{"id":"https://openalex.org/W7160094564","doi":"https://doi.org/10.1016/j.eswa.2026.132657","title":"From perception to cognition: Unifying multi-object 3D visual grounding and dense captioning in monocular images","display_name":"From perception to cognition: Unifying multi-object 3D visual grounding and dense captioning in monocular images","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7160094564","doi":"https://doi.org/10.1016/j.eswa.2026.132657"},"language":"en","primary_location":{"id":"doi:10.1016/j.eswa.2026.132657","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132657","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-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/A5124180015","display_name":"Keyu Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyu Guo","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0009-0005-0699-3992","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102665049","display_name":"Yongle Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongle Huang","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0009-0007-6462-6087","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135278472","display_name":"Hongkai Wei","orcid":"https://orcid.org/0009-0007-1414-6181"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongkai Wei","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0009-0007-1414-6181","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135212835","display_name":"Shijie Sun","orcid":"https://orcid.org/0000-0003-4043-8448"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shijie Sun","raw_affiliation_strings":["School of Data Science and Artificial Intelligence, Chang\u2019an University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0000-0003-4043-8448","affiliations":[{"raw_affiliation_string":"School of Data Science and Artificial Intelligence, Chang\u2019an University, Xi\u2019an, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135114701","display_name":"Xiangyu Song","orcid":"https://orcid.org/0000-0002-5550-6354"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangyu Song","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0000-0002-5550-6354","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135174100","display_name":"Mingtao Feng","orcid":"https://orcid.org/0000-0003-0384-3743"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingtao Feng","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0000-0003-0384-3743","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi\u2019an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135159600","display_name":"Tiantian Wang","orcid":"https://orcid.org/0009-0002-9212-5224"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiantian Wang","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0009-0002-9212-5224","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135258938","display_name":"Shan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Yu","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0000-0003-4444-1820","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135104568","display_name":"Huansheng Song","orcid":null},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huansheng Song","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0000-0001-5463-1340","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, China","institution_ids":["https://openalex.org/I25355098"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5135114701","https://openalex.org/A5135212835"],"corresponding_institution_ids":["https://openalex.org/I25355098"],"apc_list":{"value":3220,"currency":"USD","value_usd":3220},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52020663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"325","issue":null,"first_page":"132657","last_page":"132657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8543999791145325,"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":0.8543999791145325,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.03610000014305115,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.01850000023841858,"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/closed-captioning","display_name":"Closed captioning","score":0.8104000091552734},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.7822999954223633},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.7269999980926514},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.36399999260902405},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3601999878883362},{"id":"https://openalex.org/keywords/monocular-vision","display_name":"Monocular vision","score":0.3601999878883362}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8104000091552734},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7822999954223633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633000016212463},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7269999980926514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6833999752998352},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6171000003814697},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.36399999260902405},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.eswa.2026.132657","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132657","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5492256879806519,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2115579991","https://openalex.org/W2150839555","https://openalex.org/W4213019189","https://openalex.org/W4285606658","https://openalex.org/W4312565984","https://openalex.org/W4384917104","https://openalex.org/W4391136507","https://openalex.org/W4393182987","https://openalex.org/W4403822165","https://openalex.org/W4406765936","https://openalex.org/W4407191603","https://openalex.org/W4409052277","https://openalex.org/W4411920984","https://openalex.org/W4415795530","https://openalex.org/W7133243441"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-18T08:10:14.011955","created_date":"2026-05-05T00:00:00"}
