{"id":"https://openalex.org/W4390872124","doi":"https://doi.org/10.1109/iccv51070.2023.00270","title":"Learning Human-Human Interactions in Images from Weak Textual Supervision","display_name":"Learning Human-Human Interactions in Images from Weak Textual Supervision","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4390872124","doi":"https://doi.org/10.1109/iccv51070.2023.00270"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.14104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057074455","display_name":"Morris Alper","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Morris Alper","raw_affiliation_strings":["Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043669878","display_name":"Hadar Averbuch\u2010Elor","orcid":"https://orcid.org/0000-0003-3476-0940"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Hadar Averbuch-Elor","raw_affiliation_strings":["Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":70},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Visual Question Answering in Images and Videos","score":0.9653,"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":"Visual Question Answering in Images and Videos","score":0.9653,"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/T10862","display_name":"Deep Learning in Medical Image Analysis","score":0.9333,"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/T10812","display_name":"Human Action Recognition and Pose Estimation","score":0.9041,"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/image-captioning","display_name":"Image Captioning","score":0.590102},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language Understanding","score":0.553553},{"id":"https://openalex.org/keywords/human-activity-analysis","display_name":"Human Activity Analysis","score":0.516233},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"Visual Question Answering","score":0.508779}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6631587},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44586504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3901207},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37579954}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.00270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2304.14104","pdf_url":"https://arxiv.org/pdf/2304.14104","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2304.14104","pdf_url":"https://arxiv.org/pdf/2304.14104","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.61}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":78,"referenced_works":["https://openalex.org/W141352744","https://openalex.org/W1522734439","https://openalex.org/W1889081078","https://openalex.org/W1903612395","https://openalex.org/W1953661235","https://openalex.org/W1984549038","https://openalex.org/W2022633861","https://openalex.org/W2028742349","https://openalex.org/W2058256495","https://openalex.org/W2094016507","https://openalex.org/W2101105183","https://openalex.org/W2142258645","https://openalex.org/W2158168180","https://openalex.org/W2163292664","https://openalex.org/W2184544926","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2423576022","https://openalex.org/W2522042470","https://openalex.org/W2618799552","https://openalex.org/W2619947201","https://openalex.org/W2736442062","https://openalex.org/W2791369416","https://openalex.org/W2810685774","https://openalex.org/W2886641317","https://openalex.org/W2888096830","https://openalex.org/W2888814092","https://openalex.org/W2917819557","https://openalex.org/W2944006115","https://openalex.org/W2955882737","https://openalex.org/W2961193895","https://openalex.org/W2962711930","https://openalex.org/W2962844592","https://openalex.org/W2963097937","https://openalex.org/W2963524571","https://openalex.org/W2963736842","https://openalex.org/W2964134613","https://openalex.org/W2964225075","https://openalex.org/W2969812797","https://openalex.org/W2974686944","https://openalex.org/W2976818183","https://openalex.org/W2982232158","https://openalex.org/W2994508843","https://openalex.org/W3009811369","https://openalex.org/W3009916215","https://openalex.org/W3034383590","https://openalex.org/W3035252911","https://openalex.org/W3096682293","https://openalex.org/W3106234277","https://openalex.org/W3113370935","https://openalex.org/W3118781290","https://openalex.org/W3123791969","https://openalex.org/W3138154797","https://openalex.org/W3154985639","https://openalex.org/W3155104583","https://openalex.org/W3168488421","https://openalex.org/W3171169846","https://openalex.org/W3174164794","https://openalex.org/W3174480456","https://openalex.org/W3195577433","https://openalex.org/W3200114289","https://openalex.org/W3201090304","https://openalex.org/W3212496002","https://openalex.org/W3213454282","https://openalex.org/W3213990450","https://openalex.org/W4214731992","https://openalex.org/W4224048531","https://openalex.org/W4288089799","https://openalex.org/W4292199884","https://openalex.org/W4292779060","https://openalex.org/W4307106676","https://openalex.org/W4312900708","https://openalex.org/W4313483544","https://openalex.org/W4378908626","https://openalex.org/W4385570969","https://openalex.org/W4386072519","https://openalex.org/W4386076215","https://openalex.org/W99952337"],"related_works":["https://openalex.org/W3116076068","https://openalex.org/W2775347418","https://openalex.org/W2772917594","https://openalex.org/W2755342338","https://openalex.org/W2229312674","https://openalex.org/W2166024367","https://openalex.org/W2079911747","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Interactions":[0],"between":[1,51],"humans":[2],"are":[3],"diverse":[4],"and":[5,49,116,119,135,150,155],"context-dependent,":[6],"but":[7],"previous":[8],"works":[9],"have":[10],"treated":[11],"them":[12],"as":[13,31,106],"categorical,":[14],"disregarding":[15],"the":[16,44,55,85],"heavy":[17],"tail":[18],"of":[19,27,47,57,111,122],"possible":[20],"interactions.":[21],"We":[22,82,125,142],"propose":[23],"a":[24,35,75,96,109,157],"new":[25],"paradigm":[26],"learning":[28],"human-human":[29,102,164],"interactions":[30,103],"free":[32],"text":[33],"from":[34],"single":[36],"still":[37,162],"image,":[38],"allowing":[39],"for":[40,61,161],"flexibility":[41],"in":[42,104],"modeling":[43],"unlimited":[45],"space":[46],"situations":[48],"relationships":[50],"people.":[52],"To":[53],"overcome":[54],"absence":[56],"data":[58,72],"labelled":[59],"specifically":[60],"this":[62,89,140],"task,":[63],"we":[64],"use":[65],"knowledge":[66],"distillation":[67],"applied":[68],"to":[69,94,99],"synthetic":[70],"caption":[71],"produced":[73,87],"by":[74,88,108],"large":[76],"language":[77],"model":[78,98],"without":[79],"explicit":[80],"supervision.":[81],"show":[83,127],"that":[84,113,128],"pseudo-labels":[86,151],"procedure":[90],"can":[91],"be":[92],"used":[93],"train":[95],"captioning":[97,134],"effectively":[100],"understand":[101],"images,":[105],"measured":[107],"variety":[110],"metrics":[112],"measure":[114],"textual":[115],"semantic":[117],"faithfulness":[118],"factual":[120],"groundedness":[121],"our":[123,129,148],"predictions.":[124],"further":[126],"approach":[130],"outperforms":[131],"SOTA":[132],"image":[133,163],"situation":[136],"recognition":[137],"models":[138],"on":[139],"task.":[141],"will":[143],"releas":[144],"