{"id":"https://openalex.org/W7125976977","doi":"https://doi.org/10.1109/smc58881.2025.11343307","title":"AugCount: Test-Time Semantic Augmentation via Diffusion for General Open-World Object Counting","display_name":"AugCount: Test-Time Semantic Augmentation via Diffusion for General Open-World Object Counting","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125976977","doi":"https://doi.org/10.1109/smc58881.2025.11343307"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":null,"display_name":"Ziqiang Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziqiang Shi","raw_affiliation_strings":["Fujitsu Research & Development Center Co.,LTD.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Fujitsu Research & Development Center Co.,LTD.,Beijing,China","institution_ids":["https://openalex.org/I4210159607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115916756","display_name":"Rujie Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159607","display_name":"Fujitsu (China)","ror":"https://ror.org/04w4yzw62","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159607"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rujie Liu","raw_affiliation_strings":["Fujitsu Research & Development Center Co.,LTD.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Fujitsu Research & Development Center Co.,LTD.,Beijing,China","institution_ids":["https://openalex.org/I4210159607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124090870","display_name":"Jun Takahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Takahashi","raw_affiliation_strings":["Fujitsu Research,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Research,Tokyo,Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124120353","display_name":"Shan Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shan Jiang","raw_affiliation_strings":["Fujitsu Research,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Research,Tokyo,Japan","institution_ids":["https://openalex.org/I2252096349"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159607"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70788644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"822","last_page":"828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.3862999975681305,"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":0.3862999975681305,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.15639999508857727,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.055799998342990875,"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/robustness","display_name":"Robustness (evolution)","score":0.756600022315979},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6215000152587891},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5562999844551086},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5370000004768372},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4810999929904938},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.43529999256134033},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4162999987602234},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4074000120162964}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.756600022315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470999956130981},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6215000152587891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6018999814987183},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5370000004768372},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.43529999256134033},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40549999475479126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.382999986410141},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.36160001158714294},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.34529998898506165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34450000524520874},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3116999864578247},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.28450000286102295}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4766910970211029,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W3170764266","https://openalex.org/W4312933868","https://openalex.org/W4385775296","https://openalex.org/W4386076390","https://openalex.org/W4387210975","https://openalex.org/W4390873054","https://openalex.org/W4390873321","https://openalex.org/W4390873375","https://openalex.org/W4393158196","https://openalex.org/W4402703087","https://openalex.org/W4402727874","https://openalex.org/W4403878713","https://openalex.org/W4404612908","https://openalex.org/W7103755574"],"related_works":[],"abstract_inverted_index":{"Open-world":[0],"general":[1,88],"object":[2,40,57,85,89],"counting":[3,58,100,117,146],"is":[4,28,93],"a":[5,51,73,125],"critical":[6],"task":[7],"in":[8,13],"computer":[9],"vision,":[10],"with":[11],"applications":[12],"image":[14,122],"understanding,":[15],"environmental":[16],"monitoring,":[17],"and":[18,30,34,42,96,123,135,142],"surveillance.":[19],"Traditional":[20],"methods":[21],"rely":[22],"on":[23,81,109],"large-scale":[24],"annotated":[25],"data,":[26],"which":[27],"expensive":[29],"time-consuming":[31],"to":[32,37,76,98],"obtain,":[33],"often":[35],"fail":[36],"manage":[38],"diverse":[39,62],"categories":[41],"complex":[43],"scenes.":[44],"To":[45],"address":[46],"this,":[47],"we":[48,71],"propose":[49],"AugCount,":[50],"novel":[52],"framework":[53,92],"that":[54,104],"enhances":[55],"open-world":[56],"by":[59,119],"generating":[60],"high-quality,":[61],"synthetic":[63],"data":[64,133],"during":[65],"testing.":[66],"For":[67],"the":[68,115],"first":[69],"time,":[70],"employ":[72],"diffusion":[74],"model":[75,136],"produce":[77],"conditional":[78],"images":[79],"based":[80],"density":[82],"maps":[83],"specifying":[84],"locations":[86],"for":[87,144],"counting.":[90],"Our":[91],"highly":[94],"versatile":[95],"adaptable":[97],"various":[99],"tasks.":[101],"Experiments":[102],"demonstrate":[103],"AugCount":[105,130],"significantly":[106],"improves":[107],"performance":[108],"benchmark":[110],"datasets":[111],"like":[112],"FSC-147,":[113],"reducing":[114],"average":[116],"error":[118],"1":[120],"per":[121],"achieving":[124],"state-of-the-art":[126],"MAE":[127],"of":[128],"4.70.":[129],"effectively":[131],"addresses":[132],"scarcity":[134],"generalization":[137],"challenges,":[138],"offering":[139],"enhanced":[140],"robustness":[141],"adaptability":[143],"practical":[145],"systems.":[147]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-01-29T00:00:00"}