/W2589759689","https://openalex.org/W4405141166","https://openalex.org/W1978191894","https://openalex.org/W2390279801","https://openalex.org/W2018045843","https://openalex.org/W4391913857"],"abstract_inverted_index":{"Exploring":[0],"multimodal":[1],"information":[2,81],"from":[3],"external":[4,52],"knowledge":[5,53],"bases":[6],"in":[7,28],"Visual":[8],"Question":[9],"Answering":[10],"(VQA)":[11],"reasoning":[12],"tasks":[13],"presents":[14],"a":[15,65,101],"significant":[16],"challenge.":[17],"Current":[18],"methods,":[19],"such":[20],"as":[21],"attention-based":[22],"and":[23,49,115,127],"graph-based":[24],"approaches,":[25],"have":[26],"limitations":[27],"effectively":[29],"capturing":[30],"contextual":[31,80],"key":[32],"information.":[33],"It":[34],"is":[35,121],"essential":[36],"to":[37,54,111],"enhance":[38,112],"the":[39,44,47,50,76,79,90],"model\u2019s":[40],"cognitive":[41],"understanding":[42],"of":[43],"associations":[45],"between":[46],"question":[48],"corresponding":[51],"improve":[55,116],"accuracy.":[56],"To":[57],"overcome":[58],"these":[59],"challenges,":[60],"this":[61],"paper":[62],"introduces":[63],"RECA,":[64],"Retention":[66],"Enhanced":[67],"Cross-modal":[68],"Attention":[69],"method":[70,120],"for":[71],"multi-hop":[72],"VQA":[73],"inspired":[74],"by":[75,89],"hypergraph.":[77],"Specifically,":[78],"after":[82],"cross-modal":[83],"attention":[84],"fusion":[85],"are":[86],"further":[87],"enhanced":[88],"proposed":[91],"retention":[92],"module":[93],"based":[94],"on":[95,123],"Retentive":[96],"Network.":[97],"Finally,":[98],"we":[99],"introduced":[100],"mimicry":[102],"loss":[103],"through":[104],"model":[105,110],"distillation.":[106],"This":[107],"enabled":[108],"our":[109],"collaborative":[113],"learning":[114],"generalisation":[117],"performance.":[118,132],"Our":[119],"evaluated":[122],"KVQA,":[124],"FVQA,":[125],"PQ,":[126],"PQL":[128],"datasets,":[129],"demonstrating":[130],"state-of-the-art":[131]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}