{"id":"https://openalex.org/W4402706555","doi":"https://doi.org/10.1145/3664647.3681660","title":"ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Grounding","display_name":"ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Grounding","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4402706555","doi":"https://doi.org/10.1145/3664647.3681660"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681660","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681660","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3681660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071596230","display_name":"Minghang Zheng","orcid":"https://orcid.org/0000-0003-1612-975X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Minghang Zheng","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiahua Zhang","orcid":"https://orcid.org/0009-0009-0312-8484"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahua Zhang","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069484115","display_name":"Qing-Chao Chen","orcid":"https://orcid.org/0000-0002-1216-5609"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingchao Chen","raw_affiliation_strings":["National Institute of Health Data Science, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Institute of Health Data Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047811387","display_name":"Yuxin Peng","orcid":"https://orcid.org/0000-0001-7658-3845"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Peng","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355884","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-4259-3882"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University & State Key Laboratory of General Artificial Intelligence, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University & State Key Laboratory of General Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071596230"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.7339,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71969188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1187","last_page":"1196"},"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":0.9983999729156494,"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":0.994700014591217,"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":0.8447935581207275},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7170383930206299},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.7036407589912415},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.6220699548721313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5676854848861694},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.555415689945221},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43902474641799927},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4222594201564789},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41126903891563416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3275279998779297},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25455257296562195},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09232702851295471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8447935581207275},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7170383930206299},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.7036407589912415},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.6220699548721313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5676854848861694},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.555415689945221},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43902474641799927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4222594201564789},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41126903891563416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3275279998779297},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25455257296562195},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09232702851295471}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681660","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681660","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.16314","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.16314","pdf_url":"https://arxiv.org/pdf/2408.16314","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681660","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681660","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3077714275","display_name":null,"funder_award_id":"62372014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6078352744","display_name":null,"funder_award_id":"62132001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7427494650","display_name":null,"funder_award_id":"61925201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8871594933","display_name":null,"funder_award_id":"U22B2048","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2251512949","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2568262903","https://openalex.org/W2606473278","https://openalex.org/W2770129969","https://openalex.org/W2897772777","https://openalex.org/W2946086442","https://openalex.org/W2954996726","https://openalex.org/W2962764817","https://openalex.org/W2962766617","https://openalex.org/W2962823940","https://openalex.org/W2963109634","https://openalex.org/W2963783181","https://openalex.org/W2963800628","https://openalex.org/W2964089981","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W2997429269","https://openalex.org/W2998508940","https://openalex.org/W2999905431","https://openalex.org/W3034772468","https://openalex.org/W3096609285","https://openalex.org/W3096831136","https://openalex.org/W3103542727","https://openalex.org/W3110435696","https://openalex.org/W3173364567","https://openalex.org/W3174004334","https://openalex.org/W4214490042","https://openalex.org/W4225517085","https://openalex.org/W4225700112","https://openalex.org/W4283814553","https://openalex.org/W4312402470","https://openalex.org/W4312845548","https://openalex.org/W4312933868","https://openalex.org/W4313145013","https://openalex.org/W4380609723","https://openalex.org/W4382240078","https://openalex.org/W4383988673","https://openalex.org/W4385572302","https://openalex.org/W4386075819","https://openalex.org/W4387889979","https://openalex.org/W4389352357","https://openalex.org/W4390872876","https://openalex.org/W4390873208","https://openalex.org/W4390873752","https://openalex.org/W4392543666","https://openalex.org/W4392931179","https://openalex.org/W4393148632"],"related_works":["https://openalex.org/W2362939901","https://openalex.org/W2734554632","https://openalex.org/W2379200451","https://openalex.org/W2356257939","https://openalex.org/W4254623023","https://openalex.org/W2363753014","https://openalex.org/W2385567678","https://openalex.org/W2355121635","https://openalex.org/W1967100394","https://openalex.org/W4312476862"],"abstract_inverted_index":{"Visual":[0,84],"grounding":[1,199],"aims":[2],"to":[3,8,88,121,185,194,211],"localize":[4],"the":[5,34,38,64,80,95,111,125,137,165,182,213],"object":[6,188],"referred":[7],"in":[9,56,132,197,202],"an":[10,57,60],"image":[11],"based":[12,171],"on":[13,172,218],"a":[14,41,47,77,147],"natural":[15],"language":[16],"query.":[17],"Although":[18],"progress":[19],"has":[20],"been":[21],"made":[22],"recently,":[23],"accurately":[24],"localizing":[25],"target":[26,129],"objects":[27,32,130,163],"within":[28],"multiple-instance":[29,205],"distractions":[30,55,144],"(multiple":[31],"of":[33,63,98,128,139,164,215],"same":[35,166],"category":[36,167],"as":[37],"target)":[39],"remains":[40],"significant":[42,48],"challenge.":[43],"Existing":[44],"methods":[45,217],"demonstrate":[46],"performance":[49,196],"drop":[50],"when":[51],"there":[52],"are":[53],"multiple":[54,143,162],"image,":[58],"indicating":[59],"insufficient":[61],"understanding":[62,97],"fine-grained":[65,99],"semantics":[66,100,189],"and":[67,82,168,190],"spatial":[68,174,191],"relationships":[69],"between":[70],"objects.":[71],"In":[72],"this":[73,90],"paper,":[74],"we":[75,93,135],"propose":[76],"novel":[78],"approach,":[79],"Relation":[81],"Semantic-sensitive":[83],"Grounding":[85],"(ResVG)":[86],"model,":[87],"address":[89],"issue.":[91],"Firstly,":[92],"enhance":[94],"model's":[96,183],"by":[101,116,145,158],"injecting":[102],"semantic":[103,126],"prior":[104],"information":[105],"derived":[106],"from":[107],"text":[108],"queries":[109,170],"into":[110],"model.":[112],"This":[113,152],"is":[114,222],"achieved":[115],"leveraging":[117],"text-to-image":[118],"generation":[119],"models":[120],"produce":[122],"images":[123,160],"representing":[124],"attributes":[127],"described":[131],"queries.":[133],"Secondly,":[134],"tackle":[136],"lack":[138],"training":[140,156],"samples":[141],"with":[142,204],"introducing":[146],"relation-sensitive":[148],"data":[149,157],"augmentation":[150],"method.":[151],"method":[153],"generates":[154],"additional":[155],"synthesizing":[159],"containing":[161],"pseudo":[169],"their":[173],"relationships.":[175],"The":[176],"proposed":[177],"ReSVG":[178],"model":[179],"significantly":[180],"improves":[181],"ability":[184],"comprehend":[186],"both":[187],"relations,":[192],"leading":[193],"enhanced":[195],"visual":[198],"tasks,":[200],"particularly":[201],"scenarios":[203],"distractions.":[206],"We":[207],"conduct":[208],"extensive":[209],"experiments":[210],"validate":[212],"effectiveness":[214],"our":[216],"five":[219],"datasets.":[220],"Code":[221],"available":[223],"at":[224],"https://github.com/minghangz/ResVG.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}