{"id":"https://openalex.org/W4415748001","doi":"https://doi.org/10.1109/tip.2025.3624601","title":"Text-Controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion","display_name":"Text-Controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415748001","doi":"https://doi.org/10.1109/tip.2025.3624601","pmid":"https://pubmed.ncbi.nlm.nih.gov/41171667"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3624601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3624601","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5115500981","display_name":"Xinghan Wang","orcid":"https://orcid.org/0009-0007-2530-2725"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghan Wang","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2530-2725","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zixi Kang","orcid":"https://orcid.org/0009-0005-8295-6018"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixi Kang","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-8295-6018","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028877572","display_name":"Yadong Mu","orcid":"https://orcid.org/0000-0001-7815-3750"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Mu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7815-3750","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":6.2231,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.96860766,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"34","issue":null,"first_page":"7079","last_page":"7092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.7444000244140625,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.7444000244140625,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.18700000643730164,"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":0.010400000028312206,"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/motion","display_name":"Motion (physics)","score":0.6844000220298767},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.590399980545044},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5651000142097473},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5478000044822693},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.5194000005722046},{"id":"https://openalex.org/keywords/human-motion","display_name":"Human motion","score":0.48969998955726624},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4596000015735626},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3894999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562000155448914},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6844000220298767},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.590399980545044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.58160001039505},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5651000142097473},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.48969998955726624},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4068000018596649},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38679999113082886},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.34459999203681946},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.288100004196167},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.250900000333786}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3624601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3624601","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41171667","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41171667","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W1487977235","https://openalex.org/W1927052826","https://openalex.org/W2101032778","https://openalex.org/W2474702929","https://openalex.org/W2593722617","https://openalex.org/W2743372195","https://openalex.org/W2884293275","https://openalex.org/W2948058585","https://openalex.org/W2948229620","https://openalex.org/W2963076818","https://openalex.org/W2964134613","https://openalex.org/W2971856312","https://openalex.org/W2982625143","https://openalex.org/W2996249958","https://openalex.org/W3035225512","https://openalex.org/W3035339529","https://openalex.org/W3035590142","https://openalex.org/W3040942941","https://openalex.org/W3125955391","https://openalex.org/W3128140926","https://openalex.org/W3144253442","https://openalex.org/W3176252609","https://openalex.org/W3176882544","https://openalex.org/W3194512065","https://openalex.org/W3196073975","https://openalex.org/W3203634062","https://openalex.org/W3203711169","https://openalex.org/W3215030504","https://openalex.org/W4221166385","https://openalex.org/W4226027695","https://openalex.org/W4288079574","https://openalex.org/W4297981470","https://openalex.org/W4297989763","https://openalex.org/W4304091719","https://openalex.org/W4312508181","https://openalex.org/W4312635677","https://openalex.org/W4312661503","https://openalex.org/W4312757522","https://openalex.org/W4312880366","https://openalex.org/W4312920950","https://openalex.org/W4312936899","https://openalex.org/W4313145975","https://openalex.org/W4313417834","https://openalex.org/W4378501009","https://openalex.org/W4382240036","https://openalex.org/W4382457661","https://openalex.org/W4386065848","https://openalex.org/W4386075888","https://openalex.org/W4386076069","https://openalex.org/W4386076288","https://openalex.org/W4386076315","https://openalex.org/W4386076374","https://openalex.org/W4386076405","https://openalex.org/W4386275562","https://openalex.org/W4387963302","https://openalex.org/W4387969168","https://openalex.org/W4388186306","https://openalex.org/W4389169911","https://openalex.org/W4390871790","https://openalex.org/W4390872069","https://openalex.org/W4390872595","https://openalex.org/W4390873341","https://openalex.org/W4390873423","https://openalex.org/W4390873550","https://openalex.org/W4390873580","https://openalex.org/W4390874125","https://openalex.org/W4390874197","https://openalex.org/W4390874263","https://openalex.org/W4390874409","https://openalex.org/W4390874627","https://openalex.org/W4391305822","https://openalex.org/W4393148441","https://openalex.org/W4393149270","https://openalex.org/W4393153655","https://openalex.org/W4393155961","https://openalex.org/W4393158781","https://openalex.org/W4393170627","https://openalex.org/W4393196385","https://openalex.org/W4399039553","https://openalex.org/W4401857119","https://openalex.org/W4402943982","https://openalex.org/W4402951640","https://openalex.org/W4402952320","https://openalex.org/W4403067091","https://openalex.org/W4403152483","https://openalex.org/W4403842425","https://openalex.org/W4404214611","https://openalex.org/W4414243662"],"related_works":[],"abstract_inverted_index":{"Human":[0],"motion":[1,17,29,46,62],"understanding":[2],"is":[3,68,131,148],"a":[4,106,132],"fundamental":[5],"task":[6,42],"with":[7,121,178],"diverse":[8],"practical":[9],"applications,":[10],"facilitated":[11],"by":[12,100],"the":[13,40,71,92,129,155,165,186],"availability":[14],"of":[15,43,128,157,174,188],"large-scale":[16],"capture":[18],"datasets.":[19],"Recent":[20],"studies":[21],"focus":[22],"on":[23,79,143,190],"text-motion":[24,167],"tasks,":[25],"such":[26],"as":[27],"text-based":[28,44],"generation,":[30],"editing":[31],"and":[32,117],"question":[33],"answering.":[34],"In":[35],"this":[36],"study,":[37],"we":[38,162],"introduce":[39,163],"novel":[41],"human":[45,175],"grounding":[47],"(THMG),":[48],"aimed":[49],"at":[50],"precisely":[51],"localizing":[52],"temporal":[53,66,81,111,140,181],"segments":[54],"corresponding":[55,180],"to":[56,91,151],"given":[57],"textual":[58,172],"descriptions":[59,173],"within":[60],"untrimmed":[61,88],"sequences.":[63],"Capturing":[64],"global":[65,80,112,139],"information":[67,141],"crucial":[69],"for":[70],"THMG":[72],"task.":[73],"However,":[74],"Transformer-based":[75],"models":[76],"that":[77,109,169],"rely":[78],"self-attention":[82],"face":[83],"challenges":[84,99],"when":[85],"handling":[86],"long":[87],"sequences":[89],"due":[90],"quadratic":[93],"computational":[94],"cost.":[95,125],"We":[96],"address":[97],"these":[98],"proposing":[101],"Text-controlled":[102],"Motion":[103],"Mamba":[104],"(TM-Mamba),":[105],"unified":[107],"model":[108,130,147],"integrates":[110],"context,":[113],"language":[114],"query":[115],"control,":[116],"spatial":[118],"graph":[119],"topology":[120],"only":[122],"linear":[123],"memory":[124],"The":[126,146],"core":[127],"text-controlled":[133],"selection":[134],"mechanism":[135],"which":[136],"dynamically":[137],"incorporates":[138],"based":[142],"text":[144],"query.":[145],"further":[149],"enhanced":[150],"be":[152],"topology-aware":[153],"through":[154],"integration":[156],"relational":[158],"embeddings.":[159],"For":[160],"evaluation,":[161],"BABEL-Grounding,":[164],"first":[166],"dataset":[168],"provides":[170],"detailed":[171],"actions":[176],"along":[177],"their":[179],"segments.":[182],"Extensive":[183],"evaluations":[184],"demonstrate":[185],"effectiveness":[187],"TM-Mamba":[189],"BABEL-Grounding.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-07T23:20:04.922697","created_date":"2025-10-31T00:00:00"}
