{"id":"https://openalex.org/W4387969812","doi":"https://doi.org/10.1145/3581783.3611721","title":"Suspected Objects Matter: Rethinking Model's Prediction for One-stage Visual Grounding","display_name":"Suspected Objects Matter: Rethinking Model's Prediction for One-stage Visual Grounding","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969812","doi":"https://doi.org/10.1145/3581783.3611721"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5103194585","display_name":"Yang Jiao","orcid":"https://orcid.org/0000-0002-8679-2242"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Jiao","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075329194","display_name":"Zequn Jie","orcid":"https://orcid.org/0000-0002-3038-5891"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zequn Jie","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373471","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0001-6234-1124"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115410039","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0003-3970-6548"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100644845","display_name":"Yu-Gang Jiang","orcid":"https://orcid.org/0000-0002-8781-6955"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103194585"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.6149,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70205321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"26"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9993000030517578,"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":0.9993000030517578,"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":0.7815594673156738},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7654777765274048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6399228572845459},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5803232192993164},{"id":"https://openalex.org/keywords/object-model","display_name":"Object model","score":0.490714430809021},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.47857311367988586},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.43651509284973145},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4240562915802002},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33237770199775696},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.22705551981925964},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09042602777481079}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7815594673156738},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7654777765274048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6399228572845459},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5803232192993164},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.490714430809021},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.47857311367988586},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.43651509284973145},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4240562915802002},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33237770199775696},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22705551981925964},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09042602777481079},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"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":44,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2006147162","https://openalex.org/W2058809360","https://openalex.org/W2193145675","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2565639579","https://openalex.org/W2571175805","https://openalex.org/W2601564443","https://openalex.org/W2606473278","https://openalex.org/W2770129969","https://openalex.org/W2904910963","https://openalex.org/W2948037078","https://openalex.org/W2962764817","https://openalex.org/W2963037989","https://openalex.org/W2963091558","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2963735856","https://openalex.org/W2963783181","https://openalex.org/W2964022527","https://openalex.org/W2964345792","https://openalex.org/W2982770724","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W3034772468","https://openalex.org/W3035268124","https://openalex.org/W3037533539","https://openalex.org/W3106250896","https://openalex.org/W3110435696","https://openalex.org/W3112077297","https://openalex.org/W3171547673","https://openalex.org/W3173223111","https://openalex.org/W3173364567","https://openalex.org/W3206209177","https://openalex.org/W4238216513","https://openalex.org/W4283029876","https://openalex.org/W4312650216","https://openalex.org/W4385570257","https://openalex.org/W4385571155","https://openalex.org/W6600175266","https://openalex.org/W6602670149"],"related_works":["https://openalex.org/W4287280733","https://openalex.org/W3213573742","https://openalex.org/W2128203364","https://openalex.org/W2026565050","https://openalex.org/W3136070008","https://openalex.org/W2108712229","https://openalex.org/W2161198505","https://openalex.org/W2367015181","https://openalex.org/W2048280641","https://openalex.org/W3035117168"],"abstract_inverted_index":{"Recently,":[0],"one-stage":[1,29,71,144],"visual":[2,145],"grounders":[3,146],"attract":[4],"high":[5,214],"attention":[6],"due":[7],"to":[8,50,87,147,168,198,215,227],"their":[9,67],"comparable":[10],"accuracy":[11],"but":[12],"significantly":[13],"higher":[14],"efficiency":[15],"than":[16,101],"two-stage":[17],"grounders.":[18,30],"However,":[19,65],"inter-object":[20],"relation":[21],"modeling":[22],"has":[23],"not":[24,37],"been":[25],"well":[26],"studied":[27],"for":[28],"Inter-object":[31],"relationship":[32,93],"modeling,":[33],"though":[34],"important,":[35],"is":[36,73],"necessarily":[38],"performed":[39],"among":[40,153],"all":[41],"objects,":[42,181],"as":[43,82,103],"only":[44],"part":[45],"of":[46,179,233,251],"them":[47],"are":[48,80,98,159,195],"related":[49],"the":[51,57,70,83,120,149,154,169,200,207,220,225,229,242,249],"text":[52],"query":[53],"and":[54,91,115,142,187],"may":[55,105],"confuse":[56],"model.":[58],"We":[59],"call":[60],"these":[61],"objects":[62,90,97,158],"\"suspected":[63],"objects\".":[64],"exploring":[66],"relationships":[68],"in":[69,236],"paradigm":[72],"non-trivial":[74],"because:":[75],"(1)":[76],"no":[77],"object":[78,151,217,231],"proposals":[79],"available":[81],"basis":[84],"on":[85,177],"which":[86,134],"select":[88],"suspected":[89,96,155,180,216],"perform":[92],"modeling;":[94],"(2)":[95],"more":[99,117],"confusing":[100],"others,":[102],"they":[104],"share":[106],"similar":[107],"semantics,":[108],"be":[109,136],"entangled":[110],"with":[111],"certain":[112],"relationships,":[113],"etc,":[114],"thereby":[116],"easily":[118],"mislead":[119],"model's":[121,170],"prediction.":[122,205,245],"Toward":[123],"this":[124],"end,":[125],"we":[126],"propose":[127],"a":[128,163,182,237],"Suspected":[129,157],"Object":[130],"Transformation":[131],"mechanism":[132],"(SOT),":[133],"can":[135],"seamlessly":[137],"integrated":[138],"into":[139],"existing":[140],"CNN":[141],"Transformer-based":[143],"encourage":[148],"target":[150],"selection":[152],"ones.":[156],"dynamically":[160],"discovered":[161],"from":[162],"learned":[164],"activation":[165],"map":[166],"adapted":[167],"current":[171,243],"discrimination":[172],"ability":[173],"during":[174],"training.":[175],"Afterward,":[176],"top":[178],"Keyword-Aware":[183],"Discrimination":[184],"module":[185],"(KAD)":[186],"an":[188],"Exploration":[189],"by":[190],"Random":[191],"Connection":[192],"strategy":[193],"(ERC)":[194],"concurrently":[196],"proposed":[197,253],"help":[199],"model":[201,226],"rethink":[202],"its":[203],"initial":[204],"On":[206,219],"one":[208],"hand,":[209,222],"KAD":[210],"leverages":[211],"keywords":[212],"contributing":[213],"discrimination.":[218],"other":[221],"ERC":[223],"allows":[224],"seek":[228],"correct":[230],"instead":[232],"being":[234],"trapped":[235],"situation":[238],"that":[239],"always":[240],"exploits":[241],"false":[244],"Extensive":[246],"experiments":[247],"demonstrate":[248],"effectiveness":[250],"our":[252],"method.":[254]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}