{"id":"https://openalex.org/W2963201326","doi":"https://doi.org/10.1145/3126686.3126717","title":"Watch What You Just Said","display_name":"Watch What You Just Said","publication_year":2017,"publication_date":"2017-10-23","ids":{"openalex":"https://openalex.org/W2963201326","doi":"https://doi.org/10.1145/3126686.3126717","mag":"2963201326"},"language":"en","primary_location":{"id":"doi:10.1145/3126686.3126717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126686.3126717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the on Thematic Workshops of ACM Multimedia 2017","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/A5084879213","display_name":"Luowei Zhou","orcid":"https://orcid.org/0000-0003-1197-0101"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Luowei Zhou","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064805926","display_name":"Chenliang Xu","orcid":"https://orcid.org/0000-0002-2183-822X"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenliang Xu","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036212055","display_name":"Parker Koch","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parker Koch","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079301873","display_name":"Jason J. Corso","orcid":"https://orcid.org/0000-0001-6454-9594"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason J. Corso","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084879213"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":3.0948,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.95247402,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"305","last_page":"313"},"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":0.9901999831199646,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9876000285148621,"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":0.9819768667221069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8413492441177368},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5829430222511292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5801922082901001},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5756620764732361},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5664405822753906},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5609050393104553},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5345731377601624},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5306602716445923},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.49806785583496094},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32642996311187744}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9819768667221069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413492441177368},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5829430222511292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5801922082901001},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5756620764732361},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5664405822753906},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5609050393104553},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5345731377601624},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5306602716445923},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.49806785583496094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32642996311187744},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3126686.3126717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3126686.3126717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the on Thematic Workshops of ACM Multimedia 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W92662927","https://openalex.org/W1514535095","https://openalex.org/W1687846465","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2064675550","https://openalex.org/W2097903333","https://openalex.org/W2117539524","https://openalex.org/W2118615399","https://openalex.org/W2142900973","https://openalex.org/W2143449221","https://openalex.org/W2149172860","https://openalex.org/W2157331557","https://openalex.org/W2173180041","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2302086703","https://openalex.org/W2339652278","https://openalex.org/W2346425926","https://openalex.org/W2463955103","https://openalex.org/W2526273376","https://openalex.org/W2527200148","https://openalex.org/W2949888546","https://openalex.org/W2950178297","https://openalex.org/W2962706528","https://openalex.org/W2962835968","https://openalex.org/W2963758027","https://openalex.org/W2964018924","https://openalex.org/W2964308564","https://openalex.org/W4249502209"],"related_works":["https://openalex.org/W3151908889","https://openalex.org/W2952673322","https://openalex.org/W2871882974","https://openalex.org/W2971688299","https://openalex.org/W3020826863","https://openalex.org/W2996202528","https://openalex.org/W4366260926","https://openalex.org/W2973208549","https://openalex.org/W2945836425","https://openalex.org/W2986546511"],"abstract_inverted_index":{"Attention":[0],"mechanisms":[1],"have":[2],"attracted":[3],"considerable":[4],"interest":[5],"in":[6,30,106,136,147],"image":[7,31,57,66,93,148],"captioning":[8,32,80,127],"due":[9],"to":[10,53],"their":[11],"powerful":[12],"performance.":[13],"However,":[14],"existing":[15],"methods":[16,128],"use":[17,142],"only":[18],"visual":[19],"content":[20],"as":[21,133,135],"attention":[22,29,43,70,98,146],"and":[23,99],"whether":[24],"textual":[25],"context":[26],"can":[27],"improve":[28],"remains":[33],"unsolved.":[34],"To":[35,63],"explore":[36],"this":[37],"problem,":[38],"we":[39,72],"propose":[40],"a":[41],"novel":[42],"mechanism,":[44],"called":[45],"text-conditional":[46,97,145],"attention,":[47],"which":[48,139],"allows":[49,88],"the":[50,74,92,115,141],"caption":[51],"generator":[52],"focus":[54],"on":[55,114,129],"certain":[56],"features":[58,67],"given":[59],"previously":[60],"generated":[61],"text.":[62],"obtain":[64],"text-related":[65],"for":[68],"our":[69,123,144],"model,":[71],"adopt":[73],"guiding":[75],"Long":[76],"Short-Term":[77],"Memory":[78],"(gLSTM)":[79],"architecture":[81,105],"with":[82,102],"CNN":[83],"fine-tuning.":[84],"Our":[85],"proposed":[86],"method":[87,124],"joint":[89],"learning":[90],"of":[91,143],"embedding,":[94,96],"text":[95],"language":[100],"model":[101],"one":[103],"network":[104],"an":[107],"end-to-end":[108],"manner.":[109],"We":[110],"perform":[111],"extensive":[112],"experiments":[113],"MS-COCO":[116],"dataset.":[117],"The":[118],"experimental":[119],"results":[120],"show":[121],"that":[122],"outperforms":[125],"state-of-the-art":[126],"various":[130],"quantitative":[131],"metrics":[132],"well":[134],"human":[137],"evaluation,":[138],"supports":[140],"captioning.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}