{"id":"https://openalex.org/W4386076071","doi":"https://doi.org/10.1109/cvpr52729.2023.01810","title":"Two-Stream Networks for Weakly-Supervised Temporal Action Localization with Semantic-Aware Mechanisms","display_name":"Two-Stream Networks for Weakly-Supervised Temporal Action Localization with Semantic-Aware Mechanisms","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386076071","doi":"https://doi.org/10.1109/cvpr52729.2023.01810"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.01810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.01810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5100445311","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0002-9807-2293"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Ant Group,Hangzhou,China","Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group,Hangzhou,China","institution_ids":[]},{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348448","display_name":"Yadong Li","orcid":"https://orcid.org/0000-0002-6448-9736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yadong Li","raw_affiliation_strings":["Ant Group,Hangzhou,China","Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group,Hangzhou,China","institution_ids":[]},{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100332096","display_name":"Hongbin Wang","orcid":"https://orcid.org/0000-0003-2176-2998"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongbin Wang","raw_affiliation_strings":["Ant Group,Hangzhou,China","Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group,Hangzhou,China","institution_ids":[]},{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100445311"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4436,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94247313,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"18878","last_page":"18887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9940999746322632,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9901999831199646,"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/snippet","display_name":"Snippet","score":0.7767965793609619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7705364227294922},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6089375019073486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5952439308166504},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.581649124622345},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.5643660426139832},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.5308604836463928},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.513093113899231},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.490771621465683},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.49011191725730896},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38521093130111694},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3462247848510742},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.17919716238975525}],"concepts":[{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.7767965793609619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7705364227294922},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6089375019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5952439308166504},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.581649124622345},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.5643660426139832},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.5308604836463928},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.513093113899231},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.490771621465683},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.49011191725730896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38521093130111694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3462247848510742},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.17919716238975525},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52729.2023.01810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.01810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2156303437","https://openalex.org/W2342662179","https://openalex.org/W2604113307","https://openalex.org/W2619947201","https://openalex.org/W2884293275","https://openalex.org/W2895240652","https://openalex.org/W2920182456","https://openalex.org/W2948229620","https://openalex.org/W2962677524","https://openalex.org/W2962709777","https://openalex.org/W2962876901","https://openalex.org/W2963524571","https://openalex.org/W2964158702","https://openalex.org/W2964216549","https://openalex.org/W2970724283","https://openalex.org/W2983918066","https://openalex.org/W2984478308","https://openalex.org/W2988098865","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2997063620","https://openalex.org/W2997706915","https://openalex.org/W2998702159","https://openalex.org/W3034572008","https://openalex.org/W3034623254","https://openalex.org/W3035585099","https://openalex.org/W3092976396","https://openalex.org/W3095669214","https://openalex.org/W3097664769","https://openalex.org/W3100481960","https://openalex.org/W3109715102","https://openalex.org/W3109986575","https://openalex.org/W3110589170","https://openalex.org/W3110718159","https://openalex.org/W3112040205","https://openalex.org/W3118479201","https://openalex.org/W3149230594","https://openalex.org/W3173212682","https://openalex.org/W3173459793","https://openalex.org/W3173698268","https://openalex.org/W3173874725","https://openalex.org/W3174106785","https://openalex.org/W3174421047","https://openalex.org/W3175580044","https://openalex.org/W3176444885","https://openalex.org/W3176641851","https://openalex.org/W3178036208","https://openalex.org/W3189379416","https://openalex.org/W3203848195","https://openalex.org/W3207927851","https://openalex.org/W4213188130","https://openalex.org/W4221167641","https://openalex.org/W4226500165","https://openalex.org/W4230270698","https://openalex.org/W4312383773","https://openalex.org/W4312384316","https://openalex.org/W4312421085","https://openalex.org/W4312560592","https://openalex.org/W6682864246","https://openalex.org/W6751081422","https://openalex.org/W6751389191","https://openalex.org/W6751495912","https://openalex.org/W6753013641","https://openalex.org/W6755209196","https://openalex.org/W6760239191","https://openalex.org/W6763713025","https://openalex.org/W6770961085","https://openalex.org/W6770995305","https://openalex.org/W6774816724","https://openalex.org/W6775653918","https://openalex.org/W6780511221","https://openalex.org/W6780930291","https://openalex.org/W6784219776","https://openalex.org/W6784563639","https://openalex.org/W6785234230","https://openalex.org/W6787021940","https://openalex.org/W6793520193","https://openalex.org/W6799780884","https://openalex.org/W6800168142","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W1607713096","https://openalex.org/W3036724449","https://openalex.org/W2798329462","https://openalex.org/W1511521437","https://openalex.org/W3201315194","https://openalex.org/W4318980730","https://openalex.org/W4289376745","https://openalex.org/W2950904665","https://openalex.org/W2896663616","https://openalex.org/W4393154133"],"abstract_inverted_index":{"Weakly-supervised":[0],"temporal":[1,148],"action":[2,7,53,81,91],"localization":[3],"aims":[4],"to":[5,26,95,98,107,133,146],"detect":[6,19],"boundaries":[8],"in":[9],"untrimmed":[10],"videos":[11],"with":[12,44],"only":[13],"video-level":[14,27],"annotations.":[15],"Most":[16],"existing":[17,177],"schemes":[18],"tem-poral":[20],"regions":[21],"that":[22,42,123,170],"are":[23,74,93],"most":[24],"responsive":[25],"classification,":[28],"but":[29],"they":[30],"overlook":[31],"the":[32,51,56,75,79,89,99,105,109,125,129,144,151,157],"semantic":[33],"consistency":[34],"between":[35],"frames.":[36],"In":[37],"this":[38,65],"paper,":[39],"we":[40,67,118],"hypothesize":[41],"snippets":[43,86],"similar":[45],"representations":[46,84],"should":[47],"be":[48,96],"considered":[49],"as":[50,88],"same":[52,90,100],"class":[54,76,101],"despite":[55],"absence":[57],"of":[58,78,85,111],"supervision":[59],"signals":[60],"on":[61,156],"each":[62],"snippet.":[63],"To":[64],"end,":[66],"devise":[68],"a":[69,120],"learnable":[70],"dictionary":[71],"where":[72,164],"entries":[73],"centroids":[77],"corresponding":[80],"categories.":[82],"The":[83],"identified":[87],"category":[92],"induced":[94],"close":[97],"centroid,":[102],"which":[103],"guides":[104],"network":[106],"perceive":[108],"semantics":[110],"frames":[112],"and":[113,128,137,161,167],"avoid":[114],"unreasonable":[115],"localization.":[116],"Besides,":[117],"propose":[119],"two-stream":[121],"framework":[122],"in-tegrates":[124],"attention":[126],"mechanism":[127],"multiple-instance":[130],"learning":[131],"strategy":[132],"extract":[134],"fine-grained":[135],"clues":[136],"salient":[138],"features":[139],"respectively.":[140],"Their":[141],"complementarity":[142],"enables":[143],"model":[145,153,172],"refine":[147],"boundaries.":[149],"Finally,":[150],"developed":[152],"is":[154],"validated":[155],"publicly":[158],"available":[159],"THUMOS-14":[160],"ActivityNet-1.3":[162],"datasets,":[163],"substantial":[165],"experiments":[166],"analyses":[168],"demonstrate":[169],"our":[171],"achieves":[173],"remark-able":[174],"advances":[175],"over":[176],"methods.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}