{"id":"https://openalex.org/W4416748918","doi":"https://doi.org/10.1109/iros60139.2025.11247674","title":"MaskSem: Semantic-Guided Masking for Learning 3D Hybrid High-Order Motion Representation","display_name":"MaskSem: Semantic-Guided Masking for Learning 3D Hybrid High-Order Motion Representation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748918","doi":"https://doi.org/10.1109/iros60139.2025.11247674"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5100323766","display_name":"Wei Wei","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":true,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768906","display_name":"Shaojie Zhang","orcid":"https://orcid.org/0000-0001-8168-7112"},"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":"Shaojie Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008886406","display_name":"Yonghao Dang","orcid":"https://orcid.org/0000-0002-1118-5587"},"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":"Yonghao Dang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100606496","display_name":"Jianqin Yin","orcid":"https://orcid.org/0000-0002-1595-2499"},"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":"Jianqin Yin","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100323766"],"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":0.36927311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20239","last_page":"20246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9180999994277954,"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":0.9180999994277954,"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/T12290","display_name":"Human Motion and Animation","score":0.045099999755620956,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.009499999694526196,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/motion","display_name":"Motion (physics)","score":0.7364000082015991},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5422999858856201},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5388000011444092},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5360999703407288},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5152000188827515},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4997999966144562},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4368000030517578},{"id":"https://openalex.org/keywords/structure-from-motion","display_name":"Structure from motion","score":0.41200000047683716},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.40049999952316284}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.739300012588501},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7364000082015991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301999926567078},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6194999814033508},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5388000011444092},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5152000188827515},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4997999966144562},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.41200000047683716},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3325999975204468},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.29179999232292175},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C124774092","wikidata":"https://www.wikidata.org/wiki/Q6917782","display_name":"Motion field","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2007057255","https://openalex.org/W2510185399","https://openalex.org/W2616247523","https://openalex.org/W2716916105","https://openalex.org/W2765433083","https://openalex.org/W2787919227","https://openalex.org/W2944006115","https://openalex.org/W2948058585","https://openalex.org/W2963076818","https://openalex.org/W2963465695","https://openalex.org/W2964134613","https://openalex.org/W3034548564","https://openalex.org/W3049455300","https://openalex.org/W3113067059","https://openalex.org/W3169413442","https://openalex.org/W3203227473","https://openalex.org/W3203634062","https://openalex.org/W3205106480","https://openalex.org/W4200634815","https://openalex.org/W4312543491","https://openalex.org/W4312757522","https://openalex.org/W4312841534","https://openalex.org/W4313156423","https://openalex.org/W4313185874","https://openalex.org/W4379184955","https://openalex.org/W4382240189","https://openalex.org/W4382459184","https://openalex.org/W4385768200","https://openalex.org/W4386065445","https://openalex.org/W4386215080","https://openalex.org/W4387968040","https://openalex.org/W4388240477","https://openalex.org/W4389665476","https://openalex.org/W4390871931","https://openalex.org/W4390873156","https://openalex.org/W4390874423","https://openalex.org/W4399404947","https://openalex.org/W4399800460","https://openalex.org/W4404624430"],"related_works":[],"abstract_inverted_index":{"Human":[0],"action":[1,21,199],"recognition":[2],"is":[3,216],"a":[4,52,77,165,194],"crucial":[5],"task":[6],"for":[7,82,205],"intelligent":[8],"robotics,":[9],"particularly":[10],"within":[11],"the":[12,23,28,35,42,62,100,109,121,136,140,159,170,175,183],"context":[13],"of":[14,34,55,102,169,178,213],"human-robot":[15,208],"collaboration":[16],"research.":[17],"In":[18],"self-supervised":[19],"skeleton-based":[20,198],"recognition,":[22,200],"mask-based":[24],"reconstruction":[25,137,160],"paradigm":[26],"learns":[27],"spatial":[29],"structure":[30],"and":[31,40,57,151,186],"motion":[32,59,68,87,97,134,145,149,153,172,179],"patterns":[33],"skeleton":[36],"by":[37],"masking":[38,80,101,117],"joints":[39,56],"reconstructing":[41],"target":[43],"from":[44],"unlabeled":[45],"data.":[46],"However,":[47],"existing":[48],"methods":[49],"focus":[50],"on":[51,95,182],"limited":[53],"set":[54],"low-order":[58,148],"patterns,":[60],"limiting":[61],"model\u2019s":[63,176],"ability":[64],"to":[65,98,123,142],"understand":[66],"complex":[67],"patterns.":[69,146,180],"To":[70],"address":[71],"this":[72],"issue,":[73],"we":[74,129],"introduce":[75],"MaskSem,":[76,191],"novel":[78,90],"semantic-guided":[79,116],"method":[81],"learning":[83],"3D":[84],"hybrid":[85,132],"high-order":[86,133,152],"representations.":[88],"This":[89,162],"framework":[91],"leverages":[92],"Grad-CAM":[93],"based":[94],"relative":[96],"guide":[99],"joints,":[103],"which":[104],"can":[105,119],"be":[106],"represented":[107],"as":[108,135,158],"most":[110],"semantically":[111],"rich":[112],"temporal":[113],"orgions.":[114],"The":[115,210],"process":[118],"encourage":[120],"model":[122,141],"explore":[124],"more":[125,166,203],"discriminative":[126],"features.":[127],"Furthermore,":[128],"propose":[130],"using":[131],"target,":[138],"enabling":[139],"learn":[143],"multi-order":[144],"Specifically,":[147],"velocity":[150],"acceleration":[154],"are":[155],"used":[156],"together":[157],"target.":[161],"approach":[163],"offers":[164],"comprehensive":[167],"description":[168],"dynamic":[171],"process,":[173],"enhancing":[174],"understanding":[177],"Experiments":[181],"NTU60,":[184],"NTU120,":[185],"PKU-MMD":[187],"datasets":[188],"show":[189],"that":[190],"combined":[192],"with":[193],"vanilla":[195],"transformer,":[196],"improves":[197],"making":[201],"it":[202],"suitable":[204],"applications":[206],"in":[207],"interaction.":[209],"source":[211],"code":[212],"our":[214],"MaskSem":[215],"available":[217],"at":[218],"https://github.com/JayEason66/MaskSem.":[219]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}
