{"id":"https://openalex.org/W4388189120","doi":"https://doi.org/10.1145/3581783.3611885","title":"Conversational Composed Retrieval with Iterative Sequence Refinement","display_name":"Conversational Composed Retrieval with Iterative Sequence Refinement","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388189120","doi":"https://doi.org/10.1145/3581783.3611885"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5101756276","display_name":"Wei Hao","orcid":"https://orcid.org/0000-0001-5094-8906"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Wei","raw_affiliation_strings":["Inst. of Comput. Tech., CAS & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5094-8906","affiliations":[{"raw_affiliation_string":"Inst. of Comput. Tech., CAS & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669242","display_name":"Shuhui Wang","orcid":"https://orcid.org/0000-0002-5931-0527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuhui Wang","raw_affiliation_strings":["Inst. of Comput. Tech., CAS, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5931-0527","affiliations":[{"raw_affiliation_string":"Inst. of Comput. Tech., CAS, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088046237","display_name":"Zhe Xue","orcid":"https://orcid.org/0000-0001-6123-0043"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Xue","raw_affiliation_strings":["BUPT, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6123-0043","affiliations":[{"raw_affiliation_string":"BUPT, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062618254","display_name":"Shengbo Chen","orcid":"https://orcid.org/0000-0002-9026-8128"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Chen","raw_affiliation_strings":["Henan University, Kaifeng, China"],"raw_orcid":"https://orcid.org/0000-0002-9026-8128","affiliations":[{"raw_affiliation_string":"Henan University, Kaifeng, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences & Inst. of Comput. Tech., CAS, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7542-296X","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & Inst. of Comput. Tech., CAS, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101756276"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.3532,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60456527,"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":"6390","last_page":"6399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9986000061035156,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.8576130270957947},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5762630105018616},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.5507369041442871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5458512902259827},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5454987287521362},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5340614914894104},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5282850861549377},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5132991671562195},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.48819833993911743},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4660519063472748},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3368721902370453},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33638155460357666},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3123188018798828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8576130270957947},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5762630105018616},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.5507369041442871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5458512902259827},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5454987287521362},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5340614914894104},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5282850861549377},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5132991671562195},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.48819833993911743},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4660519063472748},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3368721902370453},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33638155460357666},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3123188018798828},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2185175083","https://openalex.org/W2349436533","https://openalex.org/W2560674852","https://openalex.org/W2590822507","https://openalex.org/W2747329762","https://openalex.org/W2905544595","https://openalex.org/W3026458074","https://openalex.org/W3035579671","https://openalex.org/W3104152799","https://openalex.org/W3138516171","https://openalex.org/W3155833376","https://openalex.org/W3172514680","https://openalex.org/W3173909648","https://openalex.org/W3176909828","https://openalex.org/W6600594273"],"related_works":["https://openalex.org/W4230197055","https://openalex.org/W4296749040","https://openalex.org/W621808327","https://openalex.org/W644007644","https://openalex.org/W2497198634","https://openalex.org/W3012257603","https://openalex.org/W1586784764","https://openalex.org/W4292264782","https://openalex.org/W1559289099","https://openalex.org/W3016450995"],"abstract_inverted_index":{"Due":[0],"to":[1,15,19,44,118,161,180],"the":[2,20,46,55,75,84,90,98,115,120,123,129,134,138,141,146,149,153,163,174,183,190],"progress":[3],"of":[4,152,200],"large-scale":[5],"multimodal":[6,109,170],"model":[7,76,117,139],"pretraining,":[8],"existing":[9],"cross-modal":[10,85,164],"retrieval":[11,58,136,154,193],"techniques":[12],"is":[13,112],"accurate":[14],"align":[16],"text":[17,39],"description":[18],"target":[21,130],"image":[22,131],"when":[23],"they":[24],"show":[25],"close":[26],"and":[27,101,126,173],"clear":[28],"semantic":[29,159],"correspondence.":[30],"However,":[31],"in":[32,78,104,122,148],"real":[33],"situations,":[34],"users":[35],"only":[36],"provide":[37],"ambiguous":[38],"queries,":[40],"making":[41],"it":[42],"difficult":[43],"retrieve":[45],"desired":[47],"images.":[48],"To":[49,82],"address":[50],"this":[51],"issue,":[52],"we":[53,88],"introduce":[54],"conversational":[56,62,86,135],"composed":[57],"paradigm,":[59,137],"inspired":[60],"by":[61],"search":[63],"which":[64,111],"models":[65],"complex":[66],"user":[67],"intent":[68],"through":[69],"iterative":[70,191],"interaction.":[71],"This":[72],"paradigm":[73],"enhances":[74],"capacity":[77],"learning":[79],"fine-grained":[80,158],"correspondences.":[81],"train":[83],"retrieval,":[87],"propose":[89,167],"Iterative":[91],"Refining":[92],"Retrieval":[93],"(IRR)":[94],"framework.":[95],"It":[96],"formalizes":[97],"reference":[99],"images":[100],"modification":[102],"texts":[103],"each":[105],"session":[106,184],"as":[107],"a":[108,168],"sequence,":[110],"fed":[113],"into":[114],"generative":[116],"predict":[119],"information":[121],"sequence":[124,176],"autoregressively,":[125],"ultimately":[127],"predicting":[128],"feature.":[132],"In":[133],"refines":[140],"learned":[142],"correspondences":[143],"based":[144],"on":[145,198],"interaction":[147],"later":[150],"stage":[151],"session,":[155],"thus":[156],"captures":[157],"correspondence":[160],"enforce":[162],"representation.":[165],"We":[166],"domain-specific":[169],"pretraining":[171],"method":[172,179,194],"full":[175],"sampling":[177],"augmentation":[178],"fully":[181],"utilize":[182],"information.":[185],"Extensive":[186],"experiments":[187],"demonstrate":[188],"that":[189],"refining":[192],"achieves":[195],"state-of-the-art":[196],"performance":[197],"sessions":[199],"varying":[201],"lengths.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}