{"id":"https://openalex.org/W4403791948","doi":"https://doi.org/10.1145/3664647.3681424","title":"Bridging the Modality Gap: Dimension Information Alignment and Sparse Spatial Constraint for Image-Text Matching","display_name":"Bridging the Modality Gap: Dimension Information Alignment and Sparse Spatial Constraint for Image-Text Matching","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791948","doi":"https://doi.org/10.1145/3664647.3681424"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681424","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"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/A5036449183","display_name":"Xiang Ma","orcid":"https://orcid.org/0000-0002-4963-8705"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Ma","raw_affiliation_strings":["Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420276","display_name":"Xuemei Li","orcid":"https://orcid.org/0000-0001-5064-7425"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemei Li","raw_affiliation_strings":["Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051677056","display_name":"Lexin Fang","orcid":"https://orcid.org/0000-0003-3243-851X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lexin Fang","raw_affiliation_strings":["Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101753050","display_name":"Caiming Zhang","orcid":"https://orcid.org/0000-0003-0217-1543"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caiming Zhang","raw_affiliation_strings":["Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036449183"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.7479,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73072313,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5074","last_page":"5082"},"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":0.9998000264167786,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9980999827384949,"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/bridging","display_name":"Bridging (networking)","score":0.6734966039657593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6658766269683838},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6434822082519531},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.6384978890419006},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5726574063301086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5557811260223389},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5004217624664307},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4809531271457672},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4499571621417999},{"id":"https://openalex.org/keywords/image-matching","display_name":"Image matching","score":0.4444117248058319},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42656606435775757},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22150278091430664},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.0944567322731018},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07677391171455383}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6734966039657593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658766269683838},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6434822082519531},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6384978890419006},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5726574063301086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557811260223389},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5004217624664307},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4809531271457672},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4499571621417999},{"id":"https://openalex.org/C2986492983","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image matching","level":3,"score":0.4444117248058319},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42656606435775757},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22150278091430664},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0944567322731018},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07677391171455383},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1905882502","https://openalex.org/W1957706851","https://openalex.org/W2131774270","https://openalex.org/W2160197181","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2963350250","https://openalex.org/W2988823324","https://openalex.org/W2997525715","https://openalex.org/W3010277541","https://openalex.org/W3035454331","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3092820619","https://openalex.org/W3094172275","https://openalex.org/W3141117710","https://openalex.org/W3155230099","https://openalex.org/W3175888430","https://openalex.org/W4224952037","https://openalex.org/W4281930370","https://openalex.org/W4285606316","https://openalex.org/W4297630623","https://openalex.org/W4304080167","https://openalex.org/W4312761738","https://openalex.org/W4312810897","https://openalex.org/W4386065863","https://openalex.org/W4386071498","https://openalex.org/W4386071757","https://openalex.org/W4386322479","https://openalex.org/W4387968136","https://openalex.org/W4393154020","https://openalex.org/W6810427100"],"related_works":["https://openalex.org/W2384918310","https://openalex.org/W2383808867","https://openalex.org/W2372581239","https://openalex.org/W2107893065","https://openalex.org/W2617958085","https://openalex.org/W1509862229","https://openalex.org/W1974208548","https://openalex.org/W2050706403","https://openalex.org/W1973922169","https://openalex.org/W1519745258"],"abstract_inverted_index":{"Many":[0],"contrastive":[1],"learning":[2],"based":[3,101],"models":[4,17,44],"have":[5],"achieved":[6],"advanced":[7],"performance":[8],"in":[9,19,32,92],"image-text":[10,24],"matching":[11],"tasks.":[12],"The":[13,108],"key":[14],"of":[15,30,38,87,104,111,123,126,162],"these":[16],"lies":[18],"analyzing":[20],"the":[21,36,75,84,97,121,127,143,160],"correlation":[22,98,132],"between":[23],"pairs,":[25],"which":[26],"involves":[27],"cross-modal":[28],"interaction":[29],"embeddings":[31,37,57,88],"corresponding":[33,93],"dimensions.":[34],"However,":[35],"different":[39,43,90],"modalities":[40,91],"are":[41,117],"from":[42,78,89],"or":[45],"modules,":[46],"and":[47,60,113,150,170],"there":[48],"is":[49,100,134],"a":[50,68,130],"significant":[51,148],"modality":[52,76],"gap.":[53],"Directly":[54],"interacting":[55],"such":[56],"lacks":[58],"rationality":[59],"may":[61],"capture":[62],"inaccurate":[63],"correlation.":[64,156],"Therefore,":[65],"we":[66],"propose":[67],"novel":[69],"method":[70],"called":[71],"DIAS":[72],"to":[73,95,119,136,145],"bridge":[74],"gap":[77],"two":[79],"aspects:":[80],"(1)":[81],"We":[82],"align":[83],"information":[85],"representation":[86],"dimension":[94],"ensure":[96,120],"calculation":[99],"on":[102,168],"interactions":[103],"similar":[105],"information.":[106],"(2)":[107],"spatial":[109,140],"constraints":[110],"inter-":[112],"intra-modalities":[114],"unmatched":[115],"pairs":[116],"introduced":[118],"effectiveness":[122],"semantic":[124],"alignment":[125],"model.":[128],"Besides,":[129],"sparse":[131],"algorithm":[133],"proposed":[135],"select":[137],"strong":[138],"correlated":[139],"relationships,":[141],"enabling":[142],"model":[144],"learn":[146],"more":[147],"features":[149],"avoid":[151],"being":[152],"misled":[153],"by":[154],"weak":[155],"Extensive":[157],"experiments":[158],"demonstrate":[159],"superiority":[161],"DIAS,":[163],"achieving":[164],"4.3%-10.2%":[165],"rSum":[166],"improvements":[167],"Flickr30k":[169],"MSCOCO":[171],"benchmarks.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}