{"id":"https://openalex.org/W3092961994","doi":"https://doi.org/10.1145/3394171.3413846","title":"Cross-Modal Omni Interaction Modeling for Phrase Grounding","display_name":"Cross-Modal Omni Interaction Modeling for Phrase Grounding","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092961994","doi":"https://doi.org/10.1145/3394171.3413846","mag":"3092961994"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-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/A5101790974","display_name":"Tianyu Yu","orcid":"https://orcid.org/0000-0003-0609-0994"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyu Yu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056811650","display_name":"Tianrui Hui","orcid":"https://orcid.org/0000-0002-1172-1554"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Hui","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences &38; University of Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences &38; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026990863","display_name":"Zhihao Yu","orcid":"https://orcid.org/0009-0009-4233-9030"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Yu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002061412","display_name":"Yue Liao","orcid":"https://orcid.org/0000-0002-2671-0655"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Liao","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073608824","display_name":"Sansi Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sansi Yu","raw_affiliation_strings":["Tencent Marketing Solution, Shen Zhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent Marketing Solution, Shen Zhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076531452","display_name":"Faxi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Faxi Zhang","raw_affiliation_strings":["Tencent Marketing Solution, Shen Zhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent Marketing Solution, Shen Zhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330142","display_name":"Si Liu","orcid":"https://orcid.org/0000-0003-3578-7432"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101790974"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.1724,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.81449553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1725","last_page":"1734"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.982699990272522,"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":0.9799000024795532,"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":0.7841447591781616},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6937445402145386},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6375362873077393},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5038618445396423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.50326007604599},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47322049736976624},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4305267930030823},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4253199100494385},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41871756315231323},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.4130183756351471},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0766235888004303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7841447591781616},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6937445402145386},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6375362873077393},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5038618445396423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.50326007604599},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47322049736976624},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4305267930030823},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4253199100494385},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41871756315231323},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.4130183756351471},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0766235888004303},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W1905882502","https://openalex.org/W2006147162","https://openalex.org/W2064675550","https://openalex.org/W2112912048","https://openalex.org/W2241785942","https://openalex.org/W2251512949","https://openalex.org/W2254252455","https://openalex.org/W2410323755","https://openalex.org/W2412400526","https://openalex.org/W2522861532","https://openalex.org/W2561675875","https://openalex.org/W2753107664","https://openalex.org/W2768147806","https://openalex.org/W2799263800","https://openalex.org/W2804243936","https://openalex.org/W2891999386","https://openalex.org/W2903046518","https://openalex.org/W2922294372","https://openalex.org/W2925509384","https://openalex.org/W2950616067","https://openalex.org/W2951239727","https://openalex.org/W2951638509","https://openalex.org/W2952433032","https://openalex.org/W2962811161","https://openalex.org/W2963000732","https://openalex.org/W2963914122","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2975706270","https://openalex.org/W2981587852","https://openalex.org/W2983358816","https://openalex.org/W2987306276","https://openalex.org/W2987734933","https://openalex.org/W2989176720","https://openalex.org/W3034325957","https://openalex.org/W3034463304","https://openalex.org/W3034772468","https://openalex.org/W3035170495","https://openalex.org/W3089797362","https://openalex.org/W3098232790"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2385859805","https://openalex.org/W2021787609","https://openalex.org/W2530972254","https://openalex.org/W2097328689","https://openalex.org/W4234899305","https://openalex.org/W2012262991","https://openalex.org/W1537063595","https://openalex.org/W2379604501","https://openalex.org/W627697492"],"abstract_inverted_index":{"Phrase":[0],"grounding":[1,171],"aims":[2],"to":[3,39,130,137,150,165,207,215],"localize":[4],"the":[5,18,30,37,41,82,99,103,111,115,132,139,151,167,176],"objects":[6],"described":[7],"by":[8,190],"phrases":[9,92],"in":[10,29,197],"a":[11,52,62,66,70,75,121,127,158],"natural":[12],"language":[13],"specification.":[14],"Previous":[15],"works":[16],"model":[17],"interaction":[19,64,68,72,104,116,133,153],"of":[20,61,178,199,219],"inputs":[21],"from":[22],"text":[23],"modality":[24,27],"and":[25,34,43,74,85,91,108,146,209],"visual":[26],"only":[28],"intra-modal":[31],"global":[32,67,112],"level":[33],"consequently":[35],"lacks":[36],"ability":[38],"capture":[40,98],"precise":[42],"complete":[44],"context":[45,113,141],"information.":[46],"In":[47,148],"this":[48],"paper,":[49],"we":[50,155],"propose":[51],"novel":[53],"Cross-Modal":[54],"Omni":[55],"Interaction":[56],"network":[57],"(COI":[58],"Net)":[59],"composed":[60],"neighboring":[63,106],"module,":[65,69],"cross-modal":[71,140],"module":[73,129],"multilevel":[76,162],"alignment":[77,163],"module.":[78],"Our":[79],"approach":[80,185],"formulates":[81],"complex":[83],"spatial":[84],"semantic":[86],"relationship":[87,101],"among":[88,105,117,169],"image":[89,144],"regions":[90,107,119,145],"through":[93,114],"multi-level":[94],"multi-modal":[95],"interaction.":[96],"We":[97,124,173],"local":[100],"using":[102,120],"then":[109],"collect":[110],"all":[118,143,170],"transformer":[122],"encoder.":[123],"further":[125],"use":[126],"co-attention":[128],"apply":[131],"between":[134],"two":[135,194],"modalities":[136],"gather":[138],"for":[142],"phrases.":[147],"addition":[149],"omni":[152],"modeling,":[154],"also":[156],"leverage":[157],"straightforward":[159],"yet":[160],"effective":[161],"regularization":[164],"formulate":[166],"dependencies":[168],"decisions.":[172],"extensively":[174],"validate":[175],"effectiveness":[177],"our":[179,184,220],"model.":[180],"Experiments":[181],"show":[182],"that":[183],"outperforms":[186],"existing":[187],"state-of-the-art":[188],"methods":[189],"large":[191],"margins":[192],"on":[193,202,211],"popular":[195],"datasets":[196],"terms":[198],"accuracy:":[200],"6.15%":[201],"Flickr30K":[203],"Entities":[204],"(71.36%":[205],"increased":[206,214],"77.51%)":[208],"21.25%":[210],"ReferItGame":[212],"(44.91%":[213],"66.16%).":[216],"The":[217],"code":[218],"implementation":[221],"is":[222],"available":[223],"at":[224],"https://github.com/yiranyyu/Phrase-Grounding.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}