{"id":"https://openalex.org/W3093017735","doi":"https://doi.org/10.1145/3394171.3413902","title":"Visual-Semantic Graph Matching for Visual Grounding","display_name":"Visual-Semantic Graph Matching for Visual Grounding","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093017735","doi":"https://doi.org/10.1145/3394171.3413902","mag":"3093017735"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413902","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":"conference-paper","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/A5068555749","display_name":"Chenchen Jing","orcid":"https://orcid.org/0000-0002-1340-6064"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenchen Jing","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071656520","display_name":"Yuwei Wu","orcid":"https://orcid.org/0000-0001-6300-6336"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Wu","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076449752","display_name":"Mingtao Pei","orcid":"https://orcid.org/0000-0003-4949-7997"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingtao Pei","raw_affiliation_strings":["Beijing Institute of Technology, Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing , China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100666109","display_name":"Yao Hu","orcid":"https://orcid.org/0000-0003-4573-5740"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Hu","raw_affiliation_strings":["Alibaba Youku Cognitive &38; Intelligent Lab, Beijing, China","Alibaba Youku Cognitive &38"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Youku Cognitive &38; Intelligent Lab, Beijing, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Youku Cognitive &38","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731042","display_name":"Yunde Jia","orcid":"https://orcid.org/0000-0003-1900-8945"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunde Jia","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060958969","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0003-3631-256X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9649,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.90878517,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4041","last_page":"4050"},"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":0.9980999827384949,"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":0.9976000189781189,"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":0.7209142446517944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5383824110031128},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.5219559073448181},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5098497271537781},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4322693347930908},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.41167688369750977},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3993167579174042},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33930471539497375},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.32768911123275757},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19972580671310425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209142446517944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5383824110031128},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.5219559073448181},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5098497271537781},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4322693347930908},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41167688369750977},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3993167579174042},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33930471539497375},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.32768911123275757},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19972580671310425},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413902","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W2013603106","https://openalex.org/W2076080556","https://openalex.org/W2077069816","https://openalex.org/W2131774270","https://openalex.org/W2142900973","https://openalex.org/W2166820607","https://openalex.org/W2247513039","https://openalex.org/W2250378130","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2520141964","https://openalex.org/W2558535589","https://openalex.org/W2571175805","https://openalex.org/W2583360688","https://openalex.org/W2745461083","https://openalex.org/W2770129969","https://openalex.org/W2799132636","https://openalex.org/W2799263800","https://openalex.org/W2899771611","https://openalex.org/W2904910963","https://openalex.org/W2909593838","https://openalex.org/W2931335216","https://openalex.org/W2946086442","https://openalex.org/W2948087948","https://openalex.org/W2960655175","https://openalex.org/W2962739339","https://openalex.org/W2962764817","https://openalex.org/W2963101956","https://openalex.org/W2963109634","https://openalex.org/W2963389687","https://openalex.org/W2963735856","https://openalex.org/W2963783181","https://openalex.org/W2963800628","https://openalex.org/W2963863119","https://openalex.org/W2964022527","https://openalex.org/W2964138343","https://openalex.org/W2964276121","https://openalex.org/W2964284374","https://openalex.org/W2964345792","https://openalex.org/W2964935470","https://openalex.org/W2970798877","https://openalex.org/W2983178467","https://openalex.org/W2983358816","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2990397898","https://openalex.org/W2997072136","https://openalex.org/W2998631105","https://openalex.org/W3037533539","https://openalex.org/W3098232790"],"related_works":["https://openalex.org/W2375873920","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2392760275","https://openalex.org/W2083530853","https://openalex.org/W2009831055","https://openalex.org/W2393172683","https://openalex.org/W1986106996","https://openalex.org/W4285012873","https://openalex.org/W2122517733"],"abstract_inverted_index":{"Visual":[0],"Grounding":[1],"is":[2,82],"the":[3,53,65,91,115,139],"task":[4],"of":[5,52,64,141],"associating":[6],"entities":[7],"in":[8,15],"a":[9,26,35,40,70,86,106],"natural":[10],"language":[11,41],"sentence":[12,54],"with":[13,119],"objects":[14],"an":[16],"image.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21],"formulate":[22],"visual":[23,36,128],"grounding":[24,129],"as":[25,85],"graph":[27,38,72,80],"matching":[28,81],"problem":[29,89,118],"to":[30,75,113],"find":[31],"node":[32,62,93,97],"correspondences":[33],"between":[34],"scene":[37,42],"and":[39,55,99,105,135],"graph.":[43],"These":[44],"two":[45,66,127],"graphs":[46,67],"are":[47,110],"heterogeneous,":[48],"representing":[49],"structure":[50,100],"layouts":[51],"image,":[56],"respectively.":[57],"We":[58],"learn":[59],"unified":[60],"contextual":[61],"representations":[63,94],"by":[68],"using":[69],"cross-modal":[71],"convolutional":[73],"network":[74],"reduce":[76],"their":[77],"discrepancy.":[78],"The":[79],"thus":[83],"relaxed":[84],"linear":[87,116],"assignment":[88,117],"because":[90],"learned":[92],"characterize":[95],"both":[96],"information":[98],"information.":[101],"A":[102],"permutation":[103],"loss":[104,109],"semantic":[107],"cycle-consistency":[108],"further":[111],"introduced":[112],"solve":[114],"or":[120],"without":[121],"ground-truth":[122],"correspondences.":[123],"Experimental":[124],"results":[125],"on":[126],"tasks,":[130],"i.e.,":[131],"referring":[132],"expression":[133],"comprehension":[134],"phrase":[136],"localization,":[137],"demonstrate":[138],"effectiveness":[140],"our":[142],"method.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}