{"id":"https://openalex.org/W4415539168","doi":"https://doi.org/10.1145/3746027.3754560","title":"Towards Fine-Grained Human Motion Video Captioning","display_name":"Towards Fine-Grained Human Motion Video Captioning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539168","doi":"https://doi.org/10.1145/3746027.3754560"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754560","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754560","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754560","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084103247","display_name":"Guorui Song","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guorui Song","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-5803-5924","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014128546","display_name":"Guocun Wang","orcid":"https://orcid.org/0009-0000-1815-2342"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guocun Wang","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-1815-2342","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhe Huang","orcid":"https://orcid.org/0009-0007-4722-8749"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Huang","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0007-4722-8749","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Lin","orcid":"https://orcid.org/0009-0006-7549-6874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Lin","raw_affiliation_strings":["ByteDance, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0006-7549-6874","affiliations":[{"raw_affiliation_string":"ByteDance, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044236581","display_name":"Xuefei Zhe","orcid":"https://orcid.org/0000-0002-5005-7166"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xuefei Zhe","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-5005-7166","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jian Li","orcid":"https://orcid.org/0009-0007-0466-5930"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Li","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0007-0466-5930","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028229824","display_name":"Haoqian Wang","orcid":"https://orcid.org/0000-0003-2792-8469"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqian Wang","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2792-8469","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32848445,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"846","last_page":"855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9995999932289124,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9972000122070312,"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/closed-captioning","display_name":"Closed captioning","score":0.7893000245094299},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6917999982833862},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6412000060081482},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5123000144958496},{"id":"https://openalex.org/keywords/human-motion","display_name":"Human motion","score":0.4641000032424927},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43860000371932983},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.3986000120639801},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817300021648407},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7893000245094299},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6917999982833862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6549999713897705},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6412000060081482},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.513700008392334},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.4641000032424927},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3598000109195709},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3513999879360199},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33149999380111694},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754560","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754560","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/dd5fafcb-0252-4fc0-b5c0-369b3cbe8bb2","is_oa":true,"landing_page_url":"https://hdl.handle.net/2031/dd5fafcb-0252-4fc0-b5c0-369b3cbe8bb2","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Song, G, Wang, G, Huang, Z, Lin, J, Zhe, X, Li, J & Wang, H 2025, Towards Fine-Grained Human Motion Video Captioning. in MM '25 - Proceedings of the 33rd ACM International Conference on Multimedia. MM - Proceedings of the ACM International Conference on Multimedia, Association for Computing Machinery, pp. 846-855, 33rd ACM International Conference on Multimedia (MM '25), Dublin, Ireland, 27/10/25. https://doi.org/10.1145/3746027.3754560","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754560","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754560","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2681765956","display_name":null,"funder_award_id":"No. 2022YFB36066","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2474702929","https://openalex.org/W3166396011","https://openalex.org/W4312635677","https://openalex.org/W4312920950","https://openalex.org/W4379918953","https://openalex.org/W4380137126","https://openalex.org/W4385489997","https://openalex.org/W4386185600","https://openalex.org/W4386555477","https://openalex.org/W4387436689","https://openalex.org/W4387947626","https://openalex.org/W4389216607","https://openalex.org/W4389218156","https://openalex.org/W4389713089","https://openalex.org/W4390190334","https://openalex.org/W4390873312","https://openalex.org/W4390874409","https://openalex.org/W4400601342","https://openalex.org/W4401024099","https://openalex.org/W4402704633","https://openalex.org/W4402753774","https://openalex.org/W4402754023","https://openalex.org/W4403370767","https://openalex.org/W4403754271","https://openalex.org/W4403853618","https://openalex.org/W4403884689","https://openalex.org/W4404988633","https://openalex.org/W4407128582","https://openalex.org/W4407384889","https://openalex.org/W4413147366","https://openalex.org/W4415334628","https://openalex.org/W6948200582","https://openalex.org/W6966513288","https://openalex.org/W6967076925"],"related_works":[],"abstract_inverted_index":{"Generating":[0],"accurate":[1],"descriptions":[2],"of":[3],"human":[4,63,69,107,133],"actions":[5],"in":[6,26,83,90,129],"videos":[7],"remains":[8],"a":[9,42,112,140],"challenging":[10],"task":[11],"for":[12,115,143],"video":[13,118,145],"captioning":[14],"models.":[15],"Existing":[16],"approaches":[17],"often":[18],"struggle":[19],"to":[20,66],"capture":[21],"fine-grained":[22],"motion":[23,59],"details,":[24],"resulting":[25],"vague":[27],"or":[28],"semantically":[29],"inconsistent":[30],"captions.":[31,86],"In":[32],"this":[33,91],"work,":[34],"we":[35,93],"introduce":[36],"the":[37,84,95],"Motion-Augmented":[38],"Caption":[39],"Model":[40],"(M-ACM),":[41],"novel":[43],"generative":[44],"framework":[45],"that":[46,123],"enhances":[47],"caption":[48],"quality":[49],"by":[50],"incorporating":[51],"motion-aware":[52],"decoding.":[53],"At":[54],"its":[55],"core,":[56],"M-ACM":[57,124],"leverages":[58],"representations":[60],"derived":[61],"from":[62],"mesh":[64],"recovery":[65],"explicitly":[67],"highlight":[68],"body":[70],"dynamics,":[71],"thereby":[72],"reducing":[73],"hallucinations":[74],"and":[75,80,135],"improving":[76],"both":[77],"semantic":[78],"fidelity":[79],"spatial":[81],"alignment":[82],"generated":[85],"To":[87],"support":[88],"research":[89],"area,":[92],"present":[94],"Human":[96],"Motion":[97],"Insight":[98],"(HMI)":[99],"Dataset,":[100],"comprising":[101],"115K":[102],"video-description":[103],"pairs":[104],"focused":[105],"on":[106],"movement,":[108],"along":[109],"with":[110],"HMI-Bench,":[111],"dedicated":[113],"benchmark":[114],"evaluating":[116],"motion-focused":[117],"captioning.":[119,146],"Experimental":[120],"results":[121],"demonstrate":[122],"significantly":[125],"outperforms":[126],"previous":[127],"methods":[128],"accurately":[130],"describing":[131],"complex":[132],"motions":[134],"subtle":[136],"temporal":[137],"variations,":[138],"setting":[139],"new":[141],"standard":[142],"motion-centric":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}