{"id":"https://openalex.org/W4390969311","doi":"https://doi.org/10.1109/lra.2024.3355751","title":"FM-Fusion: Instance-Aware Semantic Mapping Boosted by Vision-Language Foundation Models","display_name":"FM-Fusion: Instance-Aware Semantic Mapping Boosted by Vision-Language Foundation Models","publication_year":2024,"publication_date":"2024-01-18","ids":{"openalex":"https://openalex.org/W4390969311","doi":"https://doi.org/10.1109/lra.2024.3355751"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3355751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3355751","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.04555","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078952009","display_name":"Chuhao Liu","orcid":"https://orcid.org/0000-0003-3050-6574"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chuhao Liu","raw_affiliation_strings":["Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-3050-6574","affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726478","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0002-6760-279X"},"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":"Ke Wang","raw_affiliation_strings":["Department of Information Engineering, Chang&#x0027;an University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0002-6760-279X","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Chang&#x0027;an University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061924094","display_name":"Jieqi Shi","orcid":"https://orcid.org/0000-0002-1223-191X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jieqi Shi","raw_affiliation_strings":["Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-1223-191X","affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089660303","display_name":"Zhijian Qiao","orcid":"https://orcid.org/0000-0001-6639-1110"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhijian Qiao","raw_affiliation_strings":["Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-6639-1110","affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001947944","display_name":"Shaojie Shen","orcid":"https://orcid.org/0000-0002-5573-2909"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shaojie Shen","raw_affiliation_strings":["Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-5573-2909","affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4786,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81161066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"9","issue":"3","first_page":"2232","last_page":"2239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.8230940103530884},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6544574499130249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6537400484085083},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.5880221128463745},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46283650398254395},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4512847065925598},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.44730469584465027},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44281086325645447},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.44215139746665955},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42761075496673584},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4254530072212219},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.42227989435195923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35099732875823975},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.07869476079940796}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230940103530884},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6544574499130249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6537400484085083},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.5880221128463745},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46283650398254395},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4512847065925598},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.44730469584465027},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44281086325645447},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.44215139746665955},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42761075496673584},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4254530072212219},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.42227989435195923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35099732875823975},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.07869476079940796},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/lra.2024.3355751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3355751","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2402.04555","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.04555","pdf_url":"https://arxiv.org/pdf/2402.04555","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-134805","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-134805","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.04555","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.04555","pdf_url":"https://arxiv.org/pdf/2402.04555","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390969311.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1745334888","https://openalex.org/W1999478155","https://openalex.org/W2132360065","https://openalex.org/W2336416123","https://openalex.org/W2523049145","https://openalex.org/W2563685048","https://openalex.org/W2594519801","https://openalex.org/W2607968634","https://openalex.org/W2786036844","https://openalex.org/W2888144883","https://openalex.org/W2919379406","https://openalex.org/W2950538710","https://openalex.org/W2963150697","https://openalex.org/W3090386798","https://openalex.org/W3102129812","https://openalex.org/W3102330937","https://openalex.org/W3183768538","https://openalex.org/W4283332944","https://openalex.org/W4312956471","https://openalex.org/W4312961455","https://openalex.org/W4324128075","https://openalex.org/W4366781106","https://openalex.org/W4379932565","https://openalex.org/W4390874575","https://openalex.org/W4393387578","https://openalex.org/W6747827861","https://openalex.org/W6791353385","https://openalex.org/W6850787431","https://openalex.org/W6852789751","https://openalex.org/W6853219587","https://openalex.org/W6853256829","https://openalex.org/W6853520483"],"related_works":["https://openalex.org/W1965623300","https://openalex.org/W3134365128","https://openalex.org/W2541135911","https://openalex.org/W2359259132","https://openalex.org/W4387489691","https://openalex.org/W2103835134","https://openalex.org/W3016822073","https://openalex.org/W2156467700","https://openalex.org/W2133831373","https://openalex.org/W2807098362"],"abstract_inverted_index":{"Semantic":[0],"mapping":[1,33,75,120,169],"based":[2],"on":[3,157],"the":[4,16,29,39,42,104,114,138,158,166],"supervised":[5],"object":[6,17,77],"detectors":[7],"is":[8],"sensitive":[9],"to":[10,24,60,71,90],"image":[11],"distribution.":[12,55],"In":[13],"real-world":[14],"environments,":[15],"detection":[18,78],"and":[19,146],"segmentation":[20,162],"performance":[21,140],"can":[22],"lead":[23],"a":[25,35,49,85,117,123],"major":[26],"drop,":[27],"preventing":[28],"use":[30],"of":[31,44,125,141],"semantic":[32,64,74,93,119,134,160,168],"in":[34,144],"wider":[36],"domain.":[37],"On":[38],"other":[40],"hand,":[41],"development":[43],"vision-language":[45],"foundation":[46,81],"models":[47],"demonstrates":[48],"strong":[50],"zero-shot":[51,139],"transferability":[52],"across":[53],"data":[54],"It":[56,164],"provides":[57],"an":[58,132],"opportunity":[59],"construct":[61],"generalizable":[62],"instance-aware":[63,73,133],"maps.":[65],"Hence,":[66],"this":[67],"work":[68,129],"explores":[69],"how":[70],"boost":[72],"from":[76,80,95],"generated":[79],"models.":[82],"We":[83,111,136],"propose":[84],"probabilistic":[86],"label":[87,97],"fusion":[88],"method":[89,143,150,170],"predict":[91],"close-set":[92],"classes":[94],"open-set":[96],"measurements.":[98],"An":[99],"instance":[100,161],"refinement":[101],"module":[102],"merges":[103],"over-segmented":[105],"instances":[106],"caused":[107],"by":[108],"inconsistent":[109],"segmentation.":[110],"integrate":[112],"all":[113],"modules":[115],"into":[116],"unified":[118],"system.":[121],"Reading":[122],"sequence":[124],"RGB-D":[126],"input,":[127],"our":[128,142],"incrementally":[130],"reconstructs":[131],"map.":[135],"evaluate":[137],"ScanNet":[145,159],"SceneNN":[147],"datasets.":[148],"Our":[149],"achieves":[151],"40.3":[152],"mean":[153],"average":[154],"precision":[155],"(mAP)":[156],"task.":[163],"outperforms":[165],"traditional":[167],"significantly.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2024-01-19T00:00:00"}
