{"id":"https://openalex.org/W4392904529","doi":"https://doi.org/10.1109/icassp48485.2024.10447556","title":"Exploring the Utility of Clip Priors for Visual Relationship Prediction","display_name":"Exploring the Utility of Clip Priors for Visual Relationship Prediction","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904529","doi":"https://doi.org/10.1109/icassp48485.2024.10447556"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447556","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447556","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/A5038385910","display_name":"Rakshith Subramanyam","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rakshith Subramanyam","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023204485","display_name":"T. S. Jayram","orcid":"https://orcid.org/0000-0001-5235-4853"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. S. Jayram","raw_affiliation_strings":["Lawrence Livermore National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026742436","display_name":"Rushil Anirudh","orcid":"https://orcid.org/0000-0002-4186-3502"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rushil Anirudh","raw_affiliation_strings":["Lawrence Livermore National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046632395","display_name":"Jayaraman J. Thiagarajan","orcid":"https://orcid.org/0000-0002-8517-5816"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayaraman J. Thiagarajan","raw_affiliation_strings":["Lawrence Livermore National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0246273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6825","last_page":"6829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9876000285148621,"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":0.9853000044822693,"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":0.7005696296691895},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6896147727966309},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6418324112892151},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.5992616415023804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5546683669090271},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4766015410423279},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.44122952222824097},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42841601371765137},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4218599796295166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1924554407596588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7005696296691895},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6896147727966309},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6418324112892151},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.5992616415023804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5546683669090271},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4766015410423279},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44122952222824097},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42841601371765137},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4218599796295166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1924554407596588},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"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":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447556","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447556","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2277195237","https://openalex.org/W2579549467","https://openalex.org/W2740962769","https://openalex.org/W2886970679","https://openalex.org/W2947385066","https://openalex.org/W2962785943","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W3035017890","https://openalex.org/W3199400376","https://openalex.org/W4312310776","https://openalex.org/W4385572897","https://openalex.org/W4385572962","https://openalex.org/W4386071547","https://openalex.org/W4390873628","https://openalex.org/W6620707391","https://openalex.org/W6747701563","https://openalex.org/W6791353385","https://openalex.org/W6845354634"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W3122088529","https://openalex.org/W2378211422","https://openalex.org/W3041320102","https://openalex.org/W2111669074","https://openalex.org/W2085259108","https://openalex.org/W3123087812"],"abstract_inverted_index":{"This":[0,121],"work":[1],"explores":[2],"the":[3,24,98,110,137,155],"challenges":[4],"of":[5,112],"leveraging":[6],"large-scale":[7],"vision":[8],"language":[9,46],"models,":[10],"such":[11,116,173],"as":[12,117,125,146],"CLIP,":[13],"for":[14,56,84,139],"visual":[15],"relationship":[16],"prediction":[17],"(VRP),":[18],"a":[19,29,73,147],"task":[20],"vital":[21],"in":[22,28,50],"understanding":[23],"relations":[25],"between":[26,53],"objects":[27],"scene":[30],"based":[31],"on":[32,97,154,172],"both":[33],"image":[34],"features":[35],"and":[36,72,119,163],"text":[37],"descriptors.":[38],"Despite":[39],"its":[40,144],"potential,":[41],"we":[42,60],"find":[43],"that":[44,103],"CLIP\u2019s":[45],"priors":[47],"are":[48],"restrictive":[49],"effectively":[51],"differentiating":[52],"various":[54],"predicates":[55],"VRP.":[57,85,151],"Towards":[58],"this,":[59],"present":[61],"CREPE":[62,86,107,126],"(CLIP":[63],"Representation":[64],"Enhanced":[65],"Predicate":[66],"Estimation),":[67],"which":[68],"utilizes":[69],"learnable":[70],"prompts":[71],"unique":[74],"contrastive":[75],"training":[76,171],"strategy":[77],"to":[78,150,161],"derive":[79],"reliable":[80],"CLIP":[81],"representations":[82,105],"suited":[83],"can":[87,127],"be":[88,128],"seamlessly":[89,129],"integrated":[90,130],"into":[91,131],"any":[92,132],"VRP":[93,114,133],"method.":[94],"Our":[95],"evaluations":[96],"Visual":[99],"Genome":[100],"benchmark":[101,157],"illustrate":[102],"using":[104],"from":[106],"significantly":[108],"enhances":[109],"performance":[111,153],"vanilla":[113],"methods,":[115],"UVTransE":[118],"VCTree.":[120],"enhancement":[122],"is":[123],"notable":[124],"method,":[134],"even":[135],"without":[136],"need":[138],"additional":[140],"calibration":[141],"techniques,":[142],"showcasing":[143],"efficacy":[145],"powerful":[148],"solution":[149],"CREPE\u2019s":[152],"Unrel":[156],"reveals":[158],"strong":[159],"generalization":[160],"diverse":[162],"previously":[164],"unseen":[165],"predicate":[166],"occurrences,":[167],"despite":[168],"lacking":[169],"explicit":[170],"examples.":[174]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}