{"id":"https://openalex.org/W4403791768","doi":"https://doi.org/10.1145/3664647.3681036","title":"Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainer","display_name":"Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainer","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791768","doi":"https://doi.org/10.1145/3664647.3681036"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681036","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5101343497","display_name":"Jiaming Lei","orcid":"https://orcid.org/0009-0001-6391-071X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Lei","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-6391-071X","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412889","display_name":"Lin Li","orcid":"https://orcid.org/0000-0002-5678-4487"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Hong Kong University of Science and Technology & AI Chip Center for Emerging Smart Systems, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-5678-4487","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology & AI Chip Center for Emerging Smart Systems, Hong Kong, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108020067","display_name":"Chunping Wang","orcid":"https://orcid.org/0000-0003-1854-8667"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunping Wang","raw_affiliation_strings":["Finvolution Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1854-8667","affiliations":[{"raw_affiliation_string":"Finvolution Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101485989","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-6142-9914"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6142-9914","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100336360","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-6148-9709","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.198504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1602","last_page":"1611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9897000193595886,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9897000193595886,"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/T10028","display_name":"Topic Modeling","score":0.9857000112533569,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9603000283241272,"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/shot","display_name":"Shot (pellet)","score":0.7034895420074463},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6849507093429565},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6160151958465576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47090911865234375},{"id":"https://openalex.org/keywords/grounded-theory","display_name":"Grounded theory","score":0.4472641348838806},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40379273891448975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38256239891052246},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.30963966250419617},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.12560927867889404},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09770902991294861},{"id":"https://openalex.org/keywords/qualitative-research","display_name":"Qualitative research","score":0.07932737469673157}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7034895420074463},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6849507093429565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6160151958465576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47090911865234375},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.4472641348838806},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40379273891448975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38256239891052246},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30963966250419617},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.12560927867889404},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09770902991294861},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.07932737469673157},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681036","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-146958","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-146958","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1519855838","https://openalex.org/W2168809519","https://openalex.org/W2423576022","https://openalex.org/W2884367402","https://openalex.org/W2963499153","https://openalex.org/W2963955422","https://openalex.org/W2963960318","https://openalex.org/W3035017890","https://openalex.org/W3098690786","https://openalex.org/W3109813419","https://openalex.org/W3144293453","https://openalex.org/W3205051885","https://openalex.org/W4200630531","https://openalex.org/W4285787895","https://openalex.org/W4287823756","https://openalex.org/W4292779060","https://openalex.org/W4312682661","https://openalex.org/W4312956471","https://openalex.org/W4385567149","https://openalex.org/W4386071652","https://openalex.org/W4386075969","https://openalex.org/W4386113259","https://openalex.org/W4386160459","https://openalex.org/W4390872395","https://openalex.org/W4390873633","https://openalex.org/W4390874107","https://openalex.org/W4393154528","https://openalex.org/W4401416473","https://openalex.org/W4402716219","https://openalex.org/W4402753931","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W1546533203","https://openalex.org/W2054080977","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W1511554945","https://openalex.org/W2015439768","https://openalex.org/W4361008414","https://openalex.org/W4396854307","https://openalex.org/W3040823075","https://openalex.org/W2773965352"],"abstract_inverted_index":{"Benefiting":[0],"from":[1,80,113],"strong":[2],"generalization":[3],"ability,":[4],"pre-trained":[5],"vision-language":[6],"models":[7,75],"(VLMs),":[8],"e.g.,":[9,83],"CLIP,":[10],"have":[11],"been":[12],"widely":[13],"utilized":[14],"in":[15,37,49,209,224],"zero-shot":[16,130,225],"scene":[17,207],"understanding.":[18],"Unlike":[19],"simple":[20],"recognition":[21,25],"tasks,":[22],"grounded":[23],"situation":[24],"(GSR)":[26],"requires":[27],"the":[28,38,50,114,139,156,197,216],"model":[29],"not":[30],"only":[31],"to":[32,42,86,154,187],"classify":[33],"salient":[34],"activity":[35],"(verb)":[36],"image,":[39],"but":[40],"also":[41],"detect":[43],"all":[44],"semantic":[45,61,175],"roles":[46,93],"that":[47,109],"participate":[48],"action.":[51],"This":[52],"complex":[53,206],"task":[54,78],"usually":[55],"involves":[56],"three":[57,144],"steps:":[58],"verb":[59,89,147,160],"recognition,":[60],"role":[62,176],"grounding,":[63],"and":[64,73,99,178,222],"noun":[65,102,180,185,190],"recognition.":[66,191],"Directly":[67],"employing":[68],"class-based":[69],"prompts":[70],"with":[71,94,200],"VLMs":[72],"grounding":[74,163],"for":[76,129,169],"this":[77,105,122],"suffers":[79],"several":[81],"limitations,":[82],"it":[84],"struggles":[85],"distinguish":[87],"ambiguous":[88],"concepts,":[90],"accurately":[91],"localize":[92],"fixed":[95],"verb-centric":[96,152,167],"template":[97],"input,":[98],"achieve":[100],"context-aware":[101,189],"predictions.":[103],"In":[104],"paper,":[106],"we":[107,124],"argue":[108],"these":[110],"limitations":[111],"stem":[112],"model's":[115,140],"poor":[116],"understanding":[117,208],"of":[118,158,196],"verb/noun":[119],"classes.":[120],"To":[121],"end,":[123],"introduce":[125],"a":[126],"new":[127],"approach":[128],"GSR":[131,198],"via":[132],"Language":[133],"EXplainer":[134],"(LEX),":[135],"which":[136,149,165,182],"significantly":[137],"boosts":[138],"comprehensive":[141],"capabilities":[142],"through":[143],"explainers:":[145],"1)":[146],"explainer,":[148,164,181,203],"generates":[150],"general":[151],"descriptions":[153,186],"enhance":[155],"discriminability":[157],"different":[159],"classes;":[161],"2)":[162],"rephrases":[166],"templates":[168],"clearer":[170],"understanding,":[171],"thereby":[172],"enhancing":[173],"precise":[174],"localization;":[177],"3)":[179],"creates":[183],"scene-specific":[184],"ensure":[188],"By":[192],"equipping":[193],"each":[194],"step":[195],"process":[199],"an":[201],"auxiliary":[202],"LEX":[204],"facilitates":[205],"real-world":[210],"scenarios.":[211],"Our":[212],"extensive":[213],"validations":[214],"on":[215],"SWiG":[217],"dataset":[218],"demonstrate":[219],"LEX's":[220],"effectiveness":[221],"interoperability":[223],"GSR.":[226]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}