{"id":"https://openalex.org/W4375958382","doi":"https://doi.org/10.1145/3595916.3626459","title":"Cross-Modal Retrieval for Motion and Text via DropTriple Loss","display_name":"Cross-Modal Retrieval for Motion and Text via DropTriple Loss","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4375958382","doi":"https://doi.org/10.1145/3595916.3626459"},"language":"en","primary_location":{"id":"doi:10.1145/3595916.3626459","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626459","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626459","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626459","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101500544","display_name":"Sheng Yan","orcid":"https://orcid.org/0009-0003-6622-9705"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sheng Yan","raw_affiliation_strings":["Chongqing University of Technology, CN"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Technology, CN","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101810463","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-5159-5954"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Sichuan University, CN"],"affiliations":[{"raw_affiliation_string":"Sichuan University, CN","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108059904","display_name":"Haoqiang Wang","orcid":"https://orcid.org/0009-0006-8954-5331"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqiang Wang","raw_affiliation_strings":["Chongqing University of Technology, CN"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Technology, CN","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101972075","display_name":"Xin Du","orcid":"https://orcid.org/0009-0001-3292-1467"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Du","raw_affiliation_strings":["Chongqing University of Technology, CN"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Technology, CN","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705472","display_name":"Mengyuan Liu","orcid":"https://orcid.org/0000-0002-6332-8316"},"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":"Mengyuan Liu","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, CN"],"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, CN","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100410326","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0002-7498-6541"},"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":"Hong Liu","raw_affiliation_strings":["Shenzhen Graduate School, Peking University, CN"],"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, CN","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101500544"],"corresponding_institution_ids":["https://openalex.org/I50632499"],"apc_list":null,"apc_paid":null,"fwci":1.3134,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82329296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.7865214347839355},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5517669320106506},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5298177003860474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5093225240707397},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4948508143424988},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46760669350624084},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44193899631500244},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4253774881362915},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42080971598625183},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.4175732135772705},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4006900489330292},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3482370376586914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7865214347839355},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5517669320106506},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5298177003860474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5093225240707397},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4948508143424988},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46760669350624084},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44193899631500244},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4253774881362915},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42080971598625183},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.4175732135772705},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4006900489330292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3482370376586914},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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":3,"locations":[{"id":"doi:10.1145/3595916.3626459","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626459","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626459","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.04195","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.04195","pdf_url":"https://arxiv.org/pdf/2305.04195","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2305.04195","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1145/3595916.3626459","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626459","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626459","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"},{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8283459870","display_name":null,"funder_award_id":"62203476","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4375958382.pdf","grobid_xml":"https://content.openalex.org/works/W4375958382.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1967554269","https://openalex.org/W2296073425","https://openalex.org/W2469134594","https://openalex.org/W2949924544","https://openalex.org/W3000226596","https://openalex.org/W3023742835","https://openalex.org/W3035524453","https://openalex.org/W3135367836","https://openalex.org/W3169193436","https://openalex.org/W3184735396","https://openalex.org/W3186617021","https://openalex.org/W4245551996","https://openalex.org/W4285138127","https://openalex.org/W4285531802","https://openalex.org/W4297683907","https://openalex.org/W4297981470","https://openalex.org/W4301045096","https://openalex.org/W4302774332","https://openalex.org/W4304944802","https://openalex.org/W4367663575","https://openalex.org/W4381198761","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2783354812","https://openalex.org/W4384112194","https://openalex.org/W2103009189","https://openalex.org/W4312958259","https://openalex.org/W4308259661","https://openalex.org/W4390813131","https://openalex.org/W2349383066","https://openalex.org/W4328132048","https://openalex.org/W1969901537","https://openalex.org/W2376202349"],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,27,136,141],"of":[2,132],"image-text":[3],"and":[4,14,31,93,114,119,137],"video-text":[5],"is":[6,152],"a":[7,43,73,130],"prominent":[8],"research":[9],"area":[10],"in":[11,59],"computer":[12],"vision":[13],"natural":[15],"language":[16],"processing.":[17],"However,":[18],"there":[19],"has":[20],"been":[21],"insufficient":[22],"attention":[23],"given":[24],"to":[25,66],"cross-modal":[26],"between":[28,69],"human":[29,61],"motion":[30,62,135],"text,":[32],"despite":[33],"its":[34],"wide-ranging":[35],"applicability.":[36],"To":[37],"address":[38],"this":[39,52],"gap,":[40],"we":[41,71,128],"utilize":[42],"concise":[44],"yet":[45],"effective":[46],"dual-unimodal":[47],"transformer":[48],"encoder":[49],"for":[50,102,134,139,149],"tackling":[51],"task.":[53],"Recognizing":[54],"that":[55],"overlapping":[56],"atomic":[57],"actions":[58],"different":[60],"sequences":[63],"can":[64],"lead":[65],"semantic":[67],"conflicts":[68],"samples,":[70],"explore":[72],"novel":[74],"triplet":[75,103],"loss":[76,82],"function":[77,83],"called":[78],"DropTriple":[79],"Loss.":[80],"This":[81],"discards":[84],"false":[85],"negative":[86,90,100],"samples":[87,101],"from":[88],"the":[89,117,124],"sample":[91],"set":[92],"focuses":[94],"on":[95,116,144],"mining":[96],"remaining":[97],"genuinely":[98],"hard":[99],"training,":[104],"thereby":[105],"reducing":[106],"violations":[107],"they":[108],"cause.":[109],"We":[110],"evaluate":[111],"our":[112,150],"model":[113],"approach":[115,151],"HumanML3D":[118,126],"KIT":[120],"Motion-Language":[121],"datasets.":[122],"On":[123],"latest":[125],"dataset,":[127],"achieve":[129],"recall":[131],"62.9%":[133],"71.5%":[138],"text":[140],"(both":[142],"based":[143],"R@10).":[145],"The":[146],"source":[147],"code":[148],"publicly":[153],"available":[154],"at":[155],"https://github.com/eanson023/rehamot.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2023-05-10T00:00:00"}