{"id":"https://openalex.org/W4415708737","doi":"https://doi.org/10.1109/icme59968.2025.11209794","title":"History Tracker: Retrieving Historical Image Embeddings for Efficient Fine-Grained Reasoning in Vision-Language Models","display_name":"History Tracker: Retrieving Historical Image Embeddings for Efficient Fine-Grained Reasoning in Vision-Language Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708737","doi":"https://doi.org/10.1109/icme59968.2025.11209794"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209794","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 Multimedia and Expo (ICME)","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/A5109676444","display_name":"Jiahua Bao","orcid":"https://orcid.org/0000-0003-0610-4321"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahua Bao","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101603499","display_name":"Siyao Cheng","orcid":"https://orcid.org/0000-0002-1263-9907"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyao Cheng","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113871275","display_name":"Jiaxing Du","orcid":"https://orcid.org/0009-0003-6451-0181"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxing Du","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046070604","display_name":"Ziqian Li","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqian Li","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103203226","display_name":"Changjiang He","orcid":"https://orcid.org/0000-0003-4447-1130"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjiang He","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100660576","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0002-9501-6894"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26600621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9793000221252441,"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":0.9793000221252441,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.003599999938160181,"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":0.0035000001080334187,"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/overfitting","display_name":"Overfitting","score":0.8440999984741211},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6309999823570251},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6226000189781189},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.42320001125335693},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3327000141143799},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.33149999380111694}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8440999984741211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015000224113464},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6309999823570251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6306999921798706},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6226000189781189},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41519999504089355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209794","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317323","display_name":"Key Research and Development Program of Heilongjiang","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2307512708","https://openalex.org/W2962858109","https://openalex.org/W4312651322","https://openalex.org/W4385100559","https://openalex.org/W4385571053","https://openalex.org/W4389665280","https://openalex.org/W4390873747","https://openalex.org/W4391021820","https://openalex.org/W4392172801","https://openalex.org/W4402726948","https://openalex.org/W4402727885","https://openalex.org/W4402979468","https://openalex.org/W4402981486","https://openalex.org/W4403081466","https://openalex.org/W4403939368","https://openalex.org/W4404356490","https://openalex.org/W4404781880"],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"effectively":[3],"align":[4],"images":[5],"and":[6,24,53,96,102,117,134,172,191],"text,":[7],"but":[8],"they":[9,40],"often":[10],"struggle":[11],"with":[12,50,56,154],"fine-grained":[13,74,124,130,173,188],"reasoning":[14,75,174],"tasks.":[15,175],"Fine-grained":[16],"training":[17],"also":[18,41],"typically":[19],"demand":[20],"substantial":[21],"GPU":[22],"memory":[23],"a":[25,67,129,185],"large":[26],"number":[27],"of":[28,85,114,180],"trainable":[29],"parameters.":[30],"While":[31],"existing":[32,165],"Parameter-Efficient":[33],"Fine-Tuning":[34],"(PEFT)":[35],"methods":[36,167],"address":[37],"these":[38,61,106],"challenges,":[39],"introduce":[42,128],"new":[43],"limitations,":[44,62],"such":[45],"as":[46],"compromising":[47],"generalization":[48],"performance":[49,76],"additional":[51],"parameters":[52],"causing":[54],"overfitting":[55],"partial":[57],"fine-tuning.":[58],"To":[59],"overcome":[60],"we":[63,127],"propose":[64],"History":[65,79,162],"Tracker,":[66],"novel":[68],"PEFT":[69],"method":[70,183],"designed":[71],"to":[72,122,132,147],"enhance":[73],"in":[77],"VLMs.":[78],"Tracker":[80,163],"leverages":[81],"the":[82,86,112,119,155],"stacked":[83],"architecture":[84],"image":[87,115],"encoder,":[88],"dividing":[89],"its":[90,152],"layers":[91],"into":[92,108],"shallow,":[93],"middle,":[94],"deep,":[95],"global":[97],"groups.":[98],"It":[99],"then":[100],"retrieves":[101],"compresses":[103],"embeddings":[104,116],"from":[105],"groups":[107],"compact":[109],"tokens,":[110],"reinforcing":[111],"distribution":[113],"allowing":[118],"text":[120,145],"decoder":[121],"capture":[123],"details.":[125],"Furthermore,":[126],"dataset":[131,138],"fine-tune":[133],"evaluate":[135],"models.":[136],"This":[137],"focuses":[139],"on":[140,151,168],"tasks":[141],"where":[142],"highly":[143],"similar":[144],"needs":[146],"be":[148],"ranked":[149],"based":[150],"alignment":[153],"given":[156],"image.":[157],"Experimental":[158],"results":[159],"demonstrate":[160],"that":[161],"outperforms":[164],"fine-tuning":[166,177],"both":[169],"general":[170],"benchmarks":[171],"By":[176],"only":[178],"7.03%":[179],"parameters,":[181],"our":[182],"strikes":[184],"balance":[186],"between":[187],"reasoning,":[189],"generalization,":[190],"efficiency.":[192]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-30T00:00:00"}