{"id":"https://openalex.org/W7124949038","doi":"https://doi.org/10.1109/cbmi66578.2025.11339243","title":"Mitigating Shortcut Learning in Online Action Detection and Anticipation via Cross-Modal Semantic Alignment","display_name":"Mitigating Shortcut Learning in Online Action Detection and Anticipation via Cross-Modal Semantic Alignment","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7124949038","doi":"https://doi.org/10.1109/cbmi66578.2025.11339243"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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/A5004812842","display_name":"Sensen Wang","orcid":"https://orcid.org/0009-0000-4394-5723"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sensen Wang","raw_affiliation_strings":["Xi'an Jiaotong University,College of Artificial Intelligence,Xi’ an,China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University,College of Artificial Intelligence,Xi’ an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123370633","display_name":"Yuehu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehu Liu","raw_affiliation_strings":["Xi'an Jiaotong University,College of Artificial Intelligence,Xi’ an,China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University,College of Artificial Intelligence,Xi’ an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123409441","display_name":"Chi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["Xi'an Jiaotong University,College of Artificial Intelligence,Xi’ an,China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University,College of Artificial Intelligence,Xi’ an,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004812842"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7111662,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.7318999767303467,"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":0.7318999767303467,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2223999947309494,"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":0.00839999970048666,"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/overfitting","display_name":"Overfitting","score":0.7907000184059143},{"id":"https://openalex.org/keywords/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.741100013256073},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6446999907493591},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6251999735832214},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6133000254631042},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.54830002784729},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5188999772071838},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.46630001068115234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954999804496765},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7907000184059143},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.741100013256073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6869999766349792},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6446999907493591},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6251999735832214},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6133000254631042},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.54830002784729},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.46630001068115234},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4433000087738037},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4189000129699707},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.38280001282691956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3580999970436096},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2685999870300293},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.26429998874664307}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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":26,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2064675550","https://openalex.org/W2342437993","https://openalex.org/W2507009361","https://openalex.org/W2524280059","https://openalex.org/W2605300166","https://openalex.org/W2897770249","https://openalex.org/W2963524571","https://openalex.org/W2963720581","https://openalex.org/W2989506443","https://openalex.org/W3016970897","https://openalex.org/W3035130921","https://openalex.org/W3198377975","https://openalex.org/W4214589115","https://openalex.org/W4312355936","https://openalex.org/W4312528573","https://openalex.org/W4312690503","https://openalex.org/W4327571590","https://openalex.org/W4385245566","https://openalex.org/W4386608764","https://openalex.org/W4386790226","https://openalex.org/W4390873483","https://openalex.org/W4390874667","https://openalex.org/W4402351152","https://openalex.org/W4403780569","https://openalex.org/W4415797610"],"related_works":[],"abstract_inverted_index":{"Online":[0,5,89],"Action":[1,6,90],"Detection":[2],"(OAD)":[3],"and":[4,98,115,131,135,143,178,193,201,209],"Anticipation":[7],"(OAA)":[8],"are":[9,196],"conventionally":[10],"framed":[11],"as":[12,100],"multi-class":[13],"classification":[14],"tasks":[15],"reliant":[16],"on":[17,140,207],"action":[18,36,122,137],"representation":[19,80],"learning.":[20,40],"However,":[21],"existing":[22],"methods":[23],"easily":[24],"overfit":[25],"to":[26,71,154,170,191],"appearance":[27],"features":[28],"corre-lated":[29],"with":[30,50,181],"specific":[31],"categories,":[32],"neglecting":[33],"semantically":[34],"meaningful":[35],"features,":[37],"i.e.,":[38],"shortcut":[39,56,107],"This":[41,104],"results":[42,198],"in":[43,77],"a":[44,86,92,150],"misinter-pretation":[45],"of":[46,159,199],"visually":[47],"similar":[48,190],"actions":[49,114,195],"distinct":[51],"semantics.":[52],"We":[53],"argue":[54],"that":[55,95],"learning":[57,81,108],"stems":[58],"from":[59,68,124],"the":[60,111,157,165,187,197],"one-hot":[61],"label":[62,160,176],"supervision,":[63],"which":[64],"simplifies":[65],"task":[66],"objectives":[67],"semantic":[69,179],"recognition":[70],"category":[72],"differentiation.":[73],"Inspired":[74],"by":[75,109],"advances":[76],"text-supervised":[78],"visual":[79,182],"(e.g.,":[82],"CLIP),":[83],"we":[84],"propose":[85],"CLIP":[87,167],"for":[88,156],"(CLIP40A),":[91],"unified":[93],"model":[94],"formulates":[96],"OAD":[97,200],"OAA":[99],"Video-Text":[101],"Retrieval":[102],"tasks.":[103],"approach":[105],"mitigates":[106],"supervising":[110],"alignment":[112],"between":[113],"their":[116],"corresponding":[117],"labels.":[118],"Specifically,":[119],"CLIP40A":[120,148,163,203],"extracts":[121],"contexts":[123,142],"distant":[125],"videos":[126],"across":[127],"multiple":[128],"time":[129],"scales,":[130],"then":[132],"learns":[133],"current":[134,192],"future":[136,194],"representations":[138],"based":[139],"these":[141],"recent":[144],"videos.":[145],"For":[146],"labels,":[147],"introduces":[149],"learnable":[151],"prompt":[152],"mechanism":[153],"compensate":[155],"lack":[158],"contexts.":[161],"Subsequently,":[162],"leverages":[164],"pretrained":[166],"text":[168],"encoder":[169],"convert":[171],"labels":[172,188],"into":[173],"representations,":[174],"preserving":[175],"semantics":[177],"associations":[180],"data.":[183],"By":[184],"similarity":[185],"comparisons,":[186],"most":[189],"OAA.":[202],"achieves":[204],"superior":[205],"performance":[206],"THUMOS'14":[208],"TVSeries.":[210]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-21T00:00:00"}