{"id":"https://openalex.org/W7204875952","doi":"https://doi.org/10.18653/2026.findings-emnlp.18","title":"Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum","display_name":"Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204875952","doi":"https://doi.org/10.18653/2026.findings-emnlp.18"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.18","doi":"https://doi.org/10.18653/2026.findings-emnlp.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.18","pdf_url":"https://aclanthology.org/2026.findings-emnlp.18.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.18.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134231352","display_name":"Xingjian Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Xingjian Wang","raw_affiliation_strings":["Monash University ;","Shanghai University of Electric Power"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University ;","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"Shanghai University of Electric Power","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127379356","display_name":"Shijian Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU","BD"],"is_corresponding":false,"raw_author_name":"Shijian Wang","raw_affiliation_strings":["Monash University ;","Southeast University ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University ;","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"Southeast University ;","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124366243","display_name":"Yibo Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU","BD"],"is_corresponding":false,"raw_author_name":"Yibo Wang","raw_affiliation_strings":["Monash University ;","Southeast University ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University ;","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"Southeast University ;","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120480123","display_name":"Zihao Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Yu","raw_affiliation_strings":["Shanghai University of Electric Power"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Electric Power","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132549868","display_name":"Runhao Fu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Runhao Fu","raw_affiliation_strings":["Monash University ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University ;","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132661458","display_name":"Xuelian Cheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuelian Cheng","raw_affiliation_strings":["Monash University ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University ;","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125528492","display_name":"Zongyuan Ge","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zongyuan Ge","raw_affiliation_strings":["Monash University ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University ;","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70542344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"355","last_page":"370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9984999895095825,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0003000000142492354,"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":0.00019999999494757503,"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/synthetic-data-generation","display_name":"synthetic data generation","score":0.5540000200271606},{"id":"https://openalex.org/keywords/curriculum-learning","display_name":"curriculum learning","score":0.7789999842643738},{"id":"https://openalex.org/keywords/scene-graph","display_name":"scene graph","score":0.3970000147819519},{"id":"https://openalex.org/keywords/constraint-programming","display_name":"constraint programming","score":0.7639999985694885},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.4359999895095825},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.47099998593330383},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.7350000143051147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133000135421753},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5005000233650208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4993000030517578},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47450000047683716},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3522999882698059},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34279999136924744},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.18","doi":"https://doi.org/10.18653/2026.findings-emnlp.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.18","pdf_url":"https://aclanthology.org/2026.findings-emnlp.18.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.30584","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30584","pdf_url":"https://arxiv.org/pdf/2608.30584","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.2608.30584","doi":"https://doi.org/10.48550/arxiv.2608.30584","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.30584","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.18","doi":"https://doi.org/10.18653/2026.findings-emnlp.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.18","pdf_url":"https://aclanthology.org/2026.findings-emnlp.18.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204875952.pdf","grobid_xml":"https://content.openalex.org/works/W7204875952.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4312245888","https://openalex.org/W4375928968","https://openalex.org/W4405078915","https://openalex.org/W7220665134","https://openalex.org/W4416665772","https://openalex.org/W4417077984","https://openalex.org/W4415539745","https://openalex.org/W7153350514","https://openalex.org/W4416789463","https://openalex.org/W3150459247"],"abstract_inverted_index":{"Despite":[0],"the":[1,24,185,190],"impressive":[2],"progress":[3],"of":[4],"recent":[5],"MLLMs":[6],"on":[7,19,118,143,151,189],"spatio-temporal":[8,93],"video":[9],"grounding":[10],"(STVG),":[11],"existing":[12],"evaluations":[13],"and":[14,43,72,100,116,136,172],"training":[15,170],"data":[16,88,112,171],"focus":[17],"primarily":[18],"simple":[20],"queries.They":[21],"largely":[22],"overlook":[23],"compositional":[25,152,193],"queries":[26,67],"prevalent":[27],"in":[28],"real-world":[29],"scenarios,":[30],"where":[31,68],"a":[32,58,86,92,97,106,124,155,175],"target":[33],"must":[34],"be":[35],"disambiguated":[36],"by":[37,127,163],"jointly":[38,132],"reasoning":[39],"about":[40],"its":[41],"attributes":[42],"relations":[44],"to":[45,63],"other":[46],"entities.To":[47],"bridge":[48],"this":[49,80,119],"gap,":[50],"we":[51,84,121],"propose":[52,173],"Compositional":[53],"Spatio-Temporal":[54],"Video":[55],"Grounding":[56],"(COMPSTVG),":[57],"task":[59,81],"that":[60,90,131,146,159,180],"requires":[61],"models":[62,142,148],"process":[64],"complex":[65],"textual":[66],"every":[69],"intertwined":[70],"attribute":[71],"relational":[73],"cue":[74],"is":[75,160],"essential":[76],"for":[77,113],"disambiguation.To":[78],"facilitate":[79],"at":[82],"scale,":[83],"build":[85],"synthetic":[87,169],"engine":[89],"leverages":[91],"scene":[94],"graph":[95],"as":[96,105],"difficulty":[98,129],"measure":[99],"casts":[101],"difficulty-controlled":[102],"query":[103],"synthesis":[104],"constraint":[107],"programming":[108],"problem,":[109],"producing":[110],"difficulty-graded":[111],"both":[114],"evaluation":[115],"training.Built":[117],"engine,":[120],"introduce":[122],"STVG-COMPBENCH,":[123],"benchmark":[125],"stratified":[126],"explicit":[128],"levels":[130],"capture":[133],"temporal":[134],"complexity":[135],"spatial":[137],"interference.Evaluating":[138],"11":[139],"representative":[140],"STVG":[141],"STVG-COMPBENCH":[144],"reveals":[145],"current":[147],"perform":[149],"poorly":[150],"queries,":[153],"exhibiting":[154],"sharp":[156],"performance":[157],"drop":[158],"typically":[161],"obscured":[162],"overall":[164],"dataset-level":[165],"averages.We":[166],"further":[167],"construct":[168],"CURRSTVG,":[174],"curriculum":[176],"reinforcement":[177],"learning":[178],"framework":[179],"delivers":[181],"consistent":[182],"gains,":[183],"with":[184],"largest":[186],"improvements":[187],"observed":[188],"most":[191],"challenging":[192],"queries.":[194]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-09-02T00:00:00"}