{"id":"https://openalex.org/W3188401685","doi":"https://doi.org/10.1145/3477314.3507047","title":"A better loss for visual-textual grounding","display_name":"A better loss for visual-textual grounding","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W3188401685","doi":"https://doi.org/10.1145/3477314.3507047","mag":"3188401685"},"language":"en","primary_location":{"id":"doi:10.1145/3477314.3507047","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507047","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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 37th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.05308","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014493429","display_name":"Davide Rigoni","orcid":"https://orcid.org/0000-0003-2092-3577"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Rigoni","raw_affiliation_strings":["University of Padua, Padua, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Padua, Padua, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023894100","display_name":"Luciano Serafini","orcid":"https://orcid.org/0000-0003-4812-1031"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luciano Serafini","raw_affiliation_strings":["Bruno Kessler Foundation, Povo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bruno Kessler Foundation, Povo, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064873591","display_name":"Alessandro Sperduti","orcid":"https://orcid.org/0000-0002-8686-850X"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Sperduti","raw_affiliation_strings":["University of Padua, Padua, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Padua, Padua, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1849,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46339775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"57"},"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":0.9972000122070312,"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":0.9958000183105469,"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":0.7973998785018921},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.7820918560028076},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6225668787956238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6116642355918884},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5825954079627991},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5503600239753723},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5237289071083069},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.51971036195755},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4540168046951294},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4441668391227722},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4427226185798645},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4303189516067505},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41956573724746704},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.415494441986084},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39724403619766235},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3289532959461212}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973998785018921},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7820918560028076},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6225668787956238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6116642355918884},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5825954079627991},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5503600239753723},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5237289071083069},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.51971036195755},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4540168046951294},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4441668391227722},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4427226185798645},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4303189516067505},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41956573724746704},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.415494441986084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39724403619766235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3289532959461212},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3477314.3507047","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507047","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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 37th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.05308","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.05308","pdf_url":"https://arxiv.org/pdf/2108.05308","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,"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":"pmh:oai:www.research.unipd.it:11577/3459579","is_oa":true,"landing_page_url":"http://hdl.handle.net/11577/3459579","pdf_url":"https://www.research.unipd.it/bitstream/11577/3459579/2/SAC_2022_A_Better_Loss_for_Visual_Textual_Grounding_Supplementary.pdf","source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.05308","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.05308","pdf_url":"https://arxiv.org/pdf/2108.05308","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,"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":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W1527575280","https://openalex.org/W1533861849","https://openalex.org/W1773149199","https://openalex.org/W1931795219","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2088049833","https://openalex.org/W2123024445","https://openalex.org/W2185175083","https://openalex.org/W2190656909","https://openalex.org/W2250539671","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2520141964","https://openalex.org/W2568262903","https://openalex.org/W2605295222","https://openalex.org/W2606473278","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2767014100","https://openalex.org/W2796347433","https://openalex.org/W2798990097","https://openalex.org/W2799263800","https://openalex.org/W2950761309","https://openalex.org/W2952524542","https://openalex.org/W2962362641","https://openalex.org/W2962706528","https://openalex.org/W2962764817","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2963042258","https://openalex.org/W2963080533","https://openalex.org/W2963109634","https://openalex.org/W2963176022","https://openalex.org/W2963191264","https://openalex.org/W2963383024","https://openalex.org/W2963389687","https://openalex.org/W2963445828","https://openalex.org/W2963681613","https://openalex.org/W2963735856","https://openalex.org/W2963783181","https://openalex.org/W2963914122","https://openalex.org/W2964022527","https://openalex.org/W2964276121","https://openalex.org/W2970798877","https://openalex.org/W2983358816","https://openalex.org/W2984194315","https://openalex.org/W2986803748","https://openalex.org/W2987734933","https://openalex.org/W2997747012","https://openalex.org/W3012008446","https://openalex.org/W3015121488","https://openalex.org/W3023254438","https://openalex.org/W3034952258","https://openalex.org/W3036255508","https://openalex.org/W3036683334","https://openalex.org/W3037533539","https://openalex.org/W3098232790","https://openalex.org/W3106250896","https://openalex.org/W3177525997","https://openalex.org/W4298136621"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W4287027631","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"Given":[0],"a":[1,27,136,163,173,185],"textual":[2],"phrase":[3],"and":[4,41,58,61,93,118],"an":[5],"image,":[6],"the":[7,12,16,19,23,46,97,102,107,119,148,154,190],"visual":[8,103],"grounding":[9,92],"problem":[10,54],"is":[11,26,115,169],"task":[13,29],"of":[14,18,101],"locating":[15],"content":[17],"image":[20],"referenced":[21],"by":[22,55,78],"sentence.":[24],"It":[25],"challenging":[28],"that":[30,64,82],"has":[31],"several":[32,49],"real-world":[33],"applications":[34],"in":[35],"human-computer":[36],"interaction,":[37],"image-text":[38],"reference":[39,43],"resolution,":[40],"video-text":[42],"resolution.":[44],"In":[45,131],"last":[47],"years,":[48],"works":[50],"have":[51],"addressed":[52],"this":[53,129,132],"proposing":[56],"more":[57,59],"large":[60],"complex":[62],"models":[63,74,121,178],"try":[65],"to":[66,86,95,128,171],"capture":[67],"visual-textual":[68],"dependencies":[69],"better":[70,186],"than":[71,176],"before.":[72],"These":[73],"are":[75,122],"typically":[76],"constituted":[77],"two":[79,113,180,191],"main":[80],"components":[81],"focus":[83],"on":[84,140,179],"how":[85,94],"learn":[87],"useful":[88],"multi-modal":[89,165],"features":[90],"for":[91],"improve":[96],"predicted":[98],"bounding":[99,141,149,155],"box":[100],"mention,":[104],"respectively.":[105],"Finding":[106],"right":[108],"learning":[109,187],"balance":[110,188],"between":[111,189],"these":[112],"sub-tasks":[114,192],"not":[116,123],"easy,":[117],"current":[120],"necessarily":[124],"optimal":[125],"with":[126],"respect":[127],"issue.":[130],"work,":[133],"we":[134],"propose":[135],"loss":[137],"function":[138],"based":[139],"boxes":[142,150,156],"classes":[143],"probabilities":[144],"that:":[145],"(i)":[146],"improves":[147,153],"selection;":[151],"(ii)":[152],"coordinates":[157],"prediction.":[158],"Our":[159],"model,":[160],"although":[161],"using":[162],"simple":[164],"feature":[166],"fusion":[167],"component,":[168],"able":[170],"achieve":[172],"higher":[174],"accuracy":[175],"state-of-the-art":[177],"widely":[181],"adopted":[182],"datasets,":[183],"reaching":[184],"mentioned":[193],"above.":[194]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}