{"id":"https://openalex.org/W4415540316","doi":"https://doi.org/10.1145/3746027.3755157","title":"Seeing the Undefined: Chain-of-Action for Generative Semantic Labels","display_name":"Seeing the Undefined: Chain-of-Action for Generative Semantic Labels","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540316","doi":"https://doi.org/10.1145/3746027.3755157"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755157","pdf_url":null,"source":null,"license":null,"license_id":null,"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":["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/A5011322650","display_name":"Meng Wei","orcid":"https://orcid.org/0009-0000-3836-6487"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wei","raw_affiliation_strings":["School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China and Mine Digitization Engineering Research Center of the Ministry of Education, Xuzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-3836-6487","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China and Mine Digitization Engineering Research Center of the Ministry of Education, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086917578","display_name":"Zhongnian Li","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongnian Li","raw_affiliation_strings":["School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China and Mine Digitization Engineering Research Center of the Ministry of Education, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3364-8703","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China and Mine Digitization Engineering Research Center of the Ministry of Education, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053428173","display_name":"Peng Ying","orcid":"https://orcid.org/0009-0005-8007-5583"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Ying","raw_affiliation_strings":["School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China and Mine Digitization Engineering Research Center of the Ministry of Education, Xuzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-8007-5583","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China and Mine Digitization Engineering Research Center of the Ministry of Education, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014874717","display_name":"Xinzheng Xu","orcid":"https://orcid.org/0000-0001-6973-799X"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinzheng Xu","raw_affiliation_strings":["School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China, The State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China, and Mine Digitization Engineering Research Center of the Ministry of Education, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6973-799X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China, The State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China, and Mine Digitization Engineering Research Center of the Ministry of Education, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33092439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3702","last_page":"3711"},"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/T10028","display_name":"Topic Modeling","score":0.9966999888420105,"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":0.9959999918937683,"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/task","display_name":"Task (project management)","score":0.6542999744415283},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6376000046730042},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6132000088691711},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6111999750137329},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5940999984741211},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5759999752044678},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5640000104904175},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795199990272522},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6542999744415283},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6376000046730042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6193000078201294},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6132000088691711},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6111999750137329},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5940999984741211},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5759999752044678},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5640000104904175},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4171000123023987},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37119999527931213},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2597000002861023}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3111527350","display_name":null,"funder_award_id":"No. 62306320, 61976217","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G392641027","display_name":null,"funder_award_id":"No. BK20231063","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2007972815","https://openalex.org/W2963518342","https://openalex.org/W4285999563","https://openalex.org/W4386057720","https://openalex.org/W4392172801","https://openalex.org/W4393160302","https://openalex.org/W4393161084","https://openalex.org/W4402727764"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1,211],"in":[2,10,32,214,226],"vision-language":[3],"models":[4],"(VLMs)":[5],"have":[6],"demonstrated":[7],"remarkable":[8],"capabilities":[9],"image":[11,65,98],"classification":[12],"by":[13,69,119],"leveraging":[14],"predefined":[15,71],"sets":[16],"of":[17,60,97,141,176,197],"labels":[18,62,72,217],"to":[19,55,111,158,165,199],"construct":[20],"text":[21],"prompts":[22],"for":[23,63,223],"zero-shot":[24,76],"reasoning.":[25],"However,":[26],"these":[27],"approaches":[28],"face":[29],"significant":[30,188],"limitations":[31],"undefined":[33],"domains,":[34],"where":[35],"the":[36,113,120,135,152,159,163,174,195,212],"label":[37],"space":[38],"is":[39,117],"vocabulary-unknown":[40],"and":[41,87,93,147,168,202,228],"composite.":[42],"We":[43,172],"thus":[44],"introduce":[45],"Generative":[46],"Semantic":[47],"Labels":[48],"(GSLs),":[49],"a":[50,57,70,91,139],"novel":[51],"task":[52,137],"that":[53,122],"aims":[54],"predict":[56],"comprehensive":[58,167],"set":[59],"semantic":[61,170,205,216],"an":[64,107],"without":[66],"being":[67],"constrained":[68],"set.":[73],"Unlike":[74],"traditional":[75],"classification,":[77],"GSLs":[78,114,136],"generates":[79],"multiple":[80],"semantic-level":[81],"labels,":[82],"encompassing":[83],"objects,":[84],"scenes,":[85],"attributes,":[86],"relationships,":[88],"thereby":[89],"providing":[90],"richer":[92],"more":[94],"accurate":[95,169,201],"representation":[96],"content.":[99],"In":[100],"this":[101],"paper,":[102],"we":[103],"propose":[104],"Chain-of-Action":[105],"(CoA),":[106],"innovative":[108],"method":[109],"designed":[110],"tackle":[112],"task.":[115],"CoA":[116,133,177,198],"motivated":[118],"observation":[121],"enriched":[123,156],"contextual":[124],"information":[125,150],"significantly":[126],"improves":[127],"generative":[128,215],"performance":[129,192],"during":[130],"inference.":[131],"Specifically,":[132],"decomposes":[134],"into":[138],"sequence":[140],"detailed":[142],"actions.":[143],"Each":[144],"action":[145],"extracts":[146],"merges":[148],"key":[149,191],"from":[151],"previous":[153],"step,":[154],"passing":[155],"context":[157],"next,":[160],"ultimately":[161],"guiding":[162],"VLM":[164],"generate":[166,200],"labels.":[171,206],"evaluate":[173],"effectiveness":[175],"through":[178],"extensive":[179],"experiments":[180],"on":[181],"widely-used":[182],"benchmark":[183],"datasets.":[184],"The":[185],"results":[186],"demonstrate":[187],"improvements":[189],"across":[190],"metrics,":[193],"validating":[194],"capability":[196],"contextually":[203],"rich":[204],"Our":[207],"work":[208],"not":[209],"only":[210],"state-of-the-art":[213],"but":[218],"also":[219],"opens":[220],"new":[221],"avenues":[222],"applying":[224],"VLMs":[225],"open-ended":[227],"dynamic":[229],"real-world":[230],"scenarios.":[231]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}