{"id":"https://openalex.org/W4416017023","doi":"https://doi.org/10.1145/3746252.3761041","title":"OFIA: An Object-centric Fine-grained Alignment Enhancement for Video-Text Retrieval","display_name":"OFIA: An Object-centric Fine-grained Alignment Enhancement for Video-Text Retrieval","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416017023","doi":"https://doi.org/10.1145/3746252.3761041"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761041","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109759516","display_name":"Zhengqi Huang","orcid":"https://orcid.org/0009-0008-2346-2044"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Huang","raw_affiliation_strings":["Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0009-0008-2346-2044","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644288","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-5422-2678"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0001-5422-2678","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110513670","display_name":"Chuanyi Dong","orcid":"https://orcid.org/0000-0002-7694-7837"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Dong","raw_affiliation_strings":["Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-7694-7837","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mingxin Liu","orcid":"https://orcid.org/0009-0002-5699-7543"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxin Liu","raw_affiliation_strings":["Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0009-0002-5699-7543","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"980","last_page":"989"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.963699996471405,"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":0.963699996471405,"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/T11439","display_name":"Video Analysis and Summarization","score":0.018400000408291817,"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/T10028","display_name":"Topic Modeling","score":0.002899999963119626,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6802999973297119},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6642000079154968},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6599000096321106},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5925999879837036},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.54830002784729},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3700999915599823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950999736785889},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6802999973297119},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6599000096321106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6184999942779541},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5925999879837036},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.54830002784729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.359499990940094},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35850000381469727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3398999869823456},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761041","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","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":30,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2425121537","https://openalex.org/W2745461083","https://openalex.org/W2962964995","https://openalex.org/W2963017553","https://openalex.org/W2963037989","https://openalex.org/W3021397474","https://openalex.org/W3173859428","https://openalex.org/W3204588463","https://openalex.org/W3217102353","https://openalex.org/W4225414521","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4304092331","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312563428","https://openalex.org/W4312655527","https://openalex.org/W4312956471","https://openalex.org/W4312999114","https://openalex.org/W4313156423","https://openalex.org/W4313186260","https://openalex.org/W4382458743","https://openalex.org/W4385767942","https://openalex.org/W4386076265","https://openalex.org/W4386076424","https://openalex.org/W4386942867","https://openalex.org/W4390874575","https://openalex.org/W4390889802","https://openalex.org/W4402704596"],"related_works":[],"abstract_inverted_index":{"Text-video":[0],"alignment":[1,13,81,102,117],"is":[2],"crucial":[3],"for":[4,45,91],"text-video":[5],"retrieval.":[6,72],"Empirical":[7],"studies":[8],"have":[9],"suggested":[10],"that":[11],"coarse-grained":[12],"overlooks":[14],"the":[15,27,41,47,51,67,75,78,86,120,159,166,188],"rich":[16],"cross-modal":[17],"details":[18],"and":[19,104,125,164,182],"therefore":[20],"performs":[21],"worse":[22],"than":[23],"fine-grained":[24,42,80],"alignment.":[25,113],"In":[26],"current":[28],"transfer":[29],"learning":[30],"paradigm,":[31],"although":[32],"researchers":[33],"primarily":[34],"utilize":[35],"patch-level":[36],"or":[37],"frame-level":[38],"embedding":[39],"as":[40],"video":[43,136],"representation":[44],"alignment,":[46],"frame":[48,107,149],"embeddings":[49],"miss":[50],"informative":[52,156],"visual":[53],"information,":[54],"while":[55],"a":[56,99,105],"single":[57],"patch":[58],"only":[59],"captures":[60],"limited":[61],"local":[62,133],"details.":[63],"These":[64],"defects":[65,76],"hinder":[66],"potential":[68],"improvement":[69],"in":[70],"video-text":[71,112,170],"To":[73],"address":[74],"of":[77,98,161,168,187],"existing":[79],"approach,":[82],"this":[83],"paper":[84],"proposes":[85],"Object-centric":[87],"Fine-grained":[88],"Alignment":[89],"Enhancement":[90],"Video-Text":[92],"Retrieval,":[93],"namely":[94],"OFIA,":[95],"which":[96],"consists":[97],"text-guided":[100,115],"object-text":[101,116],"module":[103,109,118,151],"similarity-wise":[106,148],"aggregation":[108,150],"to":[110,123,144,155],"enhance":[111],"The":[114,147,172],"leverages":[119],"textual":[121],"descriptions":[122],"detect":[124],"extract":[126],"more":[127,131],"relevant":[128],"objects,":[129],"enabling":[130],"precise":[132],"similarities":[134],"within":[135],"frames.":[137],"However,":[138],"not":[139],"all":[140],"frames":[141],"contribute":[142],"equally":[143],"effective":[145],"alignments.":[146],"assigns":[152],"greater":[153],"importance":[154],"frames,":[157],"overcoming":[158],"challenge":[160],"insignificant":[162],"ones":[163],"optimizing":[165],"similarity":[167],"matched":[169],"pairs.":[171],"empirical":[173],"evaluation":[174],"on":[175],"benchmark":[176],"datasets":[177],"including":[178],"MSRVTT,":[179],"MSVD,":[180],"DiDeMo,":[181],"ActivityNet":[183],"demonstrate":[184],"state-of-the-art":[185],"performance":[186],"proposed":[189],"method.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}