{"id":"https://openalex.org/W4411635672","doi":"https://doi.org/10.1145/3731715.3733474","title":"DSSM-KG: Dual-Stream State-Space Modeling with Adaptive Knowledge Injection for Video Captioning","display_name":"DSSM-KG: Dual-Stream State-Space Modeling with Adaptive Knowledge Injection for Video Captioning","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411635672","doi":"https://doi.org/10.1145/3731715.3733474"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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/A5104302595","display_name":"Haoying Sun","orcid":"https://orcid.org/0000-0002-0271-5515"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoying Sun","raw_affiliation_strings":["Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0271-5515","affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638587","display_name":"Shuyi Li","orcid":"https://orcid.org/0000-0001-6264-9006"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyi Li","raw_affiliation_strings":["Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6264-9006","affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050633196","display_name":"Zeyu Xi","orcid":"https://orcid.org/0000-0002-3181-6761"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Xi","raw_affiliation_strings":["Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3181-6761","affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bowen Zhang","orcid":"https://orcid.org/0009-0007-4464-8553"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Zhang","raw_affiliation_strings":["Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-4464-8553","affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005945981","display_name":"Lifang Wu","orcid":"https://orcid.org/0000-0002-7209-0215"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifang Wu","raw_affiliation_strings":["Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7209-0215","affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104302595"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":2.2665,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88610872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2038","last_page":"2042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987000226974487,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9948999881744385,"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/closed-captioning","display_name":"Closed captioning","score":0.8720464110374451},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.7099451422691345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7046253681182861},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45722854137420654},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4301726222038269},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.323150634765625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2798088788986206},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09189537167549133},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06680282950401306},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.058632105588912964}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8720464110374451},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7099451422691345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7046253681182861},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45722854137420654},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4301726222038269},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.323150634765625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2798088788986206},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09189537167549133},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06680282950401306},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.058632105588912964},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7693238454","display_name":null,"funder_award_id":"62236010,62306021","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1956340063","https://openalex.org/W2425121537","https://openalex.org/W2561529111","https://openalex.org/W3035365026","https://openalex.org/W3176425931","https://openalex.org/W3205021045","https://openalex.org/W4214540501","https://openalex.org/W4236965008","https://openalex.org/W4382464395","https://openalex.org/W4386057717","https://openalex.org/W4386234463","https://openalex.org/W4390874374","https://openalex.org/W4391454521","https://openalex.org/W4405436672","https://openalex.org/W4407856985"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Video":[0],"captioning":[1,157],"aims":[2],"to":[3,24,47,101,125],"generate":[4],"natural":[5],"language":[6],"descriptions":[7],"of":[8,41,140],"video":[9,156],"content.":[10],"Recent":[11],"methods":[12],"extract":[13],"temporal":[14],"and":[15,19,37,81,93,114,119,162],"spatial":[16],"information":[17,116],"separately":[18],"use":[20],"dataset-specific":[21,115],"prior":[22],"knowledge":[23,67,108,145],"enhance":[25],"caption":[26],"quality.":[27],"However,":[28],"they":[29],"may":[30],"be":[31],"inadequate":[32],"in":[33,78],"joint":[34,103],"spatiotemporal":[35,104],"modeling":[36],"lack":[38],"the":[39,50,72,76,86,94,123,127,137,144],"utilization":[40],"commonsense":[42,113],"knowledge,":[43],"making":[44],"it":[45],"difficult":[46],"fully":[48],"understand":[49],"video.":[51],"To":[52],"address":[53],"these":[54],"issues,":[55],"this":[56],"paper":[57],"proposes":[58],"a":[59,107],"dual-stream":[60,89,97],"state-space":[61,90,98],"model":[62,128],"(DSSM-KG)":[63],"based":[64],"on":[65,154],"cross-modal":[66],"injection.":[68],"Specifically,":[69],"by":[70],"integrating":[71],"heterogeneous":[73],"Mamba":[74],"with":[75,129,143],"Transformer":[77],"both":[79,112],"parallel":[80],"sequential":[82],"manners,":[83],"we":[84],"construct":[85],"spatially":[87],"enhanced":[88,96],"module":[91,99],"(S-DSSM)":[92],"temporally":[95],"(T-DSSM)":[100],"strengthen":[102],"modeling.":[105],"Additionally,":[106],"graph":[109],"that":[110,136],"integrates":[111],"is":[117],"constructed":[118],"adaptively":[120],"injected":[121],"into":[122],"decoder":[124],"furnish":[126],"extensive":[130],"video-related":[131],"knowledge.":[132],"Experimental":[133],"results":[134],"indicate":[135],"structural":[138],"designs":[139],"DSSM-KG,":[141],"together":[142],"injection":[146],"mechanism,":[147],"demonstrate":[148],"significant":[149],"efficacy,":[150],"yielding":[151],"competitive":[152],"performance":[153],"mainstream":[155],"datasets":[158],"such":[159],"as":[160],"MSVD":[161],"MSR-VTT.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}