{"id":"https://openalex.org/W4408353325","doi":"https://doi.org/10.1109/icassp49660.2025.10889987","title":"Density-aware and Depth-aware Visual Representation for Zero-Shot Object Counting","display_name":"Density-aware and Depth-aware Visual Representation for Zero-Shot Object Counting","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353325","doi":"https://doi.org/10.1109/icassp49660.2025.10889987"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"https://openalex.org/A5010125792","display_name":"Fang Nan","orcid":"https://orcid.org/0000-0001-5969-7066"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Nan","raw_affiliation_strings":["Xi’an Jiaotong University,Faculty of Electronic and Information Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Faculty of Electronic and Information Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013725152","display_name":"Feng Tian","orcid":"https://orcid.org/0000-0001-7888-0587"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Tian","raw_affiliation_strings":["Xi’an Jiaotong University,Faculty of Electronic and Information Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Faculty of Electronic and Information Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319347","display_name":"Ni Zhang","orcid":"https://orcid.org/0000-0002-6645-3366"},"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":"Ni Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Automation,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Automation,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377352","display_name":"Nian Liu","orcid":"https://orcid.org/0000-0002-0825-6081"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Nian Liu","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence,Computer Vision Department,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence,Computer Vision Department,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111675019","display_name":"Haonan Miao","orcid":"https://orcid.org/0009-0007-3849-4113"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Miao","raw_affiliation_strings":["Xi’an Jiaotong University,Faculty of Electronic and Information Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Faculty of Electronic and Information Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102152323","display_name":"Guang Dai","orcid":"https://orcid.org/0000-0002-3529-9087"},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Dai","raw_affiliation_strings":["State Grid Corporation of China,SGIT AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Corporation of China,SGIT AI Lab","institution_ids":["https://openalex.org/I17442442"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100429675","display_name":"Mengmeng Wang","orcid":"https://orcid.org/0000-0002-9890-8900"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengmeng Wang","raw_affiliation_strings":["Zhejiang University of Technology,Hang Zhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology,Hang Zhou,China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.864,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73168471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9939000010490417,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9861999750137329,"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/shot","display_name":"Shot (pellet)","score":0.6864365339279175},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6651871204376221},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6207643747329712},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6118033528327942},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5834460258483887},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.518354058265686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48844829201698303},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3257526159286499}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6864365339279175},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6651871204376221},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6207643747329712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6118033528327942},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5834460258483887},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.518354058265686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48844829201698303},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3257526159286499},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2962689769","https://openalex.org/W2977057439","https://openalex.org/W3047585969","https://openalex.org/W3106732900","https://openalex.org/W3170764266","https://openalex.org/W3210983250","https://openalex.org/W4221148940","https://openalex.org/W4221160666","https://openalex.org/W4226204049","https://openalex.org/W4312423884","https://openalex.org/W4312826597","https://openalex.org/W4321353653","https://openalex.org/W4385775296","https://openalex.org/W4386065414","https://openalex.org/W4386076390","https://openalex.org/W4387950844","https://openalex.org/W4390873375","https://openalex.org/W4393148727","https://openalex.org/W4393153748","https://openalex.org/W4393158196","https://openalex.org/W4394625558","https://openalex.org/W4402667892","https://openalex.org/W4402727478","https://openalex.org/W4402780099","https://openalex.org/W4403878713","https://openalex.org/W4405126873","https://openalex.org/W4409262392","https://openalex.org/W6843087422","https://openalex.org/W6853562887","https://openalex.org/W6866439361"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W1834370135"],"abstract_inverted_index":{"Previous":[0],"methods":[1],"often":[2],"utilize":[3],"CLIP":[4],"semantic":[5],"classifiers":[6],"with":[7,52,103],"class":[8],"names":[9],"for":[10,22,65],"zero-shot":[11],"object":[12],"counting.":[13],"However,":[14],"they":[15],"ignore":[16],"crucial":[17],"density":[18,37,94],"and":[19,30,48,69,78,86,89,107],"depth":[20,50],"knowledge":[21],"counting":[23,33,67],"tasks.":[24],"Thus,":[25],"we":[26,61,97],"propose":[27],"a":[28,99],"density-aware":[29,41,45],"depth-aware":[31,54],"prompt":[32],"model,":[34],"which":[35],"captures":[36],"information":[38],"via":[39],"learning":[40],"prompts":[42],"based":[43],"on":[44,84],"contrastive":[46,71],"loss":[47,68],"incorporates":[49],"guidance":[51],"predefined":[53],"prompts.":[55],"To":[56],"facilitate":[57],"the":[58,70,74,90,116,120],"training":[59],"process,":[60],"design":[62],"two":[63],"strategies":[64],"standard":[66],"loss,":[72],"where":[73],"former":[75],"prioritizes":[76],"larger":[77],"sparser":[79],"objects":[80],"initially,":[81],"gradually":[82],"focusing":[83],"smaller":[85],"denser":[87],"objects,":[88],"latter":[91],"adopts":[92],"coarse-to-fine":[93],"learning.":[95],"Besides,":[96],"construct":[98],"dataset":[100],"named":[101],"LVIS-372":[102],"more":[104],"real-world":[105],"scenarios":[106],"balanced":[108],"instance":[109],"distribution":[110],"compared":[111],"to":[112],"existing":[113],"ones.":[114],"Finally,":[115],"experimental":[117],"results":[118],"demonstrate":[119],"effectiveness":[121],"of":[122],"our":[123],"proposed":[124],"method.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}