{"id":"https://openalex.org/W2981646256","doi":"https://doi.org/10.1145/3343031.3350913","title":"MUCH","display_name":"MUCH","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981646256","doi":"https://doi.org/10.1145/3343031.3350913","mag":"2981646256"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3350913","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350913","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":"conference-paper","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/A5055504013","display_name":"Xinhang Song","orcid":"https://orcid.org/0000-0002-0895-1076"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhang Song","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685776","display_name":"Bohan Wang","orcid":"https://orcid.org/0000-0003-1439-1455"},"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":"Bohan Wang","raw_affiliation_strings":["Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007109976","display_name":"Gongwei Chen","orcid":"https://orcid.org/0000-0002-0634-6075"},"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":"Gongwei Chen","raw_affiliation_strings":["Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085719285","display_name":"Shuqiang Jiang","orcid":"https://orcid.org/0000-0002-1596-4326"},"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":"Shuqiang Jiang","raw_affiliation_strings":["Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"793","last_page":"801"},"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":0.9998000264167786,"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":0.9943000078201294,"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/closed-captioning","display_name":"Closed captioning","score":0.9665007591247559},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8588786125183105},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.684810996055603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6462038159370422},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5413517951965332},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5170298218727112},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4368937313556671},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3704128861427307},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.366031676530838},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3360012173652649},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3329468071460724}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9665007591247559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8588786125183105},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.684810996055603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6462038159370422},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5413517951965332},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5170298218727112},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4368937313556671},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3704128861427307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.366031676530838},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3360012173652649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3329468071460724},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3350913","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3350913","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1524680991","https://openalex.org/W1895577753","https://openalex.org/W1924160326","https://openalex.org/W1992718421","https://openalex.org/W2017814585","https://openalex.org/W2027668556","https://openalex.org/W2027922120","https://openalex.org/W2033832873","https://openalex.org/W2040999325","https://openalex.org/W2053229256","https://openalex.org/W2107034620","https://openalex.org/W2109586375","https://openalex.org/W2110628941","https://openalex.org/W2115628259","https://openalex.org/W2117539524","https://openalex.org/W2120750550","https://openalex.org/W2122528955","https://openalex.org/W2146022472","https://openalex.org/W2151103935","https://openalex.org/W2152161678","https://openalex.org/W2159328468","https://openalex.org/W2162915993","https://openalex.org/W2168616527","https://openalex.org/W2277195237","https://openalex.org/W2341629100","https://openalex.org/W2423822072","https://openalex.org/W2552002300","https://openalex.org/W2732026016","https://openalex.org/W2962706528","https://openalex.org/W3177525997","https://openalex.org/W4300283777"],"related_works":["https://openalex.org/W4320016117","https://openalex.org/W4307856881","https://openalex.org/W2547835662","https://openalex.org/W1987421842","https://openalex.org/W2291847203","https://openalex.org/W2944724518","https://openalex.org/W2043075591","https://openalex.org/W2161229648","https://openalex.org/W2993674027","https://openalex.org/W2130228941"],"abstract_inverted_index":{"Due":[0],"to":[1,106,124,144,153],"the":[2,43,62,83,87,126,158,179,182,186],"abstraction":[3],"of":[4,27,45,65,181],"scenes,":[5],"comprehensive":[6],"scene":[7,46,66,90,113,116,127,163,198],"understanding":[8],"requires":[9],"semantic":[10],"modeling":[11,44],"in":[12,104,130,151],"both":[13],"global":[14,25,154],"and":[15,48,68,92,95,112,134,137,161,203],"local":[16,36,93,152],"aspects.":[17],"Scene":[18],"recognition":[19,47,67],"is":[20,32,122,142],"usually":[21],"researched":[22],"from":[23,61],"a":[24,55,115,135],"point":[26],"view,":[28],"while":[29],"dense":[30,49,69,110],"captioning":[31,70,111],"typically":[33],"studied":[34],"for":[35,168],"regions.":[37],"Previous":[38],"works":[39,195],"separately":[40],"research":[41],"on":[42,148,175,196],"captioning.":[50],"In":[51],"contrast,":[52],"we":[53],"propose":[54],"joint":[56],"learning":[57],"framework":[58],"that":[59],"benefits":[60],"mutual":[63],"coupling":[64],"models.":[71,102],"Generally,":[72],"these":[73],"two":[74,79],"tasks":[75],"are":[76,165],"coupled":[77],"through":[78],"steps,":[80],"1)":[81],"fusing":[82],"supervision":[84],"by":[85],"considering":[86],"contexts":[88],"between":[89,109],"labels":[91,164],"captions,":[94],"2)":[96],"jointly":[97],"optimizing":[98],"semantically":[99],"symmetric":[100],"LSTM":[101],"Particularly,":[103],"order":[105],"balance":[107],"bias":[108],"recognition,":[114],"adaptive":[117],"non-maximum":[118],"suppression":[119],"(NMS)":[120],"method":[121,141,188],"proposed":[123,143,183,187],"emphasize":[125],"related":[128],"regions":[129,150],"region":[131],"proposal":[132],"procedure,":[133],"region-wise":[136],"category-wise":[138],"weighted":[139],"pooling":[140,155],"avoid":[145],"over":[146],"attention":[147],"particular":[149],"procedure.":[156],"For":[157],"model":[159],"training":[160],"evaluation,":[162],"manually":[166],"annotated":[167],"Visual":[169,176],"Genome":[170,177],"database.":[171],"The":[172],"experimental":[173],"results":[174],"show":[178],"effectiveness":[180],"method.":[184],"Moreover,":[185],"also":[189],"can":[190],"improve":[191],"previous":[192],"CNN":[193],"based":[194],"public":[197],"databases,":[199],"such":[200],"as":[201],"MIT67":[202],"SUN397.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2019-11-01T00:00:00"}