{"id":"https://openalex.org/W7125961551","doi":"https://doi.org/10.1109/smc58881.2025.11343715","title":"Object-Centric Transformer Framework for Fine-Grained Image-Text Retrieval with Global Consistency <sup>*</sup>","display_name":"Object-Centric Transformer Framework for Fine-Grained Image-Text Retrieval with Global Consistency <sup>*</sup>","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125961551","doi":"https://doi.org/10.1109/smc58881.2025.11343715"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5027713037","display_name":"Sitong Shen","orcid":"https://orcid.org/0009-0003-4841-8414"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sitong Shen","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059278532","display_name":"Mayire Ibrayim","orcid":"https://orcid.org/0000-0002-8766-0647"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mayire Ibrayim","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122551024","display_name":"Peichao Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peichao Jiang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027713037"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68809986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1940","last_page":"1945"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9697999954223633,"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":0.9697999954223633,"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":0.018300000578165054,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0024999999441206455,"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/transformer","display_name":"Transformer","score":0.558899998664856},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5228999853134155},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5134999752044678},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4754999876022339},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.45080000162124634},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.420199990272522},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.39399999380111694},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.3928000032901764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782999873161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5986999869346619},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.558899998664856},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5228999853134155},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.45080000162124634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.391400009393692},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3384999930858612},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33739998936653137},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27309998869895935},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":23,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2185175083","https://openalex.org/W2549139847","https://openalex.org/W2745461083","https://openalex.org/W2962964995","https://openalex.org/W2964120214","https://openalex.org/W2965848243","https://openalex.org/W2986755220","https://openalex.org/W2988823324","https://openalex.org/W3118694826","https://openalex.org/W3138516171","https://openalex.org/W3216553632","https://openalex.org/W4312761738","https://openalex.org/W4321607993","https://openalex.org/W4366241040","https://openalex.org/W4385245566","https://openalex.org/W4386071498","https://openalex.org/W4386453567","https://openalex.org/W4386766892","https://openalex.org/W4392902991","https://openalex.org/W4402715976","https://openalex.org/W4402980399"],"related_works":[],"abstract_inverted_index":{"Cross-modal":[0],"image-text":[1,34,45],"retrieval":[2,19,46],"enables":[3],"efficient":[4],"heterogeneous":[5],"modality":[6],"interaction":[7],"via":[8],"vision-language":[9],"semantic":[10],"alignment,":[11],"advancing":[12],"multimodal":[13],"intelligence":[14],"applications.":[15],"However,":[16],"traditional":[17],"cross-modal":[18,44,85],"methods":[20,112],"typically":[21],"rely":[22],"on":[23,105,117],"pre-trained":[24],"feature":[25,73,86],"extractors,":[26],"whose":[27],"performance":[28],"limitations":[29],"hinder":[30],"the":[31,99,110,118],"accuracy":[32],"of":[33],"retrieval.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"propose":[40],"an":[41],"end-to-end":[42],"Transformer-based":[43],"framework,":[47],"OCGC,":[48],"which":[49],"extracts":[50],"visual":[51,69],"and":[52,92],"textual":[53],"features":[54,70,91],"through":[55],"Transformer":[56],"models.":[57],"The":[58],"framework":[59],"employs":[60],"a":[61,77],"Global-Attentive":[62],"Slot":[63],"Fusion":[64],"module":[65,82],"to":[66,71,83],"aggregate":[67],"object-centric":[68],"address":[72],"redundancy,":[74],"combined":[75],"with":[76],"Global":[78],"Semantic":[79],"Consistency":[80],"Alignment":[81],"enhance":[84],"alignment":[87],"between":[88],"aggregated":[89],"image":[90],"text":[93],"embeddings.":[94],"Experimental":[95],"results":[96],"demonstrate":[97],"that":[98],"proposed":[100],"model":[101],"performs":[102],"exceptionally":[103],"well":[104],"two":[106],"benchmark":[107],"datasets,":[108],"outperforming":[109],"state-of-the-art":[111],"by":[113],"over":[114],"6%":[115],"Rsum":[116],"Flickr30K":[119],"dataset.":[120]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-29T00:00:00"}