{"id":"https://openalex.org/W4403919361","doi":"https://doi.org/10.1109/ro-man60168.2024.10731472","title":"The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks","display_name":"The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks","publication_year":2024,"publication_date":"2024-08-26","ids":{"openalex":"https://openalex.org/W4403919361","doi":"https://doi.org/10.1109/ro-man60168.2024.10731472"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man60168.2024.10731472","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ro-man60168.2024.10731472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)","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/A5059586745","display_name":"Carmela Calabrese","orcid":"https://orcid.org/0000-0002-1760-501X"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Carmela Calabrese","raw_affiliation_strings":["Italian Institute of Technology,Humanoid Sensing and Perception,Genoa,Italy,16163"],"affiliations":[{"raw_affiliation_string":"Italian Institute of Technology,Humanoid Sensing and Perception,Genoa,Italy,16163","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042195784","display_name":"Stefano Berti","orcid":null},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Berti","raw_affiliation_strings":["Italian Institute of Technology,Humanoid Sensing and Perception,Genoa,Italy,16163"],"affiliations":[{"raw_affiliation_string":"Italian Institute of Technology,Humanoid Sensing and Perception,Genoa,Italy,16163","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048446378","display_name":"Giulia Pasquale","orcid":"https://orcid.org/0000-0002-7221-3553"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giulia Pasquale","raw_affiliation_strings":["Italian Institute of Technology,Humanoid Sensing and Perception,Genoa,Italy,16163"],"affiliations":[{"raw_affiliation_string":"Italian Institute of Technology,Humanoid Sensing and Perception,Genoa,Italy,16163","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009034971","display_name":"Lorenzo Natale","orcid":"https://orcid.org/0000-0002-8777-5233"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Natale","raw_affiliation_strings":["Italian Institute of Technology,Humanoid Sensing and Perception,Genoa,Italy,16163"],"affiliations":[{"raw_affiliation_string":"Italian Institute of Technology,Humanoid Sensing and Perception,Genoa,Italy,16163","institution_ids":["https://openalex.org/I30771326"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059586745"],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19637029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"857","last_page":"863"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9926000237464905,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9926000237464905,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9545999765396118,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9416000247001648,"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/principle-of-compositionality","display_name":"Principle of compositionality","score":0.8724130392074585},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7418088316917419},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6342750191688538},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6031970381736755},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5507859587669373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.479885458946228},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4649784564971924},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44255203008651733},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4054257571697235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4045396149158478},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07355326414108276}],"concepts":[{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.8724130392074585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418088316917419},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6342750191688538},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6031970381736755},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5507859587669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.479885458946228},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4649784564971924},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44255203008651733},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4054257571697235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4045396149158478},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07355326414108276},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man60168.2024.10731472","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ro-man60168.2024.10731472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)","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":31,"referenced_works":["https://openalex.org/W797104241","https://openalex.org/W2009119496","https://openalex.org/W2337252826","https://openalex.org/W2398232863","https://openalex.org/W2951702519","https://openalex.org/W2963052338","https://openalex.org/W2964260135","https://openalex.org/W2981965938","https://openalex.org/W3008041990","https://openalex.org/W3034257141","https://openalex.org/W3034679267","https://openalex.org/W3034978279","https://openalex.org/W3047235076","https://openalex.org/W3135450917","https://openalex.org/W3197341423","https://openalex.org/W4200578307","https://openalex.org/W4220694990","https://openalex.org/W4313562958","https://openalex.org/W4386075807","https://openalex.org/W4390190427","https://openalex.org/W4391630552","https://openalex.org/W6791353385","https://openalex.org/W6801567822","https://openalex.org/W6804467333","https://openalex.org/W6811251429","https://openalex.org/W6838269690","https://openalex.org/W6839546733","https://openalex.org/W6841672634","https://openalex.org/W6847435255","https://openalex.org/W6849829975","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4251923961","https://openalex.org/W1526190050","https://openalex.org/W2477397717","https://openalex.org/W2500457737","https://openalex.org/W2010490241","https://openalex.org/W4287025733","https://openalex.org/W4317425742","https://openalex.org/W2732813147","https://openalex.org/W2143460112","https://openalex.org/W2042906257"],"abstract_inverted_index":{"Addressing":[0],"multi-label":[1,56,72],"action":[2,57,64],"recognition":[3,65],"in":[4,13,26],"videos":[5],"represents":[6],"a":[7,51,62,109],"significant":[8],"challenge":[9],"for":[10,54,71,153],"robotic":[11],"applications":[12],"dynamic":[14],"environments,":[15],"especially":[16],"when":[17,137],"the":[18,68,104,131,145,158,161,177],"robot":[19],"is":[20,80,92],"required":[21],"to":[22,35,127],"cooperate":[23],"with":[24,67,125],"humans":[25],"tasks":[27],"that":[28,81,107,115],"involve":[29],"objects.":[30],"Existing":[31],"methods":[32,129],"still":[33],"struggle":[34],"recognize":[36],"unseen":[37,140],"actions":[38],"or":[39],"require":[40],"extensive":[41],"training":[42,83,152],"data.":[43],"To":[44],"overcome":[45],"these":[46],"problems,":[47],"we":[48],"propose":[49],"Dual-VCLIP,":[50],"unified":[52],"approach":[53],"zero-shot":[55,63],"recognition.":[58],"Dual-VCLIP":[59],"enhances":[60],"VCLIP,":[61],"method,":[66],"DualCoOp":[69],"method":[70,79,102,122],"image":[73],"classification.":[74],"The":[75],"strength":[76],"of":[77,111,147],"our":[78,101,121],"at":[82],"time":[84],"it":[85,91],"only":[86],"learns":[87],"two":[88],"prompts,":[89],"and":[90,134,163,171],"therefore":[93],"much":[94],"simpler":[95],"than":[96],"other":[97],"methods.":[98],"We":[99],"validate":[100],"on":[103,130,139,160,176],"Charades":[105],"dataset":[106],"includes":[108],"majority":[110],"object-based":[112],"actions,":[113],"demonstrating":[114],"-":[116,120],"despite":[117],"its":[118],"simplicity":[119],"performs":[123],"favorably":[124],"respect":[126],"existing":[128],"complete":[132],"dataset,":[133],"promising":[135],"performance":[136,162],"tested":[138],"actions.":[141],"Our":[142],"contribution":[143],"emphasizes":[144],"impact":[146],"verb-object":[148],"class-splits":[149],"during":[150],"robots\u2019":[151],"new":[154],"cooperative":[155],"tasks,":[156],"highlighting":[157],"influence":[159],"giving":[164],"insights":[165],"into":[166],"mitigating":[167],"biases.":[168],"Dataset":[169],"splits":[170],"code":[172],"are":[173],"publicly":[174],"available":[175],"project\u2019s":[178],"repository<sup":[179],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[180],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[181]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}