{"id":"https://openalex.org/W7135010542","doi":"https://doi.org/10.1109/tcsvt.2026.3672884","title":"Unifying Modality and Scale: Visual Mamba for Feature Fusion in RGB-X Crowd Counting","display_name":"Unifying Modality and Scale: Visual Mamba for Feature Fusion in RGB-X Crowd Counting","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135010542","doi":"https://doi.org/10.1109/tcsvt.2026.3672884"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3672884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3672884","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5004027683","display_name":"Yaocong Hu","orcid":"https://orcid.org/0000-0001-9332-7528"},"institutions":[{"id":"https://openalex.org/I70908550","display_name":"Anhui Polytechnic University","ror":"https://ror.org/041sj0284","country_code":"CN","type":"education","lineage":["https://openalex.org/I70908550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaocong Hu","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception, Anhui Polytechnic University, Wuhu, China"],"raw_orcid":"https://orcid.org/0000-0001-9332-7528","affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception, Anhui Polytechnic University, Wuhu, China","institution_ids":["https://openalex.org/I70908550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128880716","display_name":"Mengbo Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I70908550","display_name":"Anhui Polytechnic University","ror":"https://ror.org/041sj0284","country_code":"CN","type":"education","lineage":["https://openalex.org/I70908550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengbo Jia","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception, Anhui Polytechnic University, Wuhu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception, Anhui Polytechnic University, Wuhu, China","institution_ids":["https://openalex.org/I70908550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146706499","display_name":"Pindeng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I70908550","display_name":"Anhui Polytechnic University","ror":"https://ror.org/041sj0284","country_code":"CN","type":"education","lineage":["https://openalex.org/I70908550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pindeng Wang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception, Anhui Polytechnic University, Wuhu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception, Anhui Polytechnic University, Wuhu, China","institution_ids":["https://openalex.org/I70908550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002562155","display_name":"Ning Jiang","orcid":"https://orcid.org/0000-0002-1286-0839"},"institutions":[{"id":"https://openalex.org/I70908550","display_name":"Anhui Polytechnic University","ror":"https://ror.org/041sj0284","country_code":"CN","type":"education","lineage":["https://openalex.org/I70908550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Jiang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception, Anhui Polytechnic University, Wuhu, China"],"raw_orcid":"https://orcid.org/0000-0002-1286-0839","affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Advanced Detection and Intelligent Perception, Anhui Polytechnic University, Wuhu, China","institution_ids":["https://openalex.org/I70908550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128839678","display_name":"Ke Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I70908550","display_name":"Anhui Polytechnic University","ror":"https://ror.org/041sj0284","country_code":"CN","type":"education","lineage":["https://openalex.org/I70908550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Xu","raw_affiliation_strings":["School of Integrated Circuits, Anhui Polytechnic University, Wuhu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Anhui Polytechnic University, Wuhu, China","institution_ids":["https://openalex.org/I70908550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026220866","display_name":"Wenbo Zhu","orcid":"https://orcid.org/0000-0002-4474-4752"},"institutions":[{"id":"https://openalex.org/I70908550","display_name":"Anhui Polytechnic University","ror":"https://ror.org/041sj0284","country_code":"CN","type":"education","lineage":["https://openalex.org/I70908550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Zhu","raw_affiliation_strings":["School of Integrated Circuits, Anhui Polytechnic University, Wuhu, China"],"raw_orcid":"https://orcid.org/0000-0002-4474-4752","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Anhui Polytechnic University, Wuhu, China","institution_ids":["https://openalex.org/I70908550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128884973","display_name":"Chao Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I167027274","display_name":"Nanjing Forestry University","ror":"https://ror.org/03m96p165","country_code":"CN","type":"education","lineage":["https://openalex.org/I167027274"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Xie","raw_affiliation_strings":["College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7542-1270","affiliations":[{"raw_affiliation_string":"College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing, China","institution_ids":["https://openalex.org/I167027274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033741559","display_name":"Huanjie Tao","orcid":"https://orcid.org/0000-0002-1453-2468"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanjie Tao","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085987622","display_name":"Tianming Ni","orcid":"https://orcid.org/0000-0001-6272-8660"},"institutions":[{"id":"https://openalex.org/I70908550","display_name":"Anhui Polytechnic University","ror":"https://ror.org/041sj0284","country_code":"CN","type":"education","lineage":["https://openalex.org/I70908550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianming Ni","raw_affiliation_strings":["School of Integrated Circuits, Anhui Polytechnic University, Wuhu, China"],"raw_orcid":"https://orcid.org/0000-0001-6272-8660","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Anhui Polytechnic University, Wuhu, China","institution_ids":["https://openalex.org/I70908550"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100416750","display_name":"Teng Li","orcid":"https://orcid.org/0000-0003-0111-0108"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Li","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0111-0108","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16846404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"7","first_page":"10577","last_page":"10590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.33070001006126404,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.33070001006126404,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.267300009727478,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.043299999088048935,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6904000043869019},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5153999924659729},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5015000104904175},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4153999984264374},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4023999869823456},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3725000023841858}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.711899995803833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7045000195503235},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6904000043869019},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5192999839782715},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5153999924659729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3672884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3672884","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5170755150","display_name":null,"funder_award_id":"62203012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6563427075","display_name":null,"funder_award_id":"U25A20486","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W2105934661","https://openalex.org/W2316109659","https://openalex.org/W2463631526","https://openalex.org/W2565639579","https://openalex.org/W2895051362","https://openalex.org/W2949333977","https://openalex.org/W2962898354","https://openalex.org/W2963767186","https://openalex.org/W2964209782","https://openalex.org/W3004672782","https://openalex.org/W3110089972","https://openalex.org/W3131500599","https://openalex.org/W3152836081","https://openalex.org/W3177211876","https://openalex.org/W3203845557","https://openalex.org/W3210983250","https://openalex.org/W4205315370","https://openalex.org/W4225264236","https://openalex.org/W4226404986","https://openalex.org/W4283312418","https://openalex.org/W4285229583","https://openalex.org/W4295832202","https://openalex.org/W4313182800","https://openalex.org/W4317754346","https://openalex.org/W4321505055","https://openalex.org/W4361802978","https://openalex.org/W4383503678","https://openalex.org/W4385757103","https://openalex.org/W4386065414","https://openalex.org/W4387623954","https://openalex.org/W4389076493","https://openalex.org/W4391020313","https://openalex.org/W4391582439","https://openalex.org/W4394567758","https://openalex.org/W4394625572","https://openalex.org/W4395017574","https://openalex.org/W4399618753","https://openalex.org/W4399990758","https://openalex.org/W4400111301","https://openalex.org/W4402952320","https://openalex.org/W4403977303","https://openalex.org/W4405531479","https://openalex.org/W4405897510","https://openalex.org/W4406163025","https://openalex.org/W4406457474","https://openalex.org/W4406517291","https://openalex.org/W4406857697","https://openalex.org/W4406947007","https://openalex.org/W4407360833","https://openalex.org/W4407638717","https://openalex.org/W4408323584","https://openalex.org/W4408519713","https://openalex.org/W4408703306","https://openalex.org/W4409366556","https://openalex.org/W4409427764","https://openalex.org/W4412445010","https://openalex.org/W4413147024","https://openalex.org/W4413465567","https://openalex.org/W4414243662","https://openalex.org/W4414540732","https://openalex.org/W4414837197","https://openalex.org/W4415796023","https://openalex.org/W7124419417","https://openalex.org/W7125428527","https://openalex.org/W7160063680"],"related_works":[],"abstract_inverted_index":{"Crowd":[0],"counting":[1,30],"has":[2,31],"long":[3],"been":[4],"a":[5,34,60,75],"crucial":[6],"topic":[7],"in":[8,50,66,106],"the":[9,20,46,89,115,123,132,168],"domains":[10],"of":[11,23,63],"computer":[12],"vision":[13],"and":[14,55,103,149],"video":[15],"surveillance.":[16],"In":[17],"particular,":[18],"with":[19,152],"widespread":[21],"use":[22],"thermal":[24],"or":[25,40],"depth":[26,39],"cameras,":[27],"RGB-X":[28,175],"crowd":[29,64,84,176],"emerged":[32],"as":[33],"prominent":[35],"research":[36],"focus.":[37],"Although":[38],"infrared":[41],"images":[42],"provide":[43],"complementary":[44],"information,":[45],"core":[47],"challenge":[48],"remains":[49],"effectively":[51],"unifying":[52],"heterogeneous":[53],"cross-modality":[54,90],"cross-scale":[56,119,124],"information":[57],"to":[58,100,136],"form":[59],"comprehensive":[61],"representation":[62],"distributions":[65],"complex":[67],"scenes.":[68],"To":[69],"address":[70],"this":[71],"problem,":[72],"we":[73,87,121],"propose":[74],"novel":[76],"Mamba-based":[77],"framework,":[78],"termed":[79],"UMS-VMamba-CC":[80,169],"for":[81,174],"multi-modal":[82,111],"(RGB-X)":[83],"counting.":[85,177],"Specifically,":[86],"design":[88,122],"disentanglement":[91],"fusion":[92,126],"visual":[93,127],"Mamba":[94,128],"(CMDF-VMamba)":[95],"that":[96,167],"uses":[97],"self-supervised":[98],"learning":[99],"decompose":[101],"modality-invariant":[102],"modality-specific":[104],"features":[105,139,148,154],"spatial-frequency":[107],"domains,":[108],"followed":[109],"by":[110],"feature":[112],"aggregation":[113],"via":[114],"gating":[116],"mechanism.":[117],"For":[118],"fusion,":[120],"pyramid":[125,134],"(CSPF-VMamba),":[129],"which":[130],"adopts":[131],"bi-directional":[133],"structure":[135],"incorporate":[137],"low-level":[138,153],"into":[140],"high-level":[141,147],"representations":[142],"during":[143],"downsampling,":[144],"while":[145],"upsampling":[146],"aggregating":[150],"them":[151],"through":[155],"state":[156],"space":[157],"contextual":[158],"modeling.":[159],"Comprehensive":[160],"experiments":[161],"on":[162],"multiple":[163],"mainstream":[164],"datasets":[165],"demonstrate":[166],"framework":[170],"achieves":[171],"competitive":[172],"performance":[173]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-03-13T00:00:00"}