{"id":"https://openalex.org/W4415707941","doi":"https://doi.org/10.1109/icme59968.2025.11209588","title":"Think Twice: Empowering Action Recognition Models with Human-Like Deep Reasoning","display_name":"Think Twice: Empowering Action Recognition Models with Human-Like Deep Reasoning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707941","doi":"https://doi.org/10.1109/icme59968.2025.11209588"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5040983509","display_name":"Xiangning Ruan","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangning Ruan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101243457","display_name":"Baoxing Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoxing Xie","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112294881","display_name":"Zhaohui Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaohui Hou","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qixiang Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixiang Yin","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101754632","display_name":"Fei Su","orcid":"https://orcid.org/0000-0003-4245-4687"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Su","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079144156","display_name":"Zhicheng Zhao","orcid":"https://orcid.org/0000-0002-2761-7399"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Zhao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34159037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3822000026702881,"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":0.3822000026702881,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.22849999368190765,"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/T11431","display_name":"Action Observation and Synchronization","score":0.11580000072717667,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6043000221252441},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.5425999760627747},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.474700003862381},{"id":"https://openalex.org/keywords/clique","display_name":"Clique","score":0.38269999623298645},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3474999964237213},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.33880001306533813},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3248000144958496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6887999773025513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6276999711990356},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6043000221252441},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5425999760627747},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.474700003862381},{"id":"https://openalex.org/C2777035058","wikidata":"https://www.wikidata.org/wiki/Q1662634","display_name":"Clique","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36410000920295715},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35899999737739563},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2126579184","https://openalex.org/W2625366777","https://openalex.org/W3128138976","https://openalex.org/W4285166085","https://openalex.org/W4312558481","https://openalex.org/W4312651322","https://openalex.org/W4386065852","https://openalex.org/W4393148669","https://openalex.org/W4402753480","https://openalex.org/W4404724811"],"related_works":[],"abstract_inverted_index":{"When":[0],"engaged":[1],"in":[2],"complex":[3],"visual":[4,57],"cognition,":[5],"humans":[6],"tend":[7],"to":[8,48,65,99,104,114,118],"rely":[9],"on":[10,56],"their":[11],"experience":[12],"and":[13,19,31,94],"make":[14],"decisions":[15],"after":[16],"thinking":[17],"again":[18],"again.":[20],"Inspired":[21],"by":[22],"this,":[23],"we":[24],"pour":[25],"similar":[26,43],"capability":[27],"into":[28,73],"action":[29],"recognition":[30],"propose":[32],"a":[33,59,70,77,108,124],"new":[34],"Think":[35],"Twice":[36],"framework,":[37],"that":[38,45],"is,":[39],"think":[40],"twice":[41],"about":[42],"categories":[44,68],"are":[46,92],"easy":[47],"confuse,":[49],"thus":[50],"obtaining":[51],"performance":[52,138],"improvement.":[53],"Firstly,":[54],"based":[55],"similarity,":[58],"large":[60],"language":[61],"model":[62],"is":[63,102,112,144],"applied":[64],"cluster":[66],"all":[67],"of":[69],"given":[71],"dataset":[72],"disjoint":[74],"cliques.":[75],"Accordingly,":[76],"textual":[78],"prompt":[79,97,109],"for":[80],"each":[81,105],"clique":[82,101],"will":[83],"be":[84],"generated.":[85],"Secondly,":[86],"through":[87],"the":[88,96,116],"first":[89],"inference,":[90],"pseudo-labels":[91],"obtained,":[93],"then":[95],"corresponding":[98],"its":[100],"assigned":[103],"sample.":[106],"Thirdly,":[107],"learning":[110],"method":[111],"integrated":[113],"enable":[115],"framework":[117,129],"simulate":[119],"human-like":[120],"iterative":[121],"thinking,":[122],"yielding":[123],"final":[125],"decision.":[126],"Our":[127,142],"proposed":[128],"requires":[130],"minimal":[131],"parameters":[132],"while":[133],"achieving":[134],"state-of-the-art":[135],"parameter-efficient":[136],"fine-tuning(PEFT)":[137],"across":[139],"four":[140],"datasets.":[141],"code":[143],"available":[145],"at":[146],"https://github.com/KangRuan6/ThinkTwice.":[147]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}