{"id":"https://openalex.org/W4416251817","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227744","title":"MSALNet: Capturing Contextual Relationships for Monocular 3D Visual Grounding","display_name":"MSALNet: Capturing Contextual Relationships for Monocular 3D Visual Grounding","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251817","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227744"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5111012169","display_name":"Keyu Guo","orcid":"https://orcid.org/0009-0005-0699-3992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keyu Guo","raw_affiliation_strings":["Chang’an University,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang’an University,Xi’an,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102665049","display_name":"Yongle Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongle Huang","raw_affiliation_strings":["Chang’an University,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang’an University,Xi’an,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112754056","display_name":"Yongfeng Bu","orcid":"https://orcid.org/0009-0006-8898-4308"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongfeng Bu","raw_affiliation_strings":["Chang’an University,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang’an University,Xi’an,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongkai Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongkai Wei","raw_affiliation_strings":["Chang’an University,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang’an University,Xi’an,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103070400","display_name":"Shijie Sun","orcid":"https://orcid.org/0000-0003-4043-8448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shijie Sun","raw_affiliation_strings":["Chang’an University,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang’an University,Xi’an,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068123569","display_name":"Xiangyu Song","orcid":"https://orcid.org/0000-0001-8560-1638"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Song","raw_affiliation_strings":["Chang’an University,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang’an University,Xi’an,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30407053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9510999917984009,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9510999917984009,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.014000000432133675,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.007199999876320362,"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/monocular","display_name":"Monocular","score":0.7681000232696533},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6486999988555908},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5486000180244446},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5393999814987183},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.448199987411499},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.38510000705718994},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3546999990940094},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.35370001196861267}],"concepts":[{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7681000232696533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7608000040054321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305999994277954},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6486999988555908},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5949000120162964},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5486000180244446},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5393999814987183},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38510000705718994},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2791686160","https://openalex.org/W2799263800","https://openalex.org/W2953303875","https://openalex.org/W2986803748","https://openalex.org/W3110435696","https://openalex.org/W3185591032","https://openalex.org/W4213019189","https://openalex.org/W4304084012","https://openalex.org/W4312351586","https://openalex.org/W4312385518","https://openalex.org/W4386075583","https://openalex.org/W4386075853","https://openalex.org/W4387272106","https://openalex.org/W4387623721","https://openalex.org/W4391582736","https://openalex.org/W4393156227","https://openalex.org/W4393159049","https://openalex.org/W4401061446","https://openalex.org/W4402570948","https://openalex.org/W4406374230","https://openalex.org/W4407191603"],"related_works":[],"abstract_inverted_index":{"Monocular":[0,57],"3D":[1,9,94],"Visual":[2],"Grounding":[3],"(Mono3DVG)":[4],"aims":[5],"to":[6,110],"predict":[7],"the":[8,56,66,85,89,93,100,104,108,113,117,120,123,156],"localization":[10,69],"of":[11,70,115],"objects":[12,71],"in":[13,27],"monocular":[14],"RGB":[15],"images":[16],"based":[17],"on":[18,155],"natural":[19],"language":[20],"descriptions.":[21],"This":[22,63,106],"task":[23],"has":[24],"broad":[25],"applications":[26],"areas":[28],"such":[29],"as":[30],"autonomous":[31],"driving,":[32],"human-computer":[33],"interaction":[34,130],"and":[35,43,68,79,96,119,131,137,140],"robotic":[36],"manipulation,":[37],"making":[38],"it":[39],"both":[40,116],"a":[41,52,80],"significant":[42],"challenging":[44],"task.":[45],"To":[46],"tackle":[47],"this":[48],"challenge,":[49],"we":[50],"propose":[51],"novel":[53],"network":[54,64],"architecture,":[55],"Selective":[58],"Attention":[59],"Learning":[60,76],"Network":[61],"(MSALNet).":[62],"enhances":[65],"understanding":[67],"by":[72],"introducing":[73],"an":[74],"Adaptive":[75],"Module":[77],"(ALM)":[78],"Vision-Text":[81,124],"Interaction":[82,125],"Encoder.":[83],"Specifically,":[84],"ALM":[86],"further":[87],"learns":[88],"features":[90],"extracted":[91],"from":[92],"scene":[95,118],"textual":[97,138],"descriptions,":[98],"capturing":[99],"contextual":[101],"relationships":[102],"within":[103],"features.":[105],"enables":[107],"model":[109],"better":[111],"understand":[112],"meaning":[114],"text.":[121],"Meanwhile,":[122],"Encoder":[126],"facilitates":[127],"refined":[128],"cross-modal":[129],"fusion,":[132],"promoting":[133],"alignment":[134],"between":[135],"visual":[136],"information":[139],"providing":[141],"more":[142],"discriminative":[143],"feature":[144],"representations.":[145],"Experimental":[146],"results":[147],"demonstrate":[148],"that":[149],"our":[150],"method":[151],"achieves":[152],"competitive":[153],"performance":[154],"Mono3DRefer":[157],"dataset.":[158]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-14T00:00:00"}