{"id":"https://openalex.org/W4395470960","doi":"https://doi.org/10.1109/tpami.2024.3393452","title":"Enhancing Video-Language Representations With Structural Spatio-Temporal Alignment","display_name":"Enhancing Video-Language Representations With Structural Spatio-Temporal Alignment","publication_year":2024,"publication_date":"2024-04-25","ids":{"openalex":"https://openalex.org/W4395470960","doi":"https://doi.org/10.1109/tpami.2024.3393452","pmid":"https://pubmed.ncbi.nlm.nih.gov/38662568"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3393452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3393452","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.19255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055815455","display_name":"Hao Fei","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Hao Fei","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089517967","display_name":"Shengqiong Wu","orcid":"https://orcid.org/0000-0001-6192-1194"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shengqiong Wu","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004953265","display_name":"Meishan Zhang","orcid":"https://orcid.org/0000-0001-6335-1340"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meishan Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology (Shenzhen), China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology (Shenzhen), China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381753","display_name":"Shuicheng Yan","orcid":"https://orcid.org/0000-0001-8906-3777"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["Skywork AI, Kunlun 2050 Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Skywork AI, Kunlun 2050 Research, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055815455"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":12.6739,"has_fulltext":true,"cited_by_count":52,"citation_normalized_percentile":{"value":0.99259078,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"46","issue":"12","first_page":"7701","last_page":"7719"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10812","display_name":"Human Pose and Action Recognition","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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9970999956130981,"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":0.7110775709152222},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6650724411010742},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5300295948982239},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42755356431007385},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38700979948043823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110775709152222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6650724411010742},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5300295948982239},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42755356431007385},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38700979948043823}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2024.3393452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3393452","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38662568","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38662568","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 pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2406.19255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.19255","pdf_url":"https://arxiv.org/pdf/2406.19255","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.19255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.19255","pdf_url":"https://arxiv.org/pdf/2406.19255","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1883487206","display_name":null,"funder_award_id":"62336008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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/G6092351401","display_name":null,"funder_award_id":"CCF-Baidu Open Fund","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4395470960.pdf"},"referenced_works_count":95,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2077069816","https://openalex.org/W2131774270","https://openalex.org/W2250378130","https://openalex.org/W2342662179","https://openalex.org/W2425121537","https://openalex.org/W2512435841","https://openalex.org/W2550936021","https://openalex.org/W2600702321","https://openalex.org/W2606982687","https://openalex.org/W2619947201","https://openalex.org/W2625366777","https://openalex.org/W2745461083","https://openalex.org/W2765716052","https://openalex.org/W2952132648","https://openalex.org/W2963017553","https://openalex.org/W2963101956","https://openalex.org/W2963916161","https://openalex.org/W2981851019","https://openalex.org/W3006320872","https://openalex.org/W3034188691","https://openalex.org/W3034679267","https://openalex.org/W3035313462","https://openalex.org/W3035356601","https://openalex.org/W3035524453","https://openalex.org/W3035640828","https://openalex.org/W3105232955","https://openalex.org/W3113177135","https://openalex.org/W3126721948","https://openalex.org/W3132753749","https://openalex.org/W3153005511","https://openalex.org/W3161945002","https://openalex.org/W3168640669","https://openalex.org/W3197804339","https://openalex.org/W3203592524","https://openalex.org/W3203711169","https://openalex.org/W3204588463","https://openalex.org/W3206384369","https://openalex.org/W3207212285","https://openalex.org/W3217059257","https://openalex.org/W3217102353","https://openalex.org/W4214612132","https://openalex.org/W4226289673","https://openalex.org/W4285606530","https://openalex.org/W4309396261","https://openalex.org/W4312463400","https://openalex.org/W4312480274","https://openalex.org/W4312560592","https://openalex.org/W4312561757","https://openalex.org/W4313186260","https://openalex.org/W4318718936","https://openalex.org/W4323572061","https://openalex.org/W4360836968","https://openalex.org/W4366330503","https://openalex.org/W4377865169","https://openalex.org/W4385245566","https://openalex.org/W4385574085","https://openalex.org/W4386071707","https://openalex.org/W4386076615","https://openalex.org/W4386076661","https://openalex.org/W4387385612","https://openalex.org/W4387389147","https://openalex.org/W4389519526","https://openalex.org/W4389519587","https://openalex.org/W4390871765","https://openalex.org/W4390872366","https://openalex.org/W4402671548","https://openalex.org/W4404784276","https://openalex.org/W6620707391","https://openalex.org/W6638523607","https://openalex.org/W6684090549","https://openalex.org/W6745537798","https://openalex.org/W6751751081","https://openalex.org/W6765163099","https://openalex.org/W6773737242","https://openalex.org/W6784333009","https://openalex.org/W6787995345","https://openalex.org/W6791353385","https://openalex.org/W6795711426","https://openalex.org/W6796761347","https://openalex.org/W6801013943","https://openalex.org/W6805349323","https://openalex.org/W6810265253","https://openalex.org/W6810334672","https://openalex.org/W6843018836","https://openalex.org/W6846305988","https://openalex.org/W6846726380","https://openalex.org/W6849177959","https://openalex.org/W6850503672","https://openalex.org/W6850936240","https://openalex.org/W6851592950","https://openalex.org/W6853314951","https://openalex.org/W6856659047","https://openalex.org/W6858543224","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"While":[0],"pre-training":[1],"large-scale":[2],"video-language":[3,13,34,170],"models":[4],"(VLMs)":[5],"has":[6],"shown":[7],"remarkable":[8],"potential":[9],"for":[10,80,118,194],"various":[11],"downstream":[12,208],"tasks,":[14],"existing":[15,191,230],"VLMs":[16,42,193,233],"can":[17,187],"still":[18],"suffer":[19],"from":[20,200],"certain":[21],"commonly":[22],"seen":[23],"limitations,":[24],"e.g.,":[25],"coarse-grained":[26],"cross-modal":[27],"aligning,":[28],"under-modeling":[29],"of":[30,54,70,137,154],"temporal":[31,121,145,165],"dynamics,":[32],"detached":[33],"view.":[35],"In":[36],"this":[37],"work,":[38],"we":[39,56,158],"target":[40],"enhancing":[41,168],"with":[43,63,97,112],"a":[44,76,98,113,183],"fine-grained":[45,64,151],"structural":[46,152],"spatio-temporal":[47],"alignment":[48,162,166],"learning":[49],"method":[50,181],"(namely":[51],"Finsta).":[52],"First":[53],"all,":[55],"represent":[57],"the":[58,91,102,108,135,138,150,169,174,229,237,246],"input":[59],"texts":[60],"and":[61,107,120,144,156,163,176,222,235,248],"videos":[62],"scene":[65],"graph":[66,99,116,128],"(SG)":[67],"structures,":[68],"both":[69,173,220,245],"which":[71,186],"are":[72,110],"further":[73,131,195],"unified":[74],"into":[75,190],"holistic":[77],"SG":[78,93,105,205],"(HSG)":[79],"bridging":[81],"two":[82],"modalities.":[83],"Then,":[84],"an":[85],"SG-based":[86],"framework":[87],"is":[88,95,130],"built,":[89],"where":[90],"textual":[92],"(TSG)":[94],"encoded":[96],"Transformer,":[100],"while":[101],"video":[103,224],"dynamic":[104],"(DSG)":[106],"HSG":[109],"modeled":[111],"novel":[114],"recurrent":[115],"Transformer":[117,129],"spatial":[119,143,161],"feature":[122],"propagation.":[123],"A":[124],"spatial-temporal":[125],"Gaussian":[126],"differential":[127],"devised":[132],"to":[133],"strengthen":[134],"sense":[136],"changes":[139],"in":[140,172,207,219,244],"objects":[141],"across":[142],"dimensions.":[146],"Next,":[147],"based":[148],"on":[149,204],"features":[153],"TSG":[155],"DSG,":[157],"perform":[159],"object-centered":[160],"predicate-centered":[164],"respectively,":[167],"grounding":[171],"spatiality":[175],"temporality.":[177],"We":[178],"design":[179],"our":[180],"as":[182],"plug&play":[184],"system,":[185],"be":[188],"integrated":[189],"well-trained":[192],"representation":[196],"augmentation,":[197],"without":[198],"training":[199],"scratch":[201],"or":[202],"relying":[203],"annotations":[206],"applications.":[209],"On":[210],"6":[211],"representative":[212],"VL":[213],"modeling":[214],"tasks":[215],"over":[216],"12":[217],"datasets":[218],"standard":[221],"long-form":[223],"scenarios,":[225],"Finsta":[226],"consistently":[227],"improves":[228],"13":[231],"strong-performing":[232],"persistently,":[234],"refreshes":[236],"current":[238],"state-of-the-art":[239],"end":[240],"task":[241],"performance":[242],"significantly":[243],"fine-tuning":[247],"zero-shot":[249],"settings.":[250]},"counts_by_year":[{"year":2025,"cited_by_count":41},{"year":2024,"cited_by_count":11}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}