{"id":"https://openalex.org/W4285620459","doi":"https://doi.org/10.1145/3394171.3414025","title":"One-shot Scene Graph Generation","display_name":"One-shot Scene Graph Generation","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W4285620459","doi":"https://doi.org/10.1145/3394171.3414025"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3414025","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3414025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/A5103213404","display_name":"Yuyu Guo","orcid":"https://orcid.org/0000-0003-4376-6922"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyu Guo","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3090","last_page":"3098"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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":0.9973999857902527,"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":0.8060334324836731},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.6361685991287231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.599068284034729},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5552006959915161},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.49843859672546387},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4882550537586212},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45409271121025085},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.34698522090911865},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.18155524134635925},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.09494072198867798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060334324836731},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.6361685991287231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.599068284034729},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5552006959915161},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.49843859672546387},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4882550537586212},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45409271121025085},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.34698522090911865},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18155524134635925},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.09494072198867798}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3414025","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3414025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W2044072771","https://openalex.org/W2077069816","https://openalex.org/W2097117768","https://openalex.org/W2115733720","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2561529111","https://openalex.org/W2591644541","https://openalex.org/W2621571501","https://openalex.org/W2741727820","https://openalex.org/W2786585376","https://openalex.org/W2799029629","https://openalex.org/W2807941860","https://openalex.org/W2883170015","https://openalex.org/W2886970679","https://openalex.org/W2895902247","https://openalex.org/W2904452845","https://openalex.org/W2962785943","https://openalex.org/W2962958773","https://openalex.org/W2963037989","https://openalex.org/W2963938081","https://openalex.org/W2981582341","https://openalex.org/W2983050716","https://openalex.org/W2987123286","https://openalex.org/W3035212740","https://openalex.org/W3099677434","https://openalex.org/W4221148458"],"related_works":["https://openalex.org/W4285818553","https://openalex.org/W1979978247","https://openalex.org/W4285208802","https://openalex.org/W2807873315","https://openalex.org/W4221142755","https://openalex.org/W4302773889","https://openalex.org/W3206452419","https://openalex.org/W4226538672","https://openalex.org/W4299805252","https://openalex.org/W4388144322"],"abstract_inverted_index":{"As":[0],"a":[1,16,50,61,170,216,233],"structured":[2],"representation":[3],"of":[4,38,124,167,184,189,242],"the":[5,8,28,110,117,121,130,134,151,185,220,240,243,249],"image":[6],"content,":[7,132],"visual":[9,47,131,135,192],"scene":[10,29,112],"graph":[11,30,113,171],"(visual":[12],"relationship)":[13],"acts":[14],"as":[15],"bridge":[17],"between":[18,126,146],"computer":[19],"vision":[20],"and":[21,106,141,148,248],"natural":[22],"language":[23],"processing.":[24],"Existing":[25],"models":[26],"on":[27,215],"generation":[31,114],"task":[32,62],"notoriously":[33],"require":[34],"tens":[35],"or":[36,52],"hundreds":[37],"labeled":[39,78],"samples.":[40],"By":[41,162],"contrast,":[42],"human":[43],"beings":[44],"can":[45,91,159],"learn":[46],"relationships":[48,125,136],"from":[49,75,88,129,194],"few":[51],"even":[53],"one":[54,77,90],"example.":[55,79],"Inspired":[56],"by":[57,198,232],"this,":[58],"we":[59,99,201],"design":[60],"named":[63],"One-Shot":[64],"Scene":[65],"Graph":[66,173],"Generation,":[67],"where":[68],"each":[69,195],"relationship":[70],"triplet":[71],"(e.g.,":[72],"\"dog-has-head'')":[73],"comes":[74],"only":[76],"The":[80],"key":[81],"insight":[82],"is":[83],"that":[84,224],"rather":[85],"than":[86],"learning":[87],"scratch,":[89],"utilize":[92,202],"rich":[93],"prior":[94,122],"knowledge.":[95],"In":[96],"this":[97],"paper,":[98],"propose":[100],"Multiple":[101,250],"Structured":[102,251],"Knowledge":[103,105,119,153],"(Relational":[104],"Commonsense":[107,152],"Knowledge)":[108],"for":[109],"one-shot":[111,218],"task.":[115],"Specifically,":[116],"Relational":[118],"represents":[120],"knowledge":[123,156,168],"entities":[127],"extracted":[128],"e.g.,":[133],"\"standing":[137],"in'',":[138,140],"\"sitting":[139],"\"lying":[142],"in''":[143],"may":[144],"exist":[145],"\"dog''":[147],"\"yard'',":[149],"while":[150],"encodes":[154],"\"sense-making''":[155],"like":[157],"\"dog":[158],"guard":[160],"yard''.":[161],"organizing":[163],"these":[164],"two":[165],"kinds":[166],"in":[169],"structure,":[172],"Convolution":[174],"Networks":[175],"(GCNs)":[176],"are":[177],"used":[178],"to":[179,208],"extract":[180],"knowledge-embedded":[181],"semantic":[182],"features":[183,193],"entities.":[186],"Besides,":[187],"instead":[188],"extracting":[190],"isolated":[191],"entity":[196],"generated":[197],"Faster":[199],"R-CNN,":[200],"an":[203],"Instance":[204,244],"Relation":[205,245],"Transformer":[206,246],"encoder":[207,247],"fully":[209],"explore":[210],"their":[211],"context":[212],"information.":[213],"Based":[214],"constructed":[217],"dataset,":[219],"experimental":[221],"results":[222],"show":[223],"our":[225],"method":[226],"significantly":[227],"outperforms":[228],"existing":[229],"state-of-the-art":[230],"methods":[231],"large":[234],"margin.":[235],"Ablation":[236],"studies":[237],"also":[238],"verify":[239],"effectiveness":[241],"Knowledge.":[252]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}