{"id":"https://openalex.org/W7160299609","doi":"https://doi.org/10.48550/arxiv.2605.02357","title":"Channel-Level Relation to Attentive Aggregation with Neighborhood-Homogeneity Constraint for Point Cloud Analysis","display_name":"Channel-Level Relation to Attentive Aggregation with Neighborhood-Homogeneity Constraint for Point Cloud Analysis","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7160299609","doi":"https://doi.org/10.48550/arxiv.2605.02357"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.02357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02357","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.02357","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104101066","display_name":"Jiaqi Shi","orcid":"https://orcid.org/0009-0001-9385-742X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039890630","display_name":"Jin Xiao","orcid":"https://orcid.org/0000-0003-2462-4996"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135311822","display_name":"Xiaoguang Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Xiaoguang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101312388","display_name":"Wenxuan Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Wenxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101321804","display_name":"Zichong Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Zichong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135283915","display_name":"Zifan Long","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Zifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709430","display_name":"Tianyou Chen","orcid":"https://orcid.org/0000-0002-7107-1004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Tianyou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zhang, Baochang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Baochang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9391999840736389,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9391999840736389,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.003700000001117587,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.0034000000450760126,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7466999888420105},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.5835000276565552},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5544999837875366},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5274999737739563},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5031999945640564},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4189999997615814},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.40849998593330383},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.40610000491142273},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4058000147342682},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.3986999988555908}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7466999888420105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6958000063896179},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.5835000276565552},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5031999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47909998893737793},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46160000562667847},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41830000281333923},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33550000190734863},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3343000113964081},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26409998536109924}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.02357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02357","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:10.48550/arxiv.2605.02357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02357","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7381907105445862}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"3D":[1],"point":[2,57],"cloud":[3,58],"understanding,":[4],"the":[5,20,102,167,191,197,205],"core":[6,87],"challenge":[7],"lies":[8],"in":[9,68,110],"accurately":[10],"capturing":[11],"discriminative":[12],"features":[13],"within":[14],"complex":[15],"neighborhoods,":[16],"which":[17],"directly":[18],"affects":[19],"execution":[21],"precision":[22],"of":[23],"downstream":[24],"tasks":[25],"such":[26,60],"as":[27,95],"embodied":[28],"AI":[29],"and":[30,113,133,163,173,176,200,210],"autonomous":[31],"driving.":[32],"Existing":[33],"methods":[34],"explore":[35],"feature":[36,145,150],"correlation":[37],"discrimination":[38],"but":[39],"are":[40,213],"limited":[41],"to":[42,90,100,139,147],"point-level":[43],"spatial":[44,112],"distribution":[45],"or":[46],"channel":[47,114,141],"responses,":[48],"enabling":[49],"only":[50],"coarse-grained":[51,61],"level":[52],"evaluation.":[53],"For":[54],"modern":[55],"multi-scale":[56],"networks,":[59],"metrics":[62],"inevitably":[63],"incur":[64],"significant":[65],"information":[66,103],"loss":[67,104,137],"deeper":[69],"layers.":[70],"To":[71],"address":[72],"this,":[73],"we":[74,120],"propose":[75],"PointCRA,":[76],"a":[77,81,96,122,135],"novel":[78],"network":[79],"with":[80,154],"channel-level":[82],"metric-based":[83],"enhancement":[84],"mechanism.":[85],"Our":[86,158,185],"idea":[88],"is":[89,160],"introduce":[91],"temporal":[92],"trend":[93],"variation":[94],"new":[97],"evaluation":[98],"dimension":[99,108],"avoid":[101],"caused":[105],"by":[106,127],"weight":[107,131],"collapse":[109],"existing":[111],"attention":[115],"mechanisms.":[116],"On":[117],"this":[118],"basis,":[119],"construct":[121],"multi-level":[123],"calibration":[124],"framework":[125],"guided":[126],"neighborhood":[128],"homogeneity":[129],"for":[130],"calibration,":[132],"design":[134],"dedicated":[136],"function":[138],"enhance":[140],"discriminability.PointCRA":[142],"leverages":[143],"intrinsic":[144],"priors":[146],"adaptively":[148],"correct":[149],"aggregation,":[151],"offering":[152],"interpretability":[153],"low":[155],"parameter":[156],"overhead.":[157],"method":[159,169],"transferable,":[161],"interpretable,":[162],"efficient.":[164],"We":[165],"validate":[166],"proposed":[168],"on":[170,190,196,204,216],"diverse":[171],"datasets":[172],"benchmark":[174],"models,":[175],"further":[177],"demonstrate":[178],"its":[179],"rationality":[180],"through":[181],"extensive":[182],"analytical":[183],"experiments.":[184],"PointCRA":[186],"achieves":[187],"77.5\\%":[188],"mIoU":[189,203],"S3DIS":[192],"dataset,":[193,199],"90.4\\%":[194],"OA":[195],"ScanObjectNN":[198],"87.4\\%":[201],"instance":[202],"ShapeNetPart":[206],"dataset.":[207],"The":[208],"code":[209],"pretrained":[211],"weights":[212],"publicly":[214],"available":[215],"GitHub:":[217],"https://github.com/AGENT9717/PointCRA":[218]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}