{"id":"https://openalex.org/W7125897992","doi":"https://doi.org/10.1109/smc58881.2025.11342756","title":"MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval","display_name":"MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125897992","doi":"https://doi.org/10.1109/smc58881.2025.11342756"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342756","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/A5102987554","display_name":"Jeong\u2010Woo Park","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112184","display_name":"Center for Art Studies","ror":"https://ror.org/01zbb0s29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I4210112184"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jeong-Woo Park","raw_affiliation_strings":["Korea University,Department of Artificial Intelligenc,Seoul,Korea,02841"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligenc,Seoul,Korea,02841","institution_ids":["https://openalex.org/I4210112184"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108203384","display_name":"Seong-Whan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112184","display_name":"Center for Art Studies","ror":"https://ror.org/01zbb0s29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I4210112184"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Korea University,Department of Artificial Intelligenc,Seoul,Korea,02841"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligenc,Seoul,Korea,02841","institution_ids":["https://openalex.org/I4210112184"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102987554"],"corresponding_institution_ids":["https://openalex.org/I4210112184"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7258533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"984","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":0.953499972820282,"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":0.953499972820282,"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":0.023800000548362732,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.00930000003427267,"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/focus","display_name":"Focus (optics)","score":0.6021999716758728},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5575000047683716},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5450000166893005},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46560001373291016},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.4433000087738037},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4074999988079071},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.39980000257492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6665999889373779},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6021999716758728},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5575000047683716},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5400000214576721},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4433000087738037},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3813000023365021},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.30169999599456787},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25440001487731934},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2513999938964844},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342756","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":[{"score":0.49822622537612915,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1978060137","https://openalex.org/W1989165405","https://openalex.org/W2051320331","https://openalex.org/W2058652897","https://openalex.org/W2905544595","https://openalex.org/W3035104236","https://openalex.org/W3109340983","https://openalex.org/W3154902219","https://openalex.org/W3172514680","https://openalex.org/W3203247393","https://openalex.org/W4386071700","https://openalex.org/W4390873539","https://openalex.org/W4400530983","https://openalex.org/W4402727158","https://openalex.org/W4409382789","https://openalex.org/W4413146297","https://openalex.org/W4413147773"],"related_works":[],"abstract_inverted_index":{"Composed":[0],"Image":[1],"Retrieval":[2],"(CIR)":[3],"is":[4,146],"the":[5,83,88,93,118,137,159,175,181,185],"task":[6],"of":[7,20,184,200],"retrieving":[8],"a":[9,13,16,21,25,107],"target":[10],"image":[11,23,161],"from":[12,92],"gallery":[14],"using":[15],"composed":[17],"query":[18],"consisting":[19],"reference":[22,94,160,186],"and":[24,61,124,136,158,208],"modification":[26,135,177],"text.":[27],"Among":[28],"various":[29],"CIR":[30,110],"approaches,":[31],"training-free":[32,108,196],"zero-shot":[33,109],"methods":[34,67],"based":[35,68],"on":[36,69,78,134,206,212],"pre-trained":[37],"models":[38,73],"are":[39],"cost-effective":[40],"but":[41],"still":[42],"face":[43],"notable":[44],"limitations.":[45],"For":[46],"example,":[47],"sequential":[48],"VLM-LLM":[49],"pipelines":[50],"process":[51],"each":[52],"modality":[53],"independently,":[54],"which":[55],"often":[56,75],"results":[57,194],"in":[58,204,210],"information":[59,91],"loss":[60],"limits":[62],"cross-modal":[63],"interaction.":[64],"In":[65],"contrast,":[66],"multimodal":[70],"large":[71],"language":[72],"(MLLMs)":[74],"focus":[76],"exclusively":[77],"applying":[79],"changes":[80],"indicated":[81],"by":[82,172],"text,":[84],"without":[85],"fully":[86],"utilizing":[87],"contextual":[89,125],"visual":[90,126,182],"image.":[95,187],"To":[96],"address":[97],"these":[98,155],"issues,":[99],"we":[100,153],"propose":[101],"multi-faceted":[102,114],"Chain-of-Thought":[103,115],"with":[104,174],"re-ranking":[105],"(MCoT-RE),":[106],"framework.":[111],"MCoT-RE":[112,191],"utilizes":[113],"to":[116,120,148,162,202],"guide":[117],"MLLM":[119],"balance":[121],"explicit":[122],"modifications":[123],"cues,":[127],"generating":[128],"two":[129,156],"distinct":[130],"captions:":[131],"one":[132],"focused":[133],"other":[138],"integrating":[139],"comprehensive":[140],"visual-textual":[141],"context.":[142],"The":[143],"first":[144],"caption":[145],"used":[147],"filter":[149],"candidate":[150],"images.":[151],"Subsequently,":[152],"combine":[154],"captions":[157],"perform":[163],"multi-grained":[164],"re-ranking.":[165],"This":[166],"two-stage":[167],"approach":[168],"facilitates":[169],"precise":[170],"retrieval":[171],"aligning":[173],"textual":[176],"instructions":[178],"while":[179],"preserving":[180],"context":[183],"Through":[188],"extensive":[189],"experiments,":[190],"achieves":[192],"state-of-the-art":[193],"among":[195],"methods,":[197],"yielding":[198],"improvements":[199],"up":[201],"6.24%":[203],"Recall@10":[205],"FashionIQ":[207],"8.58%":[209],"Recall@1":[211],"CIRR.":[213]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-29T00:00:00"}