{"id":"https://openalex.org/W2981519940","doi":"https://doi.org/10.1145/3343031.3350907","title":"Finding Images by Dialoguing with Image","display_name":"Finding Images by Dialoguing with Image","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981519940","doi":"https://doi.org/10.1145/3343031.3350907","mag":"2981519940"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3350907","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th 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/A5036565640","display_name":"Lejian Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lejian Ren","raw_affiliation_strings":["Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Science, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Beihang University & Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology, SIAT, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University & Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology, SIAT, CAS, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015343168","display_name":"Han Huang","orcid":"https://orcid.org/0000-0001-6876-4742"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Huang","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112539471","display_name":"Jizhong Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jizhong Han","raw_affiliation_strings":["Chinese Academy of Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Science, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381753","display_name":"Shuicheng Yan","orcid":"https://orcid.org/0000-0001-8906-3777"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["YITU Tech, Beijing, China"],"affiliations":[{"raw_affiliation_string":"YITU Tech, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100758169","display_name":"Bo Li","orcid":"https://orcid.org/0000-0001-5980-4861"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036565640"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11727685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1220","last_page":"1229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9952999949455261,"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":0.804802656173706},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6319230794906616},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5770878791809082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5726782083511353},{"id":"https://openalex.org/keywords/adjacency-matrix","display_name":"Adjacency matrix","score":0.5723579525947571},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5460278391838074},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.521552562713623},{"id":"https://openalex.org/keywords/adjacency-list","display_name":"Adjacency list","score":0.46506837010383606},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4641045331954956},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3964003622531891},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3587992191314697},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15408116579055786},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09182801842689514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804802656173706},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6319230794906616},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5770878791809082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5726782083511353},{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.5723579525947571},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5460278391838074},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.521552562713623},{"id":"https://openalex.org/C110484373","wikidata":"https://www.wikidata.org/wiki/Q264398","display_name":"Adjacency list","level":2,"score":0.46506837010383606},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4641045331954956},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3964003622531891},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3587992191314697},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15408116579055786},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09182801842689514},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3350907","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th 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":50,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W639708223","https://openalex.org/W1947481528","https://openalex.org/W1985697096","https://openalex.org/W2064675550","https://openalex.org/W2069870183","https://openalex.org/W2077069816","https://openalex.org/W2092399515","https://openalex.org/W2098411764","https://openalex.org/W2125560515","https://openalex.org/W2128532956","https://openalex.org/W2144211451","https://openalex.org/W2153579005","https://openalex.org/W2160254296","https://openalex.org/W2161969291","https://openalex.org/W2187089797","https://openalex.org/W2250378130","https://openalex.org/W2277195237","https://openalex.org/W2294130536","https://openalex.org/W2295537791","https://openalex.org/W2340690086","https://openalex.org/W2479423890","https://openalex.org/W2519887557","https://openalex.org/W2544587078","https://openalex.org/W2549139847","https://openalex.org/W2579549467","https://openalex.org/W2591644541","https://openalex.org/W2607855566","https://openalex.org/W2744926832","https://openalex.org/W2777602943","https://openalex.org/W2810482788","https://openalex.org/W2886970679","https://openalex.org/W2895842584","https://openalex.org/W2897182555","https://openalex.org/W2950898568","https://openalex.org/W2962706528","https://openalex.org/W2962785943","https://openalex.org/W2963131783","https://openalex.org/W2963150697","https://openalex.org/W2963314968","https://openalex.org/W2963351448","https://openalex.org/W2963389687","https://openalex.org/W2963449176","https://openalex.org/W2963534356","https://openalex.org/W2963536419","https://openalex.org/W2963588253","https://openalex.org/W2963649796","https://openalex.org/W2963858333","https://openalex.org/W2964199361","https://openalex.org/W3143107425"],"related_works":["https://openalex.org/W4213150077","https://openalex.org/W2369410163","https://openalex.org/W2059018062","https://openalex.org/W2604585036","https://openalex.org/W2078477160","https://openalex.org/W1989103179","https://openalex.org/W1991172810","https://openalex.org/W125803343","https://openalex.org/W2063218608","https://openalex.org/W2117632582"],"abstract_inverted_index":{"Image":[0],"retrieval":[1,27,37,53,148],"in":[2,142,153],"complicated":[3],"scene":[4,23,32,55,81,126,144,150],"is":[5,75,110],"a":[6,22,45,64,87],"challenging":[7],"task":[8],"that":[9,29,59],"requires":[10],"the":[11,31,41,67,79,95,104,125,133,139,154],"comprehensive":[12],"understanding":[13],"of":[14],"an":[15,51,61,100],"image.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20,49],"propose":[21],"graph":[24,33,56,127,145,151],"based":[25,146],"image":[26,36,52,62,68,147],"framework":[28],"combines":[30],"generation":[34,57,152],"with":[35],"and":[38,63,97,149],"fine":[39],"tuning":[40],"searching":[42],"results":[43],"via":[44],"dialogue":[46],"mechanism.":[47],"Specifically,":[48],"proposed":[50,136],"oriented":[54],"model":[58],"takes":[60],"text":[65,73],"describing":[66],"as":[69],"inputs.":[70],"The":[71],"additional":[72],"input":[74],"used":[76,112],"to":[77,92,113],"control":[78],"generated":[80],"graph.":[82],"It":[83],"provides":[84],"information":[85,115],"for":[86,118],"newly":[88],"introduced":[89],"attributes":[90,96],"head":[91],"better":[93],"predict":[94],"helps":[98],"constructing":[99],"adjacency":[101],"matrix":[102],"at":[103],"same":[105],"time.":[106],"Graph":[107],"Convolutional":[108],"Network":[109],"further":[111],"gather":[114],"among":[116],"nodes":[117],"precise":[119],"relation":[120],"estimation.":[121],"Moreover,":[122],"modification":[123],"on":[124],"can":[128],"be":[129],"done":[130],"by":[131],"changing":[132],"text.":[134],"Our":[135],"approach":[137],"achieves":[138],"state-of-the-art":[140],"performances":[141],"both":[143],"Visual":[155],"Genome":[156],"dataset.":[157]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}