{"id":"https://openalex.org/W4415428890","doi":"https://doi.org/10.3233/faia250884","title":"CCRC: A Change-Aware Captioning and Reasoning Chain for Image Change Captioning and Segmentation","display_name":"CCRC: A Change-Aware Captioning and Reasoning Chain for Image Change Captioning and Segmentation","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428890","doi":"https://doi.org/10.3233/faia250884"},"language":null,"primary_location":{"id":"doi:10.3233/faia250884","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250884","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250884","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111228016","display_name":"Jinhong Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhong Hu","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046880065","display_name":"Xiaoping Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoping Wang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102448431","display_name":"Shuyin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyin Huang","raw_affiliation_strings":["Guangxi Minzu University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Minzu University, China","institution_ids":["https://openalex.org/I145897649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089792276","display_name":"Guojin Zhong","orcid":"https://orcid.org/0000-0002-6054-3694"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojin Zhong","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034728007","display_name":"Kaitai Liu","orcid":"https://orcid.org/0000-0003-1757-5591"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaitai Liu","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100625354","display_name":"Kai L\u00fc","orcid":"https://orcid.org/0000-0002-6378-7002"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Lu","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.55675228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9757000207901001,"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":0.9635000228881836,"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/closed-captioning","display_name":"Closed captioning","score":0.97079998254776},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5110999941825867},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5013999938964844},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5001000165939331},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4925000071525574},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.459199994802475},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4106999933719635},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4041000008583069},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.4027000069618225}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.97079998254776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896000146865845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.620199978351593},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43650001287460327},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4097000062465668},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4041000008583069},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34790000319480896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.25619998574256897}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/faia250884","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250884","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2606.28724","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.28724","pdf_url":"https://arxiv.org/pdf/2606.28724","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2606.28724","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28724","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.3233/faia250884","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250884","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"and":[1,15,36,49,60,95,133,151],"localizing":[2],"subtle":[3],"changes":[4],"between":[5,92],"paired":[6],"images":[7],"is":[8,111,126,166],"critical":[9],"for":[10,141],"tasks":[11],"such":[12],"as":[13],"surveillance":[14],"image":[16],"editing.":[17],"However,":[18],"traditional":[19],"Image":[20,33],"Change":[21,34],"Captioning":[22,35,59],"(ICC)":[23],"methods":[24],"lack":[25],"spatial":[26,72,129],"grounding,":[27],"limiting":[28],"their":[29],"precision.":[30],"We":[31,145],"introduce":[32],"Segmentation":[37],"(ICCS),":[38],"a":[39,64,84,99,109,137],"new":[40],"multimodal":[41],"task":[42],"that":[43,67],"jointly":[44],"requires":[45],"structured":[46],"change":[47,81,110,153],"description":[48],"pixel-level":[50,157],"localization.":[51,144],"To":[52],"address":[53],"ICCS,":[54],"we":[55],"propose":[56],"the":[57,93,118,121],"Change-aware":[58,90,138],"Reasoning":[61],"Chain":[62],"(CCRC),":[63],"dual-chain":[65],"framework":[66],"decouples":[68],"semantic":[69],"reasoning":[70],"from":[71,131],"segmentation.":[73],"The":[74],"first":[75],"chain,":[76,123],"Chain-of-Change-Captioning":[77],"(CCC),":[78],"enhances":[79],"fine-grained":[80],"perception":[82],"via":[83],"visual":[85,94],"fusion":[86],"module\u2014based":[87],"on":[88,148],"Multi-Head":[89],"Attention\u2014inserted":[91],"language":[96],"components":[97],"of":[98],"Multimodal":[100],"Large":[101],"Language":[102],"Model":[103],"(MLLM).":[104],"CCC":[105,132],"also":[106],"determines":[107],"whether":[108],"segmentable.":[112],"If":[113],"not,":[114],"it":[115],"alone":[116],"generates":[117],"caption.":[119],"Otherwise,":[120],"second":[122],"Chain-of-Change-Segmenting":[124],"(CCS),":[125],"activated,":[127],"leveraging":[128],"priors":[130],"refining":[134],"masks":[135],"with":[136,156],"Token":[139],"Refiner":[140],"accurate":[142],"boundary":[143],"evaluate":[146],"CCRC":[147,161],"both":[149],"synthetic":[150],"real-world":[152],"detection":[154],"benchmarks":[155],"supervision.":[158],"Experiments":[159],"show":[160],"achieves":[162],"state-of-the-art":[163],"performance.":[164],"Code":[165],"available":[167],"at":[168],"https://github.com/user-jinhong/CCRC.":[169]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-24T00:00:00"}
