{"id":"https://openalex.org/W3189718596","doi":"https://doi.org/10.1145/3474085.3475634","title":"Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval","display_name":"Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3189718596","doi":"https://doi.org/10.1145/3474085.3475634","mag":"3189718596"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475634","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://eprints.gla.ac.uk/view/author/60445.html>","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xuri Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xuri Ge","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fuhai Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fuhai Chen","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Joemon M. Jose","orcid":null},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joemon M. Jose","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhilong Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhilong Ji","raw_affiliation_strings":["Tomorrow Advancing Life, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tomorrow Advancing Life, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhongqin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongqin Wu","raw_affiliation_strings":["Tomorrow Advancing Life, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tomorrow Advancing Life, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Liu","raw_affiliation_strings":["Tomorrow Advancing Life, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tomorrow Advancing Life, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.784,"has_fulltext":true,"cited_by_count":49,"citation_normalized_percentile":{"value":0.94706537,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5185","last_page":"5193"},"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":0.9973999857902527,"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":0.9925000071525574,"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/embedding","display_name":"Embedding","score":0.6383000016212463},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6377000212669373},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5759000182151794},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5432000160217285},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5157999992370605},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.5059000253677368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360000014305115},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6383000016212463},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6377000212669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607699990272522},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5759000182151794},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5432000160217285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5379999876022339},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5157999992370605},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4830000102519989},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.476500004529953},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4049000144004822},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.26510000228881836}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3474085.3475634","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:253061","is_oa":true,"landing_page_url":"http://eprints.gla.ac.uk/view/author/60445.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:arXiv.org:2108.02417","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.02417","pdf_url":"https://arxiv.org/pdf/2108.02417","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:253061","is_oa":true,"landing_page_url":"http://eprints.gla.ac.uk/view/author/60445.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2064675550","https://openalex.org/W2131774270","https://openalex.org/W2143017621","https://openalex.org/W2185175083","https://openalex.org/W2546696630","https://openalex.org/W2606473278","https://openalex.org/W2745461083","https://openalex.org/W2767057417","https://openalex.org/W2778940641","https://openalex.org/W2896826707","https://openalex.org/W2962964995","https://openalex.org/W2963389687","https://openalex.org/W2964120214","https://openalex.org/W2964276596","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W3035454331","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3107807204","https://openalex.org/W3110042533"],"related_works":[],"abstract_inverted_index":{"The":[0],"current":[1],"state-of-the-art":[2],"image-sentence":[3],"retrieval":[4,33],"methods":[5],"implicitly":[6],"align":[7],"the":[8,25,32,57,71,98],"visual-textual":[9],"fragments,":[10],"like":[11],"regions":[12],"in":[13,17,44,82],"images":[14],"and":[15,19,47,88,94,100],"words":[16],"sentences,":[18],"adopt":[20],"attention":[21],"modules":[22],"to":[23,38,55],"highlight":[24],"relevance":[26],"of":[27,41,73],"cross-modal":[28],"semantic":[29,83,95],"correspondences.":[30],"However,":[31],"performance":[34],"remains":[35],"unsatisfactory":[36],"due":[37],"a":[39],"lack":[40],"consistent":[42],"representation":[43],"both":[45],"semantics":[46],"structural":[48,93],"spaces.":[49],"In":[50],"this":[51],"work,":[52],"we":[53],"propose":[54],"address":[56],"above":[58],"issue":[59],"from":[60],"two":[61],"aspects:":[62],"(i)":[63],"constructing":[64],"intrinsic":[65],"structure":[66,84],"(along":[67],"with":[68],"relations)":[69],"among":[70],"fragments":[72],"respective":[74],"modalities,":[75],"e.g.,":[76],"\"dog":[77],"\u2192":[78,80],"play":[79],"ball\"":[81],"for":[85],"an":[86],"image,":[87],"(ii)":[89],"seeking":[90],"explicit":[91],"inter-modal":[92],"correspondence":[96],"between":[97],"visual":[99],"textual":[101],"modalities.":[102]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2021-08-16T00:00:00"}
