{"id":"https://openalex.org/W4408345989","doi":"https://doi.org/10.1109/icassp49660.2025.10888334","title":"Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection","display_name":"Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345989","doi":"https://doi.org/10.1109/icassp49660.2025.10888334"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888334","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":"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/A5016488014","display_name":"H Wang","orcid":"https://orcid.org/0000-0003-3934-0224"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxuan Wang","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Laboratory of Data Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Data Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010996897","display_name":"Qingdong He","orcid":"https://orcid.org/0000-0003-3203-0071"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingdong He","raw_affiliation_strings":["Tencent Youtu Lab,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101873531","display_name":"Jinlong Peng","orcid":"https://orcid.org/0009-0003-1887-6406"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Peng","raw_affiliation_strings":["Tencent Youtu Lab,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078840193","display_name":"Hao Yang","orcid":"https://orcid.org/0009-0007-0032-4186"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057267422","display_name":"Mingmin Chi","orcid":"https://orcid.org/0000-0003-2650-4146"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingmin Chi","raw_affiliation_strings":["Fudan University,School of Computer Science, Shanghai Key Laboratory of Data Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science, Shanghai Key Laboratory of Data Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabiao Wang","raw_affiliation_strings":["Tencent Youtu Lab,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab,China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.4032,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.99363545,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9678999781608582,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9678999781608582,"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":0.5446507334709167},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4603635370731354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34892046451568604},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.070333331823349}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5446507334709167},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4603635370731354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34892046451568604},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.070333331823349},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888334","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2948672349","https://openalex.org/W2963037989","https://openalex.org/W2963518342","https://openalex.org/W2983943451","https://openalex.org/W3096609285","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3173859428","https://openalex.org/W4312956471","https://openalex.org/W4386076029","https://openalex.org/W4386076396","https://openalex.org/W4402716047","https://openalex.org/W4404612908","https://openalex.org/W4404792981","https://openalex.org/W4409365576","https://openalex.org/W6620707391","https://openalex.org/W6730365400","https://openalex.org/W6764322716","https://openalex.org/W6784094891","https://openalex.org/W6789992408","https://openalex.org/W6802517928","https://openalex.org/W6803444062","https://openalex.org/W6809665764","https://openalex.org/W6811013733","https://openalex.org/W6842874653","https://openalex.org/W6851592950","https://openalex.org/W6856826615","https://openalex.org/W6859298233","https://openalex.org/W6861342692","https://openalex.org/W6861387779","https://openalex.org/W6862565613","https://openalex.org/W6868789466","https://openalex.org/W6869726950","https://openalex.org/W6869952813"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Open-vocabulary":[0],"detection":[1],"(OVD)":[2],"aims":[3],"to":[4,119],"detect":[5],"objects":[6],"beyond":[7],"a":[8,14,61,91,97],"predefined":[9],"set":[10],"of":[11,90],"categories.":[12],"As":[13],"pioneering":[15],"model":[16,65,129],"incorporating":[17],"the":[18,45,49,67,121,131,135],"YOLO":[19],"series":[20],"into":[21],"OVD,":[22],"YOLO-World":[23,133],"is":[24,35],"well-suited":[25],"for":[26],"scenarios":[27],"prioritizing":[28],"speed":[29],"and":[30,48,96,105,115,137,143,150,162],"efficiency.":[31],"However,":[32],"its":[33,38,75],"performance":[34],"hindered":[36],"by":[37],"neck":[39,76],"feature":[40,86],"fusion":[41,87],"mechanism,":[42],"which":[43],"causes":[44],"quadratic":[46],"complexity":[47,104],"limited":[50],"guided":[51,107],"receptive":[52,108],"fields.":[53,109],"To":[54],"address":[55],"these":[56],"limitations,":[57],"we":[58,79],"present":[59],"Mamba-YOLO-World,":[60],"novel":[62],"YOLO-based":[63],"OVD":[64,157],"employing":[66],"proposed":[68],"MambaFusion":[69],"Path":[70],"Aggregation":[71],"Network":[72],"(MambaFusion-PAN)":[73],"as":[74],"architecture.":[77],"Specifically,":[78],"introduce":[80],"an":[81],"innovative":[82],"State":[83],"Space":[84],"Model-based":[85],"mechanism":[88],"consisting":[89],"Parallel-Guided":[92],"Selective":[93,99],"Scan":[94,100],"algorithm":[95,101],"Serial-Guided":[98],"with":[102,159],"linear":[103],"globally":[106],"It":[110],"leverages":[111],"multi-modal":[112],"input":[113],"sequences":[114],"mamba":[116],"hidden":[117],"states":[118],"guide":[120],"selective":[122],"scanning":[123],"process.":[124],"Experiments":[125],"demonstrate":[126],"that":[127],"our":[128],"outperforms":[130],"original":[132],"on":[134],"COCO":[136],"LVIS":[138],"benchmarks":[139],"in":[140],"both":[141],"zero-shot":[142],"fine-tuning":[144],"settings":[145],"while":[146],"maintaining":[147],"comparable":[148],"parameters":[149,161],"FLOPs.":[151,163],"Additionally,":[152],"it":[153],"surpasses":[154],"existing":[155],"state-of-the-art":[156],"methods":[158],"fewer":[160]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}