{"id":"https://openalex.org/W4385775296","doi":"https://doi.org/10.1145/3581783.3611789","title":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","display_name":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4385775296","doi":"https://doi.org/10.1145/3581783.3611789"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611789","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","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/A5066227057","display_name":"Ruixiang Jiang","orcid":"https://orcid.org/0000-0001-8666-6767"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Ruixiang Jiang","raw_affiliation_strings":["The Hong Kong Polytechnic University, HKSAR, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, HKSAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102971183","display_name":"Lingbo Liu","orcid":"https://orcid.org/0000-0001-8179-6685"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lingbo Liu","raw_affiliation_strings":["The Hong Kong Polytechnic University, HKSAR, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, HKSAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002277899","display_name":"Chang Wen Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Changwen Chen","raw_affiliation_strings":["The Hong Kong Polytechnic University, HKSAR, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, HKSAR, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066227057"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":10.7053,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.98792816,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4535","last_page":"4545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9918000102043152,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9918000102043152,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9890999794006348,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9882000088691711,"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/zero","display_name":"Zero (linguistics)","score":0.6634650230407715},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6193458437919617},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6119505167007446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.560179591178894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46046018600463867},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.331587553024292}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6634650230407715},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6193458437919617},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6119505167007446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.560179591178894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46046018600463867},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.331587553024292},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611789","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2463631526","https://openalex.org/W2962854645","https://openalex.org/W2962921175","https://openalex.org/W2963035940","https://openalex.org/W2965247173","https://openalex.org/W2982007926","https://openalex.org/W3032910121","https://openalex.org/W3095336680","https://openalex.org/W3120979957","https://openalex.org/W3159481202","https://openalex.org/W3170764266","https://openalex.org/W3177211876","https://openalex.org/W3198377975","https://openalex.org/W3201927751","https://openalex.org/W3216551675","https://openalex.org/W4214926101","https://openalex.org/W4221148940","https://openalex.org/W4221160666","https://openalex.org/W4226058394","https://openalex.org/W4287073179","https://openalex.org/W4312310776","https://openalex.org/W4312563428","https://openalex.org/W4312818263","https://openalex.org/W6600234944","https://openalex.org/W6600741150","https://openalex.org/W6717243457"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,67],"visual-language":[3],"models":[4,26,43],"have":[5],"shown":[6],"remarkable":[7],"zero-shot":[8,69],"text-image":[9],"matching":[10],"ability":[11],"that":[12,57,86],"is":[13,161],"transferable":[14],"to":[15,90,107],"downstream":[16],"tasks":[17],"such":[18],"as":[19],"object":[20,28,47],"detection":[21],"and":[22,146,154],"segmentation.":[23],"Adapting":[24],"these":[25],"for":[27,45,61,96,139],"counting,":[29],"however,":[30],"remains":[31],"a":[32,68,82,102],"formidable":[33],"challenge.":[34],"In":[35],"this":[36],"study,":[37],"we":[38,50,80,100],"first":[39,54],"investigate":[40],"transferring":[41],"vision-language":[42],"(VLMs)":[44],"class-agnostic":[46],"counting.":[48],"Specifically,":[49],"propose":[51],"CLIP-Count,":[52],"the":[53,73,88,120,124,157],"end-to-end":[55],"pipeline":[56],"estimates":[58],"density":[59,137],"maps":[60,138],"open-vocabulary":[62],"objects":[63],"with":[64,76],"text":[65,74],"guidance":[66],"manner.":[70],"To":[71],"align":[72],"embedding":[75],"dense":[77,97],"visual":[78,94,116],"features,":[79],"introduce":[81],"patch-text":[83,104],"contrastive":[84],"loss":[85],"guides":[87],"model":[89],"learn":[91],"informative":[92],"patch-level":[93],"representations":[95],"prediction.":[98],"Moreover,":[99],"design":[101],"hierarchical":[103],"interaction":[105],"module":[106],"propagate":[108],"semantic":[109],"information":[110],"across":[111],"different":[112],"resolution":[113],"levels":[114],"of":[115,123,129,156],"features.":[117],"Benefiting":[118],"from":[119],"full":[121],"exploitation":[122],"rich":[125],"image-text":[126],"alignment":[127],"knowledge":[128],"pretrained":[130],"VLMs,":[131],"our":[132],"method":[133],"effectively":[134],"generates":[135],"high-quality":[136],"objects-of-interest.":[140],"Extensive":[141],"experiments":[142],"on":[143],"FSC-147,":[144],"CARPK,":[145],"ShanghaiTech":[147],"crowd":[148],"counting":[149],"datasets":[150],"demonstrate":[151],"state-of-the-art":[152],"accuracy":[153],"generalizability":[155],"proposed":[158],"method.":[159],"Code":[160],"available:":[162],"https://github.com/songrise/CLIP-Count.":[163,164]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":31},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}