{"id":"https://openalex.org/W4415541307","doi":"https://doi.org/10.1145/3746027.3755338","title":"Visual Grounding with Attention-Driven Constraint Balancing","display_name":"Visual Grounding with Attention-Driven Constraint Balancing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415541307","doi":"https://doi.org/10.1145/3746027.3755338"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755338","doi":"https://doi.org/10.1145/3746027.3755338","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755338","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/2407.03243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113395507","display_name":"Weitai Kang","orcid":"https://orcid.org/0009-0007-6484-0665","observed_orcids":["https://orcid.org/0009-0007-6484-0665"]},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weitai Kang","raw_affiliation_strings":["University of Illinois Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0009-0007-6484-0665","affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084879213","display_name":"Luowei Zhou","orcid":"https://orcid.org/0000-0003-1197-0101","observed_orcids":["https://orcid.org/0000-0003-1197-0101"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luowei Zhou","raw_affiliation_strings":["Samsung, Bellevue, USA"],"raw_orcid":"https://orcid.org/0000-0003-1197-0101","affiliations":[{"raw_affiliation_string":"Samsung, Bellevue, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junyi Wu","orcid":"https://orcid.org/0009-0003-8867-7285","observed_orcids":["https://orcid.org/0009-0003-8867-7285"]},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junyi Wu","raw_affiliation_strings":["University of Illinois Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0009-0003-8867-7285","affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081724365","display_name":"Changchang Sun","orcid":"https://orcid.org/0000-0003-3685-1205","observed_orcids":["https://orcid.org/0000-0003-3685-1205"]},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changchang Sun","raw_affiliation_strings":["University of Illinois Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0000-0003-3685-1205","affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100395035","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-7618-119X","observed_orcids":["https://orcid.org/0000-0002-7618-119X","https://orcid.org/0000-0002-3674-7160","https://orcid.org/0009-0007-1227-8594","https://orcid.org/0000-0001-9108-6767","https://orcid.org/0000-0002-3182-1739","https://orcid.org/0000-0002-1669-0662"]},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["University of Illinois Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0009-0007-1227-8594","affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7574,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92294093,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1637","last_page":"1645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955999851226807,"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":0.9955999851226807,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0017999999690800905,"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":0.00139999995008111,"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/visual-grounding","display_name":"visual grounding","score":0.9980000257492065},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.40299999713897705},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.625},{"id":"https://openalex.org/keywords/loss-function-design","display_name":"loss function design","score":0.6510000228881836},{"id":"https://openalex.org/keywords/bounding-box-regression","display_name":"bounding box regression","score":0.8059999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5782999992370605},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3709999918937683},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3594000041484833},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2669000029563904},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3746027.3755338","doi":"https://doi.org/10.1145/3746027.3755338","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755338","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.03243","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.03243","pdf_url":"https://arxiv.org/pdf/2407.03243","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":"doi:10.48550/arxiv.2407.03243","doi":"https://doi.org/10.48550/arxiv.2407.03243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.03243","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:2407.03243","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.03243","pdf_url":"https://arxiv.org/pdf/2407.03243","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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415541307.pdf","grobid_xml":"https://content.openalex.org/works/W4415541307.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2251512949","https://openalex.org/W2302086703","https://openalex.org/W2489434015","https://openalex.org/W2505639562","https://openalex.org/W2745461083","https://openalex.org/W2770717329","https://openalex.org/W2796347433","https://openalex.org/W2896457183","https://openalex.org/W2904164128","https://openalex.org/W2950628590","https://openalex.org/W2962749469","https://openalex.org/W2963109634","https://openalex.org/W2963705779","https://openalex.org/W2964157791","https://openalex.org/W2964345792","https://openalex.org/W2984121207","https://openalex.org/W2986755220","https://openalex.org/W2987734933","https://openalex.org/W3030520226","https://openalex.org/W3034772468","https://openalex.org/W3034984754","https://openalex.org/W3110435696","https://openalex.org/W3123746945","https://openalex.org/W3156978626","https://openalex.org/W3173364567","https://openalex.org/W3174004334","https://openalex.org/W4312351586","https://openalex.org/W4313145013","https://openalex.org/W4386071469","https://openalex.org/W4386076636","https://openalex.org/W4393212018","https://openalex.org/W4399152057","https://openalex.org/W4400376900","https://openalex.org/W4402996979"],"related_works":["https://openalex.org/W7125376029","https://openalex.org/W4313145013","https://openalex.org/W3156978626","https://openalex.org/W4414539906","https://openalex.org/W3163747765","https://openalex.org/W4394995067","https://openalex.org/W4403617341","https://openalex.org/W4404654761","https://openalex.org/W4404294518","https://openalex.org/W4411635479"],"abstract_inverted_index":{"Unlike":[0],"Object":[1,65],"Detection,":[2],"Visual":[3],"Grounding":[4],"task":[5],"necessitates":[6],"the":[7,49,54,70,80,93,115],"detection":[8],"of":[9,96,117],"an":[10],"object":[11],"described":[12],"by":[13,154],"complex":[14,21],"free-form":[15],"language.":[16],"To":[17,83],"simultaneously":[18],"model":[19],"such":[20],"semantic":[22],"and":[23,52],"visual":[24,44,118],"representations,":[25],"recent":[26],"state-of-the-art":[27,152],"studies":[28],"adopt":[29],"transformer-based":[30,97],"models":[31,141],"to":[32,46,76,113],"fuse":[33],"features":[34,45,119],"from":[35],"both":[36],"modalities,":[37],"further":[38,103],"introducing":[39],"various":[40],"modules":[41],"that":[42,127],"modulate":[43],"align":[47],"with":[48],"language":[50],"expressions":[51],"eliminate":[53],"irrelevant":[55],"redundant":[56],"information.":[57],"However,":[58],"their":[59],"loss":[60],"function,":[61],"still":[62],"adopting":[63],"common":[64],"Detection":[66],"losses,":[67],"solely":[68],"governs":[69],"bounding":[71],"box":[72],"regression":[73],"output,":[74],"failing":[75],"fully":[77],"optimize":[78,114],"for":[79],"above":[81],"objectives.":[82],"tackle":[84],"this":[85,88],"problem,":[86],"in":[87],"paper,":[89],"we":[90,102,134,148],"first":[91],"analyze":[92],"attention":[94],"mechanisms":[95],"models.":[98],"Building":[99],"upon":[100],"this,":[101],"propose":[104],"a":[105,150],"novel":[106],"framework":[107],"named":[108],"Attention-Driven":[109],"Constraint":[110],"Balancing":[111],"(AttBalance)":[112],"behavior":[116],"within":[120],"language-relevant":[121],"regions.":[122],"Extensive":[123],"experimental":[124],"results":[125],"show":[126],"our":[128,156],"method":[129,157],"brings":[130],"impressive":[131],"improvements.":[132],"Specifically,":[133],"achieve":[135],"constant":[136],"improvements":[137],"over":[138],"five":[139],"different":[140,145],"evaluated":[142],"on":[143],"four":[144],"benchmarks.":[146],"Moreover,":[147],"attain":[149],"new":[151],"performance":[153],"integrating":[155],"into":[158],"QRNet.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-25T00:00:00"}