{"id":"https://openalex.org/W4296339243","doi":"https://doi.org/10.1109/tmm.2022.3207581","title":"Weakly-Supervised Video Object Grounding via Learning Uni-Modal Associations","display_name":"Weakly-Supervised Video Object Grounding via Learning Uni-Modal Associations","publication_year":2022,"publication_date":"2022-09-19","ids":{"openalex":"https://openalex.org/W4296339243","doi":"https://doi.org/10.1109/tmm.2022.3207581"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3207581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3207581","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5115695506","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-5750-6980"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Wang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014526931","display_name":"Junyu Gao","orcid":"https://orcid.org/0000-0002-8105-5497"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Gao","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","PengCheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"PengCheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5115695506"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210100255","https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.3057,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54832618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"25","issue":null,"first_page":"6329","last_page":"6340"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9966999888420105,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8351090550422668},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.700587809085846},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6409082412719727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.627422571182251},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6163120269775391},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5716477632522583},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.569499135017395},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5592905282974243},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5193154215812683},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.517778754234314},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5137901902198792},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48412832617759705},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4570792019367218},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38184675574302673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8351090550422668},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.700587809085846},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6409082412719727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.627422571182251},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6163120269775391},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5716477632522583},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.569499135017395},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5592905282974243},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5193154215812683},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.517778754234314},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5137901902198792},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48412832617759705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4570792019367218},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38184675574302673},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3207581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3207581","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1100260481","display_name":null,"funder_award_id":"62072455","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1498893086","display_name":null,"funder_award_id":"62036012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2037785589","display_name":null,"funder_award_id":"U21B2044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2407878474","display_name":null,"funder_award_id":"62072286","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2908564948","display_name":null,"funder_award_id":"62002355","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4100755579","display_name":null,"funder_award_id":"L201001","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G4790433124","display_name":null,"funder_award_id":"62102415","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6431871145","display_name":null,"funder_award_id":"61721004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8434150956","display_name":null,"funder_award_id":"61832002","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"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W805710393","https://openalex.org/W1905882502","https://openalex.org/W2247513039","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2520141964","https://openalex.org/W2568262903","https://openalex.org/W2588999492","https://openalex.org/W2606473278","https://openalex.org/W2620365397","https://openalex.org/W2622044949","https://openalex.org/W2798708692","https://openalex.org/W2798990097","https://openalex.org/W2803088946","https://openalex.org/W2896457183","https://openalex.org/W2901412525","https://openalex.org/W2946086442","https://openalex.org/W2962811161","https://openalex.org/W2963042258","https://openalex.org/W2963445828","https://openalex.org/W2963916161","https://openalex.org/W2968101724","https://openalex.org/W2981663434","https://openalex.org/W2982651953","https://openalex.org/W2989176720","https://openalex.org/W2999541181","https://openalex.org/W3034298080","https://openalex.org/W3034636873","https://openalex.org/W3035049560","https://openalex.org/W3035590142","https://openalex.org/W3092198590","https://openalex.org/W3092803144","https://openalex.org/W3093034080","https://openalex.org/W3098232790","https://openalex.org/W3103542727","https://openalex.org/W3117585461","https://openalex.org/W3117854388","https://openalex.org/W3118580076","https://openalex.org/W3126391825","https://openalex.org/W3160989675","https://openalex.org/W3178418424","https://openalex.org/W3179041377","https://openalex.org/W3205059508","https://openalex.org/W3205945847","https://openalex.org/W3215892227","https://openalex.org/W6620707391","https://openalex.org/W6638145986","https://openalex.org/W6751762309","https://openalex.org/W6755207826","https://openalex.org/W6786030337","https://openalex.org/W6795389030"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Grounding":[0],"objects":[1],"described":[2],"in":[3,9,17,54,59,139,148,158],"natural":[4],"language":[5],"to":[6,47,99,112,154],"visual":[7,60,108,146,161,174],"regions":[8,58],"the":[10,26,49,63,74,81,115,136,156,173,186,200,204],"video":[11,28,121],"is":[12,46,167],"a":[13,164],"crucial":[14],"capability":[15],"needed":[16],"vision-and-language":[18],"fields.":[19],"In":[20],"this":[21,44,95],"paper,":[22],"we":[23,66,97,126,144],"deal":[24],"with":[25,185],"weakly-supervised":[27],"object":[29,122,138],"grounding":[30],"(WSVOG)":[31],"task,":[32,180],"where":[33],"only":[34,171],"video-sentence":[35],"pairs":[36],"are":[37],"provided":[38],"for":[39,77,119,178],"learning.":[40],"The":[41],"essence":[42],"of":[43,135,206],"task":[45],"learn":[48,101,127],"cross-modal":[50,78,165],"associations":[51,103],"between":[52],"words":[53],"textual":[55,106,128,176],"modality":[56],"and":[57,83,107,142,175,199],"modality.":[61],"Despite":[62],"recent":[64],"progress,":[65],"find":[67],"that":[68],"most":[69],"existing":[70],"methods":[71],"focus":[72],"on":[73,104,195],"association":[75,188],"learning":[76,189],"samples,":[79],"while":[80],"rich":[82,132],"complementary":[84],"information":[85,118,134],"within":[86],"uni-modal":[87,102,117,187],"samples":[88],"has":[89],"not":[90,170],"been":[91],"fully":[92,113],"exploited.":[93],"To":[94],"end,":[96],"propose":[98],"explicitly":[100],"both":[105],"sides,":[109],"so":[110,152],"as":[111,153],"exploit":[114],"useful":[116],"accurate":[120],"grounding.":[123],"Specifically,":[124],"(1)":[125],"prototypes":[129,147],"by":[130],"considering":[131],"contextual":[133],"same":[137],"different":[140],"sentences,":[141],"(2)":[143],"estimate":[145],"an":[149],"adaptive":[150],"manner":[151],"overcome":[155],"uncertainties":[157],"selecting":[159],"object-relevant":[160],"regions.":[162],"Besides,":[163],"correspondence":[166],"learned":[168],"which":[169],"bridges":[172],"modalities":[177],"WSVOG":[179],"but":[181],"also":[182],"tightly":[183],"cooperates":[184],"process.":[190],"We":[191],"conduct":[192],"extensive":[193],"experiments":[194],"three":[196],"popular":[197],"datasets,":[198],"favorable":[201],"results":[202],"demonstrate":[203],"effectiveness":[205],"our":[207],"method.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}