{"id":"https://openalex.org/W3033200006","doi":"https://doi.org/10.1145/3372278.3390697","title":"iCap: Interactive Image Captioning with Predictive Text","display_name":"iCap: Interactive Image Captioning with Predictive Text","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W3033200006","doi":"https://doi.org/10.1145/3372278.3390697","mag":"3033200006"},"language":"en","primary_location":{"id":"doi:10.1145/3372278.3390697","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","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/A5056858488","display_name":"Zhengxiong Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengxiong Jia","raw_affiliation_strings":["Renmin University of China &amp; Visionary Intelligence Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China &amp; Visionary Intelligence Ltd., Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060270456","display_name":"Xirong Li","orcid":"https://orcid.org/0000-0002-0220-8310"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xirong Li","raw_affiliation_strings":["Renmin University of China &amp; Visionary Intelligence Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China &amp; Visionary Intelligence Ltd., Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056858488"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.6839,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.71301338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"428","last_page":"435"},"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":0.9947999715805054,"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":0.9930999875068665,"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":0.9786241054534912},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8222579956054688},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5762162208557129},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5699416995048523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5212567448616028},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4972105324268341},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.479386568069458},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.4760570228099823},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4560413956642151},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3996764123439789},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35871124267578125},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32221829891204834}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9786241054534912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8222579956054688},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5762162208557129},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5699416995048523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5212567448616028},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4972105324268341},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.479386568069458},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.4760570228099823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4560413956642151},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3996764123439789},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35871124267578125},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32221829891204834},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3372278.3390697","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G8949684276","display_name":null,"funder_award_id":"61672523","funder_id":"https://openalex.org/F4320327720","funder_display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320327720","display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W2064675550","https://openalex.org/W2280837843","https://openalex.org/W2418300416","https://openalex.org/W2425121537","https://openalex.org/W2522306626","https://openalex.org/W2609825896","https://openalex.org/W2745461083","https://openalex.org/W2749708282","https://openalex.org/W2783493343","https://openalex.org/W2795276939","https://openalex.org/W2801271919","https://openalex.org/W2901988662","https://openalex.org/W2963084599","https://openalex.org/W2963091079","https://openalex.org/W2964532449","https://openalex.org/W2964596963","https://openalex.org/W2979394918","https://openalex.org/W2981582341","https://openalex.org/W2982151481","https://openalex.org/W2986670728","https://openalex.org/W3102566412","https://openalex.org/W4298212933"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,36,67,83],"study":[4],"a":[5,24,45,86,103],"brand":[6],"new":[7,95],"topic":[8],"of":[9,47,93,107,120],"interactive":[10,53,88],"image":[11,21,27,43,74,89],"captioning":[12,22,90],"with":[13,97],"human":[14],"in":[15,32,51],"the":[16,29,33,41,52,57,80,118],"loop.":[17],"Different":[18],"from":[19,102],"automated":[20,111],"where":[23],"given":[25],"test":[26,42],"is":[28],"sole":[30],"input":[31,101],"inference":[34],"stage,":[35],"have":[37],"access":[38],"to":[39,99],"both":[40,110],"and":[44,113],"sequence":[46],"(incomplete)":[48],"user-input":[49],"sentences":[50],"scenario.":[54],"We":[55],"formulate":[56],"problem":[58],"as":[59,79],"Visually":[60],"Conditioned":[61],"Sentence":[62],"Completion":[63],"(VCSC).":[64],"For":[65],"VCSC,":[66],"propose":[68],"ABD-Cap,":[69],"asynchronous":[70],"bidirectional":[71],"decoding":[72],"for":[73],"caption":[75],"completion.":[76],"With":[77],"ABD-Cap":[78],"core":[81],"module,":[82],"build":[84],"iCap,":[85],"web-based":[87],"system":[91],"capable":[92],"predicting":[94],"text":[96],"respect":[98],"live":[100],"user.":[104],"A":[105],"number":[106],"experiments":[108],"covering":[109],"evaluations":[112],"real":[114],"user":[115],"studies":[116],"show":[117],"viability":[119],"our":[121],"proposals.":[122]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
