{"id":"https://openalex.org/W4399423104","doi":"https://doi.org/10.1145/3652583.3658108","title":"Semantic-guided RGB-Thermal Crowd Counting with Segment Anything Model","display_name":"Semantic-guided RGB-Thermal Crowd Counting with Segment Anything Model","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399423104","doi":"https://doi.org/10.1145/3652583.3658108"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658108","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658108","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658108","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658108","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001427581","display_name":"Yaqun Fang","orcid":"https://orcid.org/0009-0001-9065-968X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaqun Fang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0001-9065-968X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051477738","display_name":"Yi Fang Shi","orcid":"https://orcid.org/0009-0004-5460-5731"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Shi","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-5460-5731","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004613974","display_name":"Jia Bei","orcid":"https://orcid.org/0009-0008-3731-7294"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Bei","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-3731-7294","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084591510","display_name":"Tongwei Ren","orcid":"https://orcid.org/0000-0003-3092-424X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongwei Ren","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3092-424X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001427581"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.7142,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69628906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"570","last_page":"578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10331","display_name":"Video Surveillance and Tracking Methods","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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9943000078201294,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9898999929428101,"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":0.7978405952453613},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.7536550760269165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7323393225669861},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6842625737190247},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6128168702125549},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5577067136764526},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5272095203399658},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4773597717285156},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.46884098649024963},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4460863173007965},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.417985200881958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7978405952453613},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.7536550760269165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7323393225669861},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6842625737190247},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6128168702125549},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5577067136764526},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5272095203399658},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4773597717285156},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.46884098649024963},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4460863173007965},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.417985200881958},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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:10.1145/3652583.3658108","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658108","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658108","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658108","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658108","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658108","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4388298099","display_name":null,"funder_award_id":"021714380026","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7458595415","display_name":null,"funder_award_id":"62072232","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399423104.pdf","grobid_xml":"https://content.openalex.org/works/W4399423104.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1203557841","https://openalex.org/W1603934303","https://openalex.org/W2042718506","https://openalex.org/W2966271765","https://openalex.org/W2968848584","https://openalex.org/W3118306937","https://openalex.org/W3131500599","https://openalex.org/W3170335739","https://openalex.org/W3177211876","https://openalex.org/W3198843251","https://openalex.org/W4293519460","https://openalex.org/W4293523180","https://openalex.org/W4295832202","https://openalex.org/W4306955321","https://openalex.org/W4361802978","https://openalex.org/W4367663172","https://openalex.org/W4382567984","https://openalex.org/W4385757103","https://openalex.org/W4386159007","https://openalex.org/W4388129777","https://openalex.org/W4390874575","https://openalex.org/W4390874670","https://openalex.org/W4391109864","https://openalex.org/W6608466522"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W2793967660","https://openalex.org/W1522196789"],"abstract_inverted_index":{"RGB-Thermal":[0],"(RGB-T)":[1],"crowd":[2],"counting":[3,135],"leverages":[4],"the":[5,61,69,83,87,93,101,116,122,129,133,143],"complementary":[6],"nature":[7],"of":[8,73,86],"visible":[9],"light":[10],"and":[11,30,71,96,103,132],"thermal":[12,104],"modalities":[13,105],"for":[14],"accurate":[15],"counting.":[16],"However,":[17],"real-world":[18],"scenarios":[19],"often":[20],"introduce":[21],"challenges,":[22],"such":[23],"as":[24,32,42],"misidentifying":[25],"background":[26,72],"elements":[27],"like":[28],"trees":[29],"lampposts":[31],"individuals,":[33],"leading":[34],"to":[35,66,81,100,127],"inaccurate":[36],"counts.":[37],"Existing":[38],"methods":[39],"utilize":[40],"segmentation":[41,50],"a":[43,57],"preliminary":[44],"procedure,":[45],"which":[46],"is":[47,125],"constrained":[48],"by":[49,78],"accuracy.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,76,91],"propose":[56],"novel":[58],"method,":[59],"utilizing":[60,79],"Segment":[62],"Anything":[63],"Model":[64],"(SAM),":[65],"distinguish":[67],"between":[68],"foreground":[70],"images.":[74],"Specifically,":[75],"begin":[77],"SAM":[80],"obtain":[82],"semantic":[84,97],"map":[85,131],"original":[88],"image.":[89],"Subsequently,":[90],"extract":[92],"modality":[94],"features":[95,98,111],"corresponding":[99],"RGB":[102],"through":[106],"multimodal":[107],"feature":[108],"extraction.":[109],"These":[110],"are":[112],"then":[113],"fused":[114],"using":[115],"Semantic-guide":[117],"Feature":[118],"Fusion":[119],"module.":[120],"Finally,":[121],"Multi-level":[123],"Decoder":[124],"employed":[126],"generate":[128],"density":[130],"ultimate":[134],"results.":[136],"Our":[137],"approach":[138],"achieves":[139],"state-of-the-art":[140],"performance":[141],"on":[142],"RGBT-CC":[144],"dataset.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}