{"id":"https://openalex.org/W4403780601","doi":"https://doi.org/10.1145/3664647.3681453","title":"Differential-Perceptive and Retrieval-Augmented MLLM for Change Captioning","display_name":"Differential-Perceptive and Retrieval-Augmented MLLM for Change Captioning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780601","doi":"https://doi.org/10.1145/3664647.3681453"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681453","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681453","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/A5100678097","display_name":"Xian Zhang","orcid":"https://orcid.org/0009-0009-0279-7934"},"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":true,"raw_author_name":"Xian Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030366151","display_name":"Haokun Wen","orcid":"https://orcid.org/0000-0003-0633-3722"},"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":"Haokun Wen","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654190","display_name":"Jianlong Wu","orcid":"https://orcid.org/0000-0003-0247-5221"},"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":"Jianlong Wu","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034095320","display_name":"Pengda Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengda Qin","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337747","display_name":"Hui Xue","orcid":"https://orcid.org/0000-0002-2093-2839"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Xue'","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"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":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100678097"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.7747,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73739173,"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":"4148","last_page":"4157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9805999994277954,"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/T12031","display_name":"Speech and dialogue systems","score":0.9781000018119812,"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/closed-captioning","display_name":"Closed captioning","score":0.9483363628387451},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7745572328567505},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5256313681602478},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.5030972361564636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4124978184700012},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12230291962623596},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05083784461021423}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9483363628387451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7745572328567505},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5256313681602478},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.5030972361564636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4124978184700012},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12230291962623596},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05083784461021423},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681453","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681453","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2506483933","https://openalex.org/W2949554687","https://openalex.org/W2964196083","https://openalex.org/W2988981892","https://openalex.org/W3108170342","https://openalex.org/W3159583533","https://openalex.org/W3175933895","https://openalex.org/W3176470992","https://openalex.org/W3176689360","https://openalex.org/W3203526456","https://openalex.org/W4205844428","https://openalex.org/W4213455776","https://openalex.org/W4225739172","https://openalex.org/W4321608137","https://openalex.org/W4362013208","https://openalex.org/W4362598957","https://openalex.org/W4366996284","https://openalex.org/W4386076004","https://openalex.org/W4386076127","https://openalex.org/W4386076522","https://openalex.org/W4386501573","https://openalex.org/W4387969743","https://openalex.org/W4388187563","https://openalex.org/W4389104748","https://openalex.org/W4390871964"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403"],"abstract_inverted_index":{"Change":[0],"captioning":[1],"involves":[2],"describing":[3],"the":[4,22,44,89,106,112,121,143,149,154,176],"subtle":[5,48,126],"changes":[6],"between":[7,50],"a":[8,64],"pair":[9],"of":[10,24,91,178],"similar":[11],"images.":[12],"Although":[13],"existing":[14],"efforts":[15],"have":[16],"achieved":[17],"compelling":[18],"success,":[19],"they":[20],"overlook":[21],"potential":[23],"multimodal":[25],"large":[26],"language":[27],"models":[28],"(MLLMs)":[29],"in":[30,57,159],"tackling":[31],"this":[32,36,72],"challenging":[33],"task.":[34,73],"In":[35,74],"work,":[37],"we":[38,62,141],"aim":[39],"to":[40,46,83,146,152],"empower":[41],"MLLMs":[42],"with":[43],"capability":[45],"perceive":[47],"differences":[49],"paired":[51],"images":[52,137],"and":[53,111,132,173],"enhance":[54],"their":[55],"performance":[56],"generating":[58,160],"change":[59,162],"captions.":[60,163],"Specifically,":[61],"present":[63],"diFferentIal-perceptive":[65],"aNd":[66],"rEtRieval-augmented":[67],"MLLM":[68],"(FINER-MLLM)":[69],"tailored":[70],"for":[71],"particular,":[75],"FINER-MLLM":[76,102],"leverages":[77],"LoRA":[78],"fine-tuned":[79],"MLLM's":[80,97,155],"image":[81,85,93,131],"encoder":[82],"extract":[84,125],"patch":[86],"features,":[87],"enabling":[88],"capture":[90],"detailed":[92],"information.":[94],"Subsequently,":[95],"within":[96,129],"feature":[98,108,114],"extraction,":[99],"typically":[100],"Q-Former,":[101],"incorporates":[103],"dual":[104],"constraints:":[105],"intra-image":[107],"independence":[109],"constraint":[110],"inter-image":[113],"alignment":[115],"constraint.":[116],"These":[117],"constraints":[118],"ensure":[119],"that":[120,133],"features":[122,135],"can":[123],"comprehensively":[124],"visual":[127],"information":[128],"each":[130],"corresponding":[134],"across":[136],"align":[138],"effectively.":[139],"Last,":[140],"introduced":[142],"retrieval":[144],"augmentation":[145],"first":[147],"retrieve":[148],"relevant":[150],"corpus":[151],"facilitate":[153],"decoder":[156],"i.e.,":[157,170],"LLM,":[158],"accurate":[161],"Extensive":[164],"experiments":[165],"on":[166],"three":[167],"benchmark":[168],"datasets,":[169],"CLEVR-Change,":[171],"Spot-the-Diff,":[172],"Image-Editing-Request,":[174],"demonstrate":[175],"superiority":[177],"our":[179],"proposed":[180],"method.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}