{"id":"https://openalex.org/W3014018982","doi":"https://doi.org/10.1109/cvpr42600.2020.01043","title":"Video Object Grounding Using Semantic Roles in Language Description","display_name":"Video Object Grounding Using Semantic Roles in Language Description","publication_year":2020,"publication_date":"2020-06-01","ids":{"openalex":"https://openalex.org/W3014018982","doi":"https://doi.org/10.1109/cvpr42600.2020.01043","mag":"3014018982"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr42600.2020.01043","doi":"https://doi.org/10.1109/cvpr42600.2020.01043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr42600.2020.01043","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.10606","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003277454","display_name":"Arka Sadhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arka Sadhu","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636631","display_name":"Kan Chen","orcid":"https://orcid.org/0000-0003-1415-5495","observed_orcids":["https://orcid.org/0000-0003-1415-5495"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kan Chen","raw_affiliation_strings":["Facebook Inc","University  of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080385311","display_name":"Ram Nevatia","orcid":"https://orcid.org/0009-0003-8079-4209","observed_orcids":["https://orcid.org/0009-0003-8079-4209"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210111288","display_name":"Meta (United Kingdom)","ror":"https://ror.org/020ye1821","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ram Nevatia","raw_affiliation_strings":["University of Southern California","Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3675,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.91955897,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10414","last_page":"10424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":9.999999747378752e-05,"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/thematic-roles","display_name":"thematic roles","score":0.9559999704360962},{"id":"https://openalex.org/keywords/object-relations","display_name":"object relations","score":0.9480000138282776},{"id":"https://openalex.org/keywords/self-attention","display_name":"self-attention","score":0.9089999794960022},{"id":"https://openalex.org/keywords/relative-position-encoding","display_name":"relative position encoding","score":0.996999979019165},{"id":"https://openalex.org/keywords/multimodal-grounding","display_name":"multimodal grounding","score":0.5870000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534745931625366},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7510282397270203},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.7069811224937439},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6996192932128906},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.6498748660087585},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6355767846107483},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.619191586971283},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5837770104408264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5598007440567017},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.44639715552330017},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4424275755882263},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4417974352836609},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.4235376715660095},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32309389114379883},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22719964385032654},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2005676031112671},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09862712025642395},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06528037786483765},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06271421909332275},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cvpr42600.2020.01043","doi":"https://doi.org/10.1109/cvpr42600.2020.01043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr42600.2020.01043","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.10606","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.10606","pdf_url":"https://arxiv.org/pdf/2003.10606","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":"mag:3014018982","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.10606.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2003.10606","doi":"https://doi.org/10.48550/arxiv.2003.10606","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.10606","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.10606","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.10606","pdf_url":"https://arxiv.org/pdf/2003.10606","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1717380892","display_name":null,"funder_award_id":"N00014-18","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3014018982.pdf","grobid_xml":"https://content.openalex.org/works/W3014018982.grobid-xml"},"referenced_works_count":83,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1578985305","https://openalex.org/W1773149199","https://openalex.org/W1905882502","https://openalex.org/W1927052826","https://openalex.org/W1953661235","https://openalex.org/W2017875634","https://openalex.org/W2064675550","https://openalex.org/W2103076621","https://openalex.org/W2123442489","https://openalex.org/W2131774270","https://openalex.org/W2158847908","https://openalex.org/W2194775991","https://openalex.org/W2214124602","https://openalex.org/W2247513039","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2337252826","https://openalex.org/W2423576022","https://openalex.org/W2489434015","https://openalex.org/W2507009361","https://openalex.org/W2524365899","https://openalex.org/W2549139847","https://openalex.org/W2560747010","https://openalex.org/W2561296180","https://openalex.org/W2583360688","https://openalex.org/W2610163825","https://openalex.org/W2619947201","https://openalex.org/W2624614404","https://openalex.org/W2626778328","https://openalex.org/W2629538667","https://openalex.org/W2745166287","https://openalex.org/W2745461083","https://openalex.org/W2765137706","https://openalex.org/W2769277182","https://openalex.org/W2770368992","https://openalex.org/W2770717329","https://openalex.org/W2789158025","https://openalex.org/W2789541106","https://openalex.org/W2793407941","https://openalex.org/W2793978524","https://openalex.org/W2795151422","https://openalex.org/W2795378892","https://openalex.org/W2797678702","https://openalex.org/W2798638375","https://openalex.org/W2798708692","https://openalex.org/W2803088946","https://openalex.org/W2883275382","https://openalex.org/W2884969173","https://openalex.org/W2886424491","https://openalex.org/W2886970679","https://openalex.org/W2888814092","https://openalex.org/W2889780234","https://openalex.org/W2896457183","https://openalex.org/W2899771611","https://openalex.org/W2903073381","https://openalex.org/W2924996095","https://openalex.org/W2933138175","https://openalex.org/W2936215830","https://openalex.org/W2936649169","https://openalex.org/W2951702519","https://openalex.org/W2952342379","https://openalex.org/W2952686080","https://openalex.org/W2952997040","https://openalex.org/W2962677524","https://openalex.org/W2962749469","https://openalex.org/W2962949233","https://openalex.org/W2963097937","https://openalex.org/W2963109634","https://openalex.org/W2963341956","https://openalex.org/W2963521717","https://openalex.org/W2963541336","https://openalex.org/W2963563276","https://openalex.org/W2963649796","https://openalex.org/W2964225075","https://openalex.org/W2964242760","https://openalex.org/W2964343989","https://openalex.org/W2964345792","https://openalex.org/W2968101724","https://openalex.org/W2969318875","https://openalex.org/W3034636873","https://openalex.org/W6781044366","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4304080724","https://openalex.org/W4296339243","https://openalex.org/W3092803144","https://openalex.org/W3205059508","https://openalex.org/W4386281066","https://openalex.org/W4400871519","https://openalex.org/W3109142545","https://openalex.org/W4402125038","https://openalex.org/W3215892227","https://openalex.org/W3035049560"],"abstract_inverted_index":{"We":[0],"explore":[1,32],"the":[2,33,45,104],"task":[3],"of":[4,47,106],"Video":[5],"Object":[6],"Grounding":[7],"(VOG),":[8],"which":[9],"grounds":[10],"objects":[11],"in":[12,16,50,110],"videos":[13],"referred":[14],"to":[15,27,31,58,78],"natural":[17],"language":[18],"descriptions.":[19],"Previous":[20],"methods":[21,77],"apply":[22],"image":[23],"grounding":[24,82,98],"based":[25,93],"algorithms":[26],"address":[28],"VOG,":[29,111],"fail":[30],"object":[34,48,61,108],"relation":[35],"information":[36],"and":[37,52,85,97,112],"suffer":[38],"from":[39],"limited":[40],"generalization.":[41],"Here,":[42],"we":[43,72],"investigate":[44],"role":[46],"relations":[49,62,109],"VOG":[51],"propose":[53,73],"a":[54,87,119],"novel":[55,74],"framework":[56],"VOGNet":[57,114],"encode":[59],"multi-modal":[60],"via":[63],"self-attention":[64],"with":[65],"relative":[66],"position":[67],"encoding.":[68],"To":[69],"evaluate":[70],"VOGNet,":[71],"contrasting":[75],"sampling":[76],"generate":[79],"more":[80],"challenging":[81],"input":[83],"samples,":[84],"construct":[86],"new":[88],"dataset":[89],"called":[90],"ActivityNet-SRL":[91],"(ASRL)":[92],"on":[94,101],"existing":[95],"caption":[96],"datasets.":[99],"Experiments":[100],"ASRL":[102],"validate":[103],"need":[105],"encoding":[107],"our":[113],"outperforms":[115],"competitive":[116],"baselines":[117],"by":[118],"significant":[120],"margin.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2020-04-03T00:00:00"}