{"id":"https://openalex.org/W4394686885","doi":"https://doi.org/10.1145/3657296","title":"SigFormer: Sparse Signal-guided Transformer for Multi-modal Action Segmentation","display_name":"SigFormer: Sparse Signal-guided Transformer for Multi-modal Action Segmentation","publication_year":2024,"publication_date":"2024-04-10","ids":{"openalex":"https://openalex.org/W4394686885","doi":"https://doi.org/10.1145/3657296"},"language":"en","primary_location":{"id":"doi:10.1145/3657296","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3657296","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3657296","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3657296","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100453271","display_name":"Qi Liu","orcid":"https://orcid.org/0009-0005-6238-6804"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Liu","raw_affiliation_strings":["Chinese Academy of Sciences Institute of Information Engineering, Beijing, China and \rUniversity of the Chinese Academy of Sciences School of Cyber Security, Beijing, China and \rKey Laboratory of Cyberspace Security Defense, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Institute of Information Engineering, Beijing, China and \rUniversity of the Chinese Academy of Sciences School of Cyber Security, Beijing, China and \rKey Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030704926","display_name":"Xinchen Liu","orcid":"https://orcid.org/0000-0003-4931-8821"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinchen Liu","raw_affiliation_strings":["JD Explore Academy, JD.com Inc, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD Explore Academy, JD.com Inc, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107772089","display_name":"K Liu","orcid":"https://orcid.org/0009-0004-8398-6369"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Liu","raw_affiliation_strings":["JD.com Inc, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD.com Inc, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024344221","display_name":"Xiaoyan Gu","orcid":"https://orcid.org/0000-0003-0673-0058"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Gu","raw_affiliation_strings":["Chinese Academy of Sciences Institute of Information Engineering, Beijing, China and \rUniversity of the Chinese Academy of Sciences School of Cyber Security, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences Institute of Information Engineering, Beijing, China and \rUniversity of the Chinese Academy of Sciences School of Cyber Security, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068917997","display_name":"Wu Liu","orcid":"https://orcid.org/0000-0003-1633-7575"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Liu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100453271"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4766822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"20","issue":"8","first_page":"1","last_page":"22"},"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":0.9993000030517578,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6378931999206543},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6358171105384827},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5936952829360962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5212365388870239},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37211498618125916},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3311924338340759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32713890075683594},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3214108943939209},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21340808272361755},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.19065237045288086},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1733449399471283},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.16856715083122253},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1258430778980255},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.04992374777793884}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6378931999206543},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6358171105384827},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5936952829360962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5212365388870239},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37211498618125916},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3311924338340759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32713890075683594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3214108943939209},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21340808272361755},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.19065237045288086},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1733449399471283},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.16856715083122253},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1258430778980255},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.04992374777793884}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3657296","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3657296","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3657296","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3657296","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3657296","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3657296","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G5989818691","display_name":null,"funder_award_id":"20220484063, and XDC02050200","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"}],"funders":[{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394686885.pdf","grobid_xml":"https://content.openalex.org/works/W4394686885.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1893516992","https://openalex.org/W2021057537","https://openalex.org/W2084856978","https://openalex.org/W2099614498","https://openalex.org/W2194775991","https://openalex.org/W2292288263","https://openalex.org/W2461621749","https://openalex.org/W2508429489","https://openalex.org/W2550143307","https://openalex.org/W2792345332","https://openalex.org/W2963524571","https://openalex.org/W2963853051","https://openalex.org/W3014565582","https://openalex.org/W3015880580","https://openalex.org/W3016234935","https://openalex.org/W3021673939","https://openalex.org/W3030949666","https://openalex.org/W3034802267","https://openalex.org/W3044644239","https://openalex.org/W3083550439","https://openalex.org/W3119038403","https://openalex.org/W3138516171","https://openalex.org/W3157403981","https://openalex.org/W3168126734","https://openalex.org/W3183430956","https://openalex.org/W4210453703","https://openalex.org/W4210582445","https://openalex.org/W4214493665","https://openalex.org/W4225147643","https://openalex.org/W4225271941","https://openalex.org/W4281255037","https://openalex.org/W4281749424","https://openalex.org/W4282928124","https://openalex.org/W4284897674","https://openalex.org/W4300717114","https://openalex.org/W4311356630","https://openalex.org/W4312108539","https://openalex.org/W4366352791","https://openalex.org/W4386050422","https://openalex.org/W4390872435","https://openalex.org/W6851242572"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W4379231730","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W4389858081","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2501551404","https://openalex.org/W4385583601"],"abstract_inverted_index":{"Multi-modal":[0],"human":[1],"action":[2,115,184,201],"segmentation":[3,202],"is":[4],"a":[5,11,64,175,199],"critical":[6],"and":[7,32,80,151,169,186,217],"challenging":[8],"task":[9],"with":[10],"wide":[12],"range":[13],"of":[14,19,25,39,154,166,213],"applications.":[15],"Nowadays,":[16],"the":[17,23,36,95,113,124,135,159,164,181,195],"majority":[18],"approaches":[20,197],"concentrate":[21],"on":[22,198],"fusion":[24,165],"dense":[26,79,156,167],"signals":[27,99,105],"(i.e.,":[28],"RGB,":[29],"optical":[30],"flow,":[31],"depth":[33],"maps).":[34],"However,":[35,102],"potential":[37],"contributions":[38],"sparse":[40,81,98,104,170],"IoT":[41],"sensor":[42],"signals,":[43,171],"which":[44],"can":[45],"be":[46],"crucial":[47],"for":[48,60],"achieving":[49],"accurate":[50],"recognition,":[51],"have":[52,220],"not":[53],"been":[54,221],"fully":[55],"explored.":[56],"To":[57],"make":[58],"up":[59],"this,":[61],"we":[62,120,140,172],"introduce":[63,141],"S":[65],"parse":[66],"s":[67],"i":[68],"gnal-":[69],"g":[70],"uided":[71],"Transformer":[72],"(":[73],"SigFormer":[74,193],")":[75],"to":[76,87,122,130,146],"combine":[77],"both":[78,149],"signals.":[82],"We":[83],"employ":[84],"mask":[85],"attention":[86],"fuse":[88],"localized":[89],"features":[90,153],"by":[91],"constraining":[92],"cross-attention":[93],"within":[94],"regions":[96],"where":[97],"are":[100,106],"valid.":[101],"since":[103],"discrete,":[107],"they":[108],"lack":[109],"sufficient":[110],"information":[111,126],"about":[112],"temporal":[114,187],"boundaries.":[116],"Therefore,":[117],"in":[118],"SigFormer,":[119],"propose":[121],"emphasize":[123],"boundary":[125,152],"at":[127,224],"two":[128],"stages":[129],"alleviate":[131],"this":[132],"problem.":[133],"In":[134],"first":[136],"feature":[137],"extraction":[138],"stage,":[139],"an":[142,209],"intermediate":[143],"bottleneck":[144],"module":[145],"jointly":[147],"learn":[148],"category":[150,185],"each":[155],"modality":[157],"through":[158],"inner":[160],"loss":[161],"functions.":[162],"After":[163],"modalities":[168],"then":[173],"devise":[174],"two-branch":[176],"architecture":[177],"that":[178,192],"explicitly":[179],"models":[180,219],"interrelationship":[182],"between":[183],"boundary.":[188],"Experimental":[189],"results":[190],"demonstrate":[191],"outperforms":[194],"state-of-the-art":[196],"multi-modal":[200],"dataset":[203],"from":[204],"real":[205],"industrial":[206],"environments,":[207],"reaching":[208],"outstanding":[210],"F1":[211],"score":[212],"0.958.":[214],"The":[215],"codes":[216],"pre-trained":[218],"made":[222],"available":[223],"https://github.com/LIUQI-creat/SigFormer":[225],".":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}