{"id":"https://openalex.org/W4399885811","doi":"https://doi.org/10.1145/3653946.3653952","title":"Prompt Retrieval from Stable Diffusion Generated Images Using the ConvNeXt CLIP Network","display_name":"Prompt Retrieval from Stable Diffusion Generated Images Using the ConvNeXt CLIP Network","publication_year":2024,"publication_date":"2024-03-12","ids":{"openalex":"https://openalex.org/W4399885811","doi":"https://doi.org/10.1145/3653946.3653952"},"language":"en","primary_location":{"id":"doi:10.1145/3653946.3653952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3653946.3653952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Machine Vision and Applications","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":null,"display_name":"Weijing Cheng","orcid":"https://orcid.org/0009-0005-5819-3575"},"institutions":[{"id":"https://openalex.org/I4210166603","display_name":"Jinling Institute of Technology","ror":"https://ror.org/05em1gq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210166603"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weijing Cheng","raw_affiliation_strings":["Nanjing Jinling High School, Nanjing Jinling High School, China"],"raw_orcid":"https://orcid.org/0009-0005-5819-3575","affiliations":[{"raw_affiliation_string":"Nanjing Jinling High School, Nanjing Jinling High School, China","institution_ids":["https://openalex.org/I4210166603"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210166603"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9977999925613403,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9977999925613403,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.994700014591217,"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":0.9854999780654907,"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":0.7299679517745972},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6418019533157349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5831993818283081},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4628896117210388},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4316466450691223},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.42956677079200745},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4284645915031433},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.4207450747489929},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.308184951543808},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27085167169570923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7299679517745972},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6418019533157349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5831993818283081},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4628896117210388},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4316466450691223},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.42956677079200745},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4284645915031433},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.4207450747489929},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.308184951543808},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27085167169570923},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3653946.3653952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3653946.3653952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Machine Vision and Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2194775991","https://openalex.org/W2946948417","https://openalex.org/W2970641574","https://openalex.org/W4312443924","https://openalex.org/W4312933868","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W3134175397","https://openalex.org/W2389818373","https://openalex.org/W2220831889","https://openalex.org/W4312683641","https://openalex.org/W3027421045","https://openalex.org/W2576320324","https://openalex.org/W2980386803","https://openalex.org/W3215994059","https://openalex.org/W2319823519","https://openalex.org/W4206798987"],"abstract_inverted_index":{"Stable":[0,21,50,93,108],"Diffusion":[1,22,51,94,109],"has":[2],"recently":[3],"emerged":[4],"as":[5],"a":[6,67,123,144],"groundbreaking":[7],"technique":[8],"in":[9,164],"the":[10,37,53,71,74,78,83,103,106,131,139,154,168],"field":[11],"of":[12,25,55,73,89,105,117,128,156,170,175],"generative":[13],"artificial":[14],"intelligence.":[15],"By":[16],"utilizing":[17],"concise":[18],"text":[19,171],"prompts,":[20],"is":[23,52,120,174],"capable":[24],"producing":[26],"images":[27,173],"that":[28,69],"are":[29],"either":[30],"strikingly":[31],"realistic":[32],"or":[33],"visually":[34],"stunning,":[35],"bridging":[36],"gap":[38],"between":[39,130],"textual":[40],"descriptions":[41],"and":[42,133],"visual":[43],"representations.":[44],"A":[45],"notable":[46],"challenge":[47],"associated":[48],"with":[49],"retrieval":[54,169],"corresponding":[56],"prompts":[57],"from":[58,172],"generated":[59,95],"images.":[60],"To":[61],"tackle":[62],"this":[63],"challenge,":[64],"we":[65,97],"employed":[66],"strategy":[68],"leverages":[70],"capabilities":[72],"ConvNeXt":[75],"model":[76,84],"within":[77],"OpenCLIP":[79],"framework.":[80],"Having":[81],"trained":[82],"on":[85,138],"an":[86],"extensive":[87],"dataset":[88],"nearly":[90],"2.1":[91],"million":[92],"images,":[96],"then":[98],"subjected":[99],"our":[100,118,157],"approach":[101,158],"to":[102,112,153],"evaluation":[104],"Kaggle":[107],"-":[110],"Image":[111],"Prompts":[113],"competition.":[114],"The":[115],"effectiveness":[116],"methodology":[119],"underscored":[121],"by":[122],"mean":[124],"cosine":[125],"similarity":[126],"score":[127],"0.63032":[129],"predicted":[132],"actual":[134],"prompt":[135],"embedding":[136],"vectors":[137],"private":[140],"test":[141],"set,":[142],"securing":[143],"silver":[145],"medal":[146],"position.":[147],"This":[148],"achievement":[149],"not":[150],"only":[151],"attests":[152],"robustness":[155],"but":[159],"also":[160],"signifies":[161],"its":[162],"potential":[163],"diverse":[165],"sectors":[166],"where":[167],"great":[176],"importance.":[177]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}