{"id":"https://openalex.org/W7148744895","doi":"https://doi.org/10.48550/arxiv.2604.01742","title":"Dense Point-to-Mask Optimization with Reinforced Point Selection for Crowd Instance Segmentation","display_name":"Dense Point-to-Mask Optimization with Reinforced Point Selection for Crowd Instance Segmentation","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7148744895","doi":"https://doi.org/10.48550/arxiv.2604.01742"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.01742","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01742","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.01742","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132901720","display_name":"Hongru Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hongru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130191924","display_name":"Jiyang Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132857421","display_name":"Jia Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132906816","display_name":"Antoni B. Chan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chan, Antoni B.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.3208000063896179,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.3208000063896179,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.22269999980926514,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.18019999563694,"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/segmentation","display_name":"Segmentation","score":0.8133999705314636},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5803999900817871},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48910000920295715},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4781000018119812},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4490000009536743},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.42149999737739563},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.41690000891685486},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.4101000130176544}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8133999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7106999754905701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6902999877929688},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5803999900817871},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48910000920295715},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43959999084472656},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.42149999737739563},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.4101000130176544},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.362199991941452},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.28850001096725464},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.263700008392334},{"id":"https://openalex.org/C2779952087","wikidata":"https://www.wikidata.org/wiki/Q11831792","display_name":"Ideal point","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.01742","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01742","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.01742","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01742","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Crowd":[0],"instance":[1,102,128,169],"segmentation":[2,38,103,129,170],"is":[3],"a":[4,8,135,155],"crucial":[5],"task":[6],"with":[7,91,142],"wide":[9],"range":[10],"of":[11,44,157,199],"applications,":[12],"including":[13],"surveillance":[14],"and":[15,32,47,55,109,176],"transportation.":[16],"Currently,":[17],"point":[18,105,119,153,160],"labels":[19,27,46],"are":[20,30],"common":[21],"in":[22,75,130,202],"crowd":[23,56,123,168],"datasets,":[24],"while":[25],"region":[26,45],"(e.g.,":[28],"boxes)":[29],"rare":[31],"inaccurate.":[33],"The":[34],"masks":[35,187],"obtained":[36],"through":[37],"help":[39],"to":[40,99,126],"improve":[41],"the":[42,49,92,117,150,158,196],"accuracy":[43],"resolve":[48],"correspondence":[50],"between":[51],"individual":[52],"location":[53],"coordinates":[54],"density":[57],"maps.":[58],"However,":[59],"directly":[60],"applying":[61],"currently":[62],"popular":[63],"large":[64],"foundation":[65],"models":[66],"such":[67],"as":[68],"SAM":[69,90],"does":[70],"not":[71],"yield":[72],"ideal":[73],"results":[74],"dense":[76,101,131],"crowds.":[77],"To":[78],"this":[79],"end,":[80],"we":[81,112,133,165,180],"first":[82],"propose":[83,134],"Dense":[84],"Point-to-Mask":[85],"Optimization":[86,146],"(DPMO),":[87],"which":[88,148],"integrates":[89],"Nearest":[93],"Neighbor":[94],"Exclusive":[95],"Circle":[96],"(NNEC)":[97],"constraint":[98],"generate":[100],"from":[104,116,154],"annotations.":[106],"With":[107],"DPMO":[108],"manual":[110],"correction,":[111],"obtain":[113],"mask":[114,200],"annotations":[115,120,201],"existing":[118],"for":[121],"traditional":[122],"datasets.":[124,178],"Then,":[125],"predict":[127],"crowds,":[132],"Reinforced":[136],"Point":[137],"Selection":[138],"(RPS)":[139],"framework":[140],"trained":[141],"Group":[143],"Relative":[144],"Policy":[145],"(GRPO),":[147],"selects":[149],"best":[151],"predicted":[152],"sampling":[156],"initial":[159],"prediction.":[161],"Through":[162],"extensive":[163],"experiments,":[164],"achieve":[166],"state-of-the-art":[167],"performance":[171,191],"on":[172],"ShanghaiTech,":[173],"UCF-QNRF,":[174],"JHU-CROWD++,":[175],"NWPU-Crowd":[177],"Furthermore,":[179],"design":[181],"new":[182],"loss":[183],"functions":[184],"supervised":[185],"by":[186],"that":[188],"boost":[189],"counting":[190,204],"across":[192],"different":[193],"models,":[194],"demonstrating":[195],"significant":[197],"role":[198],"enhancing":[203],"accuracy.":[205]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-04T00:00:00"}