{"id":"https://openalex.org/W4415310295","doi":"https://doi.org/10.1145/3746027.3754707","title":"Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selection","display_name":"Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415310295","doi":"https://doi.org/10.1145/3746027.3754707"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754707","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754707","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754707","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100696195","display_name":"Jingyao Wang","orcid":"https://orcid.org/0000-0003-1782-8704"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingyao Wang","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiming Chen","orcid":"https://orcid.org/0009-0005-0873-3078"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Chen","raw_affiliation_strings":["Beijing University of Technology, Beijing, China and Institute of Software Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China and Institute of Software Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003513450","display_name":"Lingyu Si","orcid":"https://orcid.org/0000-0002-7735-6676"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyu Si","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062168363","display_name":"Changwen Zheng","orcid":"https://orcid.org/0000-0002-2311-6757"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changwen Zheng","raw_affiliation_strings":["Institute of Software Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100696195"],"corresponding_institution_ids":["https://openalex.org/I4210128818"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2812538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2663","last_page":"2672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9864000082015991,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9864000082015991,"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":0.9836000204086304,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9817000031471252,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5468000173568726},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5375999808311462},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4571000039577484},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.43459999561309814},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42250001430511475},{"id":"https://openalex.org/keywords/universality","display_name":"Universality (dynamical systems)","score":0.39239999651908875},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.38089999556541443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6604999899864197},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5468000173568726},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42250001430511475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4059000015258789},{"id":"https://openalex.org/C183992945","wikidata":"https://www.wikidata.org/wiki/Q2495574","display_name":"Universality (dynamical systems)","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2567000091075897},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3746027.3754707","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754707","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.13061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.13061","pdf_url":"https://arxiv.org/pdf/2507.13061","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"doi:10.48550/arxiv.2507.13061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.13061","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754707","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754707","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W4386075580","https://openalex.org/W4412888645","https://openalex.org/W2592962403","https://openalex.org/W2340897893","https://openalex.org/W2133795296","https://openalex.org/W2031688197","https://openalex.org/W2600200270","https://openalex.org/W4324296295","https://openalex.org/W2045964207","https://openalex.org/W2592658867","https://openalex.org/W2796196973","https://openalex.org/W4390872423","https://openalex.org/W4390874575","https://openalex.org/W3012326541","https://openalex.org/W4393148771","https://openalex.org/W3138516171","https://openalex.org/W1628899544","https://openalex.org/W2911436056","https://openalex.org/W2886641317","https://openalex.org/W4402781025","https://openalex.org/W4311057028","https://openalex.org/W2515866431"],"related_works":[],"abstract_inverted_index":{"Scene":[0],"understanding":[1],"is":[2,122,127,146],"one":[3],"of":[4,67,106],"the":[5,52,65,77,82],"core":[6],"tasks":[7],"in":[8,28,35,43,69,141],"computer":[9],"vision,":[10],"aiming":[11],"to":[12,18,45,63,102],"extract":[13],"semantic":[14],"information":[15],"from":[16],"images":[17],"identify":[19],"objects,":[20],"scene":[21,72],"categories,":[22],"and":[23,93,139],"their":[24],"interrelationships.":[25],"Although":[26],"advancements":[27],"Vision-Language":[29],"Models":[30],"(VLMs)":[31],"have":[32],"driven":[33],"progress":[34],"this":[36,54],"field,":[37],"existing":[38],"VLMs":[39,68,101],"still":[40],"face":[41],"challenges":[42],"adaptation":[44,66],"unseen":[46,107],"complex":[47,70],"wide-area":[48,71],"scenes.":[49],"To":[50],"address":[51],"challenges,":[53],"paper":[55],"proposes":[56],"a":[57,123],"Hierarchical":[58],"Coresets":[59],"Selection":[60],"(HCS)":[61],"mechanism":[62],"advance":[64],"understanding.":[73],"It":[74],"progressively":[75],"refines":[76],"selected":[78],"regions":[79,115],"based":[80],"on":[81],"proposed":[83],"theoretically":[84],"guaranteed":[85],"importance":[86],"function,":[87],"which":[88],"considers":[89],"utility,":[90],"representativeness,":[91],"robustness,":[92],"synergy.":[94],"Without":[95],"requiring":[96],"additional":[97],"fine-tuning,":[98],"HCS":[99,121,135],"enables":[100],"achieve":[103],"rapid":[104],"understandings":[105],"scenes":[108],"at":[109,148],"any":[110,130],"scale":[111],"using":[112],"minimal":[113],"interpretable":[114],"while":[116],"mitigating":[117],"insufficient":[118],"feature":[119],"density.":[120],"plug-and-play":[124],"method":[125],"that":[126,134],"compatible":[128],"with":[129],"VLM.":[131],"Experiments":[132],"demonstrate":[133],"achieves":[136],"superior":[137],"performance":[138],"universality":[140],"various":[142],"tasks.":[143],"The":[144],"code":[145],"available":[147],"https://wangjingyao07.github.io/HCS.github.io/.":[149]},"counts_by_year":[],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-18T00:00:00"}