{"id":"https://openalex.org/W4415708471","doi":"https://doi.org/10.1109/icme59968.2025.11209330","title":"AMS-Counter: Text-Guided Zero-shot Object Counting via Adaptive Multi-view Similarity-map","display_name":"AMS-Counter: Text-Guided Zero-shot Object Counting via Adaptive Multi-view Similarity-map","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708471","doi":"https://doi.org/10.1109/icme59968.2025.11209330"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209330","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 Multimedia and Expo (ICME)","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/A5102692407","display_name":"Cheng Qian","orcid":"https://orcid.org/0009-0007-1290-4516"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Qian","raw_affiliation_strings":["Chongqing University,School of Big Data & Software Engineering,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University,School of Big Data & Software Engineering,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602897","display_name":"Jian Cao","orcid":"https://orcid.org/0000-0001-8903-2903"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiwu Cao","raw_affiliation_strings":["University of Glasgow,School of Engineering,Glasgow,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Engineering,Glasgow,UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107985523","display_name":"Ying Mao","orcid":"https://orcid.org/0000-0001-8055-115X"},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Mao","raw_affiliation_strings":["Southwest University of Science and Technology,School of Computer Science and Technology,Mianyang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University of Science and Technology,School of Computer Science and Technology,Mianyang,China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399798","display_name":"Kai Liu","orcid":"https://orcid.org/0000-0001-5951-2164"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Liu","raw_affiliation_strings":["Chongqing University,School of Big Data & Software Engineering,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University,School of Big Data & Software Engineering,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040957883","display_name":"Peng Zhu","orcid":"https://orcid.org/0000-0001-9558-3787"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhu","raw_affiliation_strings":["Chongqing University,School of Big Data & Software Engineering,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University,School of Big Data & Software Engineering,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049656956","display_name":"Jun Sang","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Sang","raw_affiliation_strings":["Chongqing University,School of Big Data & Software Engineering,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University,School of Big Data & Software Engineering,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34468095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.19370000064373016,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.19370000064373016,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.15289999544620514,"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":0.13830000162124634,"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/object","display_name":"Object (grammar)","score":0.6348999738693237},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.572700023651123},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5134999752044678},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4952999949455261},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.46650001406669617},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44609999656677246},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44530001282691956},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.43639999628067017},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.43059998750686646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7671999931335449},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6348999738693237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6039000153541565},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.572700023651123},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5134999752044678},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5069000124931335},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4952999949455261},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.46650001406669617},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44609999656677246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44530001282691956},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.42719998955726624},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4154999852180481},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3012000024318695},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209330","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":20,"referenced_works":["https://openalex.org/W2463631526","https://openalex.org/W2520304734","https://openalex.org/W2734511492","https://openalex.org/W2962921175","https://openalex.org/W2994751959","https://openalex.org/W3120979957","https://openalex.org/W3170764266","https://openalex.org/W3182464672","https://openalex.org/W3194605760","https://openalex.org/W4312651322","https://openalex.org/W4322747315","https://openalex.org/W4383345852","https://openalex.org/W4385775296","https://openalex.org/W4386065414","https://openalex.org/W4386076390","https://openalex.org/W4390873023","https://openalex.org/W4390873375","https://openalex.org/W4390874114","https://openalex.org/W4393158196","https://openalex.org/W4403878713"],"related_works":[],"abstract_inverted_index":{"Text-guided":[0],"object":[1],"counting":[2,73,137],"aims":[3],"to":[4,22,31,104],"count":[5],"objects":[6],"specified":[7],"by":[8,75],"textual":[9,26],"descriptions":[10],"in":[11,79,136],"images,":[12],"but":[13],"current":[14],"methods":[15,42],"often":[16],"rely":[17],"on":[18,98,123],"simple":[19],"cosine":[20],"similarity":[21,45],"align":[23],"visual":[24],"and":[25,55,82],"embeddings,":[27],"limiting":[28],"their":[29],"ability":[30],"capture":[32,105],"complex":[33],"relationships.":[34],"While":[35],"some":[36],"studies":[37],"have":[38],"explored":[39],"more":[40],"advanced":[41],"for":[43,93],"constructing":[44],"maps,":[46],"they":[47],"still":[48],"fall":[49],"short":[50],"of":[51],"effectively":[52,87,116],"leveraging":[53],"multi-scale":[54],"multi-layered":[56,106],"information.":[57],"To":[58],"address":[59],"this,":[60],"we":[61],"propose":[62,109],"AMS-Counter":[63,108,129],"(Adaptive":[64],"Multi-view":[65,101],"Similarity-map":[66,102],"Counter),":[67],"a":[68,110],"novel":[69],"framework":[70],"that":[71,115,128],"enhances":[72],"accuracy":[74],"fusing":[76],"multi-view":[77],"features":[78,86],"both":[80],"spatial":[81],"frequency":[83],"domains.":[84],"Frequency":[85],"represent":[88],"the":[89,99,124],"structural":[90],"information":[91,118],"necessary":[92],"precise":[94],"image":[95],"understanding.":[96],"Building":[97],"Adaptive":[100],"(AMS)":[103],"features,":[107],"U-shaped":[111],"Cross-attention":[112],"Decoder":[113],"(UC-Decoder)":[114],"integrates":[117],"across":[119],"multiple":[120],"scales.":[121],"Evaluations":[122],"FSC-147":[125],"benchmark":[126],"demonstrate":[127],"achieves":[130],"state-of-the-art":[131],"performance,":[132],"with":[133],"notable":[134],"improvements":[135],"accuracy.":[138],"Code":[139],"is":[140],"available:":[141],"https://github.com/CPSDSC-Lab/AMS-Counter.":[142]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}