{"id":"https://openalex.org/W4392902725","doi":"https://doi.org/10.1109/icassp48485.2024.10446239","title":"Supplementing Missing Visions Via Dialog for Scene Graph Generations","display_name":"Supplementing Missing Visions Via Dialog for Scene Graph Generations","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902725","doi":"https://doi.org/10.1109/icassp48485.2024.10446239"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446239","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5061651333","display_name":"Zhenghao Zhao","orcid":"https://orcid.org/0009-0000-1934-4661"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhenghao Zhao","raw_affiliation_strings":["Illinois Institute of Technology,USA","Illinois Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology,USA","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Illinois Institute of Technology, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101992281","display_name":"Ye Zhu","orcid":"https://orcid.org/0000-0003-0774-9375"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ye Zhu","raw_affiliation_strings":["Illinois Institute of Technology,USA","Illinois Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology,USA","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Illinois Institute of Technology, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685782","display_name":"Xiaoguang Zhu","orcid":"https://orcid.org/0000-0001-9554-2133"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoguang Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090850708","display_name":"Yuzhang Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzhang Shang","raw_affiliation_strings":["Illinois Institute of Technology,USA","Illinois Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology,USA","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Illinois Institute of Technology, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100395042","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-0187-7010"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["Illinois Institute of Technology,USA","Illinois Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology,USA","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Illinois Institute of Technology, USA","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061651333"],"corresponding_institution_ids":["https://openalex.org/I180949307"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02479894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3375","last_page":"3379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.991100013256073,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9815000295639038,"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":0.8696565628051758},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.840583860874176},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6897302865982056},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5833591222763062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5655742883682251},{"id":"https://openalex.org/keywords/premise","display_name":"Premise","score":0.5577225089073181},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5467053055763245},{"id":"https://openalex.org/keywords/vision","display_name":"Vision","score":0.48567259311676025},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46783649921417236},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.46276015043258667},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4243714511394501},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37825071811676025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3681589663028717},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.13903671503067017},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.08160129189491272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8696565628051758},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.840583860874176},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6897302865982056},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5833591222763062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5655742883682251},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.5577225089073181},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5467053055763245},{"id":"https://openalex.org/C133979268","wikidata":"https://www.wikidata.org/wiki/Q1682108","display_name":"Vision","level":2,"score":0.48567259311676025},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46783649921417236},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.46276015043258667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4243714511394501},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37825071811676025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3681589663028717},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.13903671503067017},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08160129189491272},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446239","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1223590526","display_name":"CRCNS Research Proposal: A Unified Framework for Unsupervised Sparse-to-dense Brain Image Generation and Neural Circuit Reconstruction","funder_award_id":"2309073","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G303595336","display_name":"Collaborative Research: SCH: Personalized Watch-based Fall Risk Analysis and Detection with Cross Modal Learning","funder_award_id":"2123521","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7156583185","display_name":null,"funder_award_id":"IIS-2309073","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2277195237","https://openalex.org/W2463565445","https://openalex.org/W2558809543","https://openalex.org/W2579549467","https://openalex.org/W2603266952","https://openalex.org/W2750998636","https://openalex.org/W2886970679","https://openalex.org/W2950096400","https://openalex.org/W2963514444","https://openalex.org/W2963536419","https://openalex.org/W2963649796","https://openalex.org/W2963938081","https://openalex.org/W2963954913","https://openalex.org/W2964213933","https://openalex.org/W2964218959","https://openalex.org/W2970641574","https://openalex.org/W2981902456","https://openalex.org/W2987123286","https://openalex.org/W3035017890","https://openalex.org/W3100806282","https://openalex.org/W3107291510","https://openalex.org/W3173972567","https://openalex.org/W4249013746","https://openalex.org/W6697449767","https://openalex.org/W6719057275","https://openalex.org/W6743696045","https://openalex.org/W6791426159"],"related_works":["https://openalex.org/W1548557026","https://openalex.org/W1975110180","https://openalex.org/W1989187808","https://openalex.org/W4377008908","https://openalex.org/W4288993906","https://openalex.org/W2117786814","https://openalex.org/W2332333067","https://openalex.org/W4236658683","https://openalex.org/W2020463334","https://openalex.org/W2026182709"],"abstract_inverted_index":{"Most":[0],"AI":[1,131],"systems":[2,132],"rely":[3],"on":[4],"the":[5,8,22,28,35,68,96,107,129,134,144,155,163],"premise":[6],"that":[7,119],"input":[9,63,86,153],"visual":[10,37,62,78,85,152],"data":[11,38,79],"are":[12],"sufficient":[13],"to":[14,43,89,94,104],"achieve":[15],"competitive":[16],"performance":[17,90,173],"in":[18,139],"various":[19,44,75],"tasks.":[20],"However,":[21],"classic":[23],"task":[24,58,73,108,148],"setup":[25],"rarely":[26],"considers":[27],"challenging,":[29],"yet":[30],"common":[31],"practical":[32],"situations":[33],"where":[34],"complete":[36],"may":[39],"be":[40,121],"inaccessible":[41],"due":[42],"reasons":[45],"(e.g.,":[46],"restricted":[47],"view":[48],"range":[49],"and":[50,154],"occlusions).":[51],"To":[52],"this":[53],"end,":[54],"we":[55,66,92],"investigate":[56],"a":[57,112],"setting":[59,149],"with":[60,74,124,133,150],"incomplete":[61],"data.":[64],"Specifically,":[65],"exploit":[67],"Scene":[69],"Graph":[70],"Generation":[71],"(SGG)":[72],"levels":[76],"of":[77,136,146,157],"missingness":[80],"as":[81,162],"input.":[82],"While":[83],"insufficient":[84],"naturally":[87],"leads":[88],"drop,":[91],"propose":[93],"supplement":[95],"missing":[97,151],"visions":[98],"via":[99],"natural":[100,140],"language":[101],"dialog":[102,160],"interactions":[103,138],"better":[105],"accomplish":[106],"objective.":[109],"We":[110,142],"design":[111],"model-agnostic":[113],"Supplementary":[114],"Interactive":[115],"Dialog":[116],"(SI-Dial)":[117],"framework":[118],"can":[120],"jointly":[122],"learned":[123],"most":[125],"existing":[126],"models,":[127],"endowing":[128],"current":[130],"ability":[135],"question-answer":[137],"language.":[141],"demonstrate":[143],"feasibility":[145],"such":[147],"effectiveness":[156],"our":[158],"proposed":[159],"module":[161],"supplementary":[164],"information":[165],"source":[166],"through":[167],"extensive":[168],"experiments,":[169],"by":[170],"achieving":[171],"promising":[172],"improvement":[174],"over":[175],"multiple":[176],"baselines.":[177]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}