{"id":"https://openalex.org/W4403678335","doi":"https://doi.org/10.1109/case59546.2024.10711649","title":"ManufVisSGG: A Vision-Language-Model Approach for Cognitive Scene Graph Generation in Manufacturing Systems","display_name":"ManufVisSGG: A Vision-Language-Model Approach for Cognitive Scene Graph Generation in Manufacturing Systems","publication_year":2024,"publication_date":"2024-08-28","ids":{"openalex":"https://openalex.org/W4403678335","doi":"https://doi.org/10.1109/case59546.2024.10711649"},"language":"en","primary_location":{"id":"doi:10.1109/case59546.2024.10711649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case59546.2024.10711649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5061850214","display_name":"Zhijie Yan","orcid":"https://orcid.org/0000-0001-8065-0748"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Yan","raw_affiliation_strings":["Beihang University,School of Mechanical Engineering and Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Mechanical Engineering and Automation,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037251172","display_name":"Zuoxu Wang","orcid":"https://orcid.org/0000-0003-2524-1217"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuoxu Wang","raw_affiliation_strings":["Beihang University,School of Mechanical Engineering and Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Mechanical Engineering and Automation,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058018789","display_name":"Shufei Li","orcid":"https://orcid.org/0000-0002-5684-6756"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shufei Li","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Industrial and Systems Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Industrial and Systems Engineering,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100684503","display_name":"Mingrui Li","orcid":"https://orcid.org/0009-0005-9444-4706"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingrui Li","raw_affiliation_strings":["Beihang University,School of Mechanical Engineering and Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Mechanical Engineering and Automation,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076480232","display_name":"Xinxin Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxin Liang","raw_affiliation_strings":["Beihang University,School of Mechanical Engineering and Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Mechanical Engineering and Automation,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100422755","display_name":"Jihong Liu","orcid":"https://orcid.org/0000-0003-2983-8766"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihong Liu","raw_affiliation_strings":["Beihang University,School of Mechanical Engineering and Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,School of Mechanical Engineering and Automation,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1632","last_page":"1637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8679999709129333,"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":0.8679999709129333,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.8019000291824341,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.7914999723434448,"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/computer-science","display_name":"Computer science","score":0.7528585195541382},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5018186569213867},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4639185667037964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43349123001098633},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3518737554550171},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3291493058204651},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.18546780943870544},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09789535403251648}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7528585195541382},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5018186569213867},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4639185667037964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43349123001098633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3518737554550171},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3291493058204651},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18546780943870544},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09789535403251648},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case59546.2024.10711649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case59546.2024.10711649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2077069816","https://openalex.org/W2277195237","https://openalex.org/W2579549467","https://openalex.org/W2807697862","https://openalex.org/W2887665961","https://openalex.org/W2962749469","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W2969679616","https://openalex.org/W2987123286","https://openalex.org/W2992049873","https://openalex.org/W3021013305","https://openalex.org/W3034538190","https://openalex.org/W3120335880","https://openalex.org/W3173181410","https://openalex.org/W3205786327","https://openalex.org/W3209825639","https://openalex.org/W4200498145","https://openalex.org/W4226054716","https://openalex.org/W4281631763","https://openalex.org/W4312815172","https://openalex.org/W4312936847","https://openalex.org/W4313148857","https://openalex.org/W4313453017","https://openalex.org/W4366352717","https://openalex.org/W4383109478","https://openalex.org/W4387123761","https://openalex.org/W4390041933","https://openalex.org/W4395091069","https://openalex.org/W6809646742","https://openalex.org/W6855033735"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2368927203","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3204019825"],"abstract_inverted_index":{"To":[0,76],"establish":[1],"a":[2,90,123,129],"cognitive":[3],"manufacturing":[4,131,141],"system,":[5],"scene":[6,64,105,132,150],"graph":[7,65,133,151],"generation":[8,134,152],"(SGG)":[9],"that":[10,58,95],"lets":[11],"machines/robots":[12],"understand":[13],"objects":[14,38],"and":[15,33,108,142,154,169],"their":[16,52],"relations":[17],"under":[18],"varied":[19],"scenarios":[20],"is":[21,67],"an":[22],"essential":[23],"task.":[24],"Existing":[25],"research":[26],"on":[27,31],"SGG":[28],"primarily":[29],"focuses":[30],"detection":[32],"panoptic":[34,45],"segmentation":[35],"approaches,":[36],"where":[37],"are":[39],"identified":[40],"through":[41],"bounding":[42],"boxes":[43],"or":[44],"segmentation,":[46],"followed":[47],"by":[48,70],"the":[49,59,62,71,82,97,117,163,166,171,174],"prediction":[50],"of":[51,61,73,99,140,165,173],"pairwise":[53],"relationships.":[54],"This":[55],"process":[56],"means":[57],"quality":[60,72],"final":[63],"predictions":[66],"heavily":[68],"influenced":[69],"costly":[74],"annotations.":[75,114],"tackle":[77],"this":[78],"issue,":[79],"we":[80,120,160],"propose":[81],"Manufacturing":[83],"Visual":[84],"Scene":[85],"Graph":[86],"Generation":[87],"(ManufVisSGG)":[88],"method,":[89,119],"simple":[91],"yet":[92],"powerful":[93],"approach":[94],"leverages":[96],"capabilities":[98],"Vision-Language":[100],"Models":[101],"(VLMs)":[102],"to":[103,127],"generate":[104],"graphs":[106],"quickly":[107],"accurately":[109],"without":[110],"any":[111],"additional":[112],"object":[113],"Furthermore,":[115],"leveraging":[116],"ManufVisSGG":[118,167],"have":[121,161],"implemented":[122],"meticulous":[124],"annotation":[125],"procedure":[126],"compile":[128],"high-quality":[130],"(MSG)":[135],"dataset,":[136],"comprising":[137],"10,000":[138],"images":[139],"other":[143,158],"industrial":[144],"scenes.":[145],"Through":[146],"comparisons":[147],"with":[148],"various":[149],"methods":[153],"benchmarks":[155],"across":[156],"two":[157],"datasets,":[159],"showcased":[162],"superiority":[164],"method":[168],"underscored":[170],"benefits":[172],"MSG":[175],"dataset":[176],"over":[177],"existing":[178],"datasets.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}