{"id":"https://openalex.org/W4414880479","doi":"https://doi.org/10.1145/3746027.3754770","title":"Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection","display_name":"Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4414880479","doi":"https://doi.org/10.1145/3746027.3754770"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754770","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754770","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754770","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101868306","display_name":"Francesco Tonini","orcid":"https://orcid.org/0000-0002-1938-3449"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]},{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Tonini","raw_affiliation_strings":["University of Trento, Trento, Italy and Fondazione Bruno Kessler, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1938-3449","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy and Fondazione Bruno Kessler, Trento, Italy","institution_ids":["https://openalex.org/I193223587","https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039878198","display_name":"Lorenzo Vaquero","orcid":"https://orcid.org/0000-0002-1874-3078"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Vaquero","raw_affiliation_strings":["Fondazione Bruno Kessler, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1874-3078","affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler, Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749512","display_name":"Alessandro Conti","orcid":"https://orcid.org/0000-0002-3044-1320"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Conti","raw_affiliation_strings":["University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-3044-1320","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057859690","display_name":"Cigdem Beyan","orcid":"https://orcid.org/0000-0002-9583-0087"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Cigdem Beyan","raw_affiliation_strings":["Department of Computer Science, University of Verona, Verona, Italy"],"raw_orcid":"https://orcid.org/0000-0002-9583-0087","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065059558","display_name":"Elisa Ricci","orcid":"https://orcid.org/0000-0002-0228-1147"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]},{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elisa Ricci","raw_affiliation_strings":["University of Trento, Trento, Italy and Fondazione Bruno Kessler, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0228-1147","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy and Fondazione Bruno Kessler, Trento, Italy","institution_ids":["https://openalex.org/I193223587","https://openalex.org/I2277624104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2801","last_page":"2810"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9969000220298767,"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/semantics","display_name":"Semantics (computer science)","score":0.6902999877929688},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6055999994277954},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5776000022888184},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5400999784469604},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5004000067710876},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.33730000257492065},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.3246000111103058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8217999935150146},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6902999877929688},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6055999994277954},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5342000126838684},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5004000067710876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.400299996137619},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3727000057697296},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3125},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754770","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754770","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.17456","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.17456","pdf_url":"https://arxiv.org/pdf/2507.17456","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754770","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754770","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1928841346","display_name":null,"funder_award_id":"101120237,101168272,101214398","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"},{"id":"https://openalex.org/G6016056428","display_name":null,"funder_award_id":"PE00000013,2022EX F3HX","funder_id":"https://openalex.org/F4320331528","funder_display_name":"Ministero dell'Universit\u00e0 e della Ricerca"}],"funders":[{"id":"https://openalex.org/F4320331528","display_name":"Ministero dell'Universit\u00e0 e della Ricerca","ror":null},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Human-Object":[0],"Interaction":[1],"(HOI)":[2],"detection":[3,91],"aims":[4],"to":[5,27,37,40,45,132,142],"identify":[6],"humans":[7],"and":[8,12,42,48,75,104,114,127,161,174],"objects":[9],"within":[10,108],"images":[11],"interpret":[13],"their":[14],"interactions.":[15,50,144,184],"Existing":[16],"HOI":[17,90],"methods":[18],"rely":[19],"heavily":[20],"on":[21],"large":[22],"datasets":[23],"with":[24,96,177],"manual":[25],"annotations":[26,34],"learn":[28],"interactions":[29],"from":[30],"visual":[31,105,125,160],"cues.":[32],"These":[33],"are":[35],"labor-intensive":[36],"create,":[38],"prone":[39],"inconsistency,":[41],"limit":[43],"scalability":[44],"new":[46],"domains":[47],"rare":[49,143,183],"We":[51],"argue":[52],"that":[53,100,153,167],"recent":[54],"advances":[55],"in":[56,64,182],"Vision-Language":[57],"Models":[58],"(VLMs)":[59],"offer":[60],"untapped":[61],"potential,":[62],"particularly":[63,180],"enhancing":[65],"interaction":[66,106,116,130],"representation.":[67],"While":[68],"prior":[69],"work":[70],"has":[71],"injected":[72],"such":[73],"potential":[74],"even":[76],"proposed":[77],"training-free":[78,89,171],"methods,":[79],"there":[80],"remain":[81],"key":[82],"gaps.":[83],"Consequently,":[84],"we":[85,146],"propose":[86,147],"a":[87,109,121,148],"novel":[88],"framework":[92],"for":[93],"Dynamic":[94],"Scoring":[95],"enhanced":[97],"semantics":[98],"(dysco)":[99],"effectively":[101],"utilizes":[102],"textual":[103,162],"representations":[107],"multimodal":[110],"registry,":[111],"enabling":[112],"robust":[113],"nuanced":[115],"understanding.":[117],"This":[118],"registry":[119],"incorporates":[120],"small":[122],"set":[123],"of":[124,137,158],"cues":[126],"uses":[128],"innovative":[129],"signatures":[131],"improve":[133],"the":[134,156,159],"semantic":[135],"alignment":[136],"verbs,":[138],"facilitating":[139],"effective":[140],"generalization":[141],"Additionally,":[145],"unique":[149],"multi-head":[150],"attention":[151],"mechanism":[152],"adaptively":[154],"weights":[155],"contributions":[157],"features.":[163],"Experimental":[164],"results":[165],"demonstrate":[166],"our":[168],"dysco":[169],"surpasses":[170],"state-of-the-art":[172],"models":[173],"is":[175,186],"competitive":[176],"training-based":[178],"approaches,":[179],"excelling":[181],"Code":[185],"available":[187],"at":[188],"https://github.com/francescotonini/dysco.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
