{"id":"https://openalex.org/W4286358315","doi":"https://doi.org/10.1109/tmm.2022.3192729","title":"What Happens in Crowd Scenes: A New Dataset About Crowd Scenes for Image Captioning","display_name":"What Happens in Crowd Scenes: A New Dataset About Crowd Scenes for Image Captioning","publication_year":2022,"publication_date":"2022-07-20","ids":{"openalex":"https://openalex.org/W4286358315","doi":"https://doi.org/10.1109/tmm.2022.3192729"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3192729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3192729","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5067691968","display_name":"Lanxiao Wang","orcid":"https://orcid.org/0000-0002-3745-0262"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lanxiao Wang","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114378292","display_name":"Hongliang Li","orcid":"https://orcid.org/0000-0002-7481-095X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongliang Li","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076823429","display_name":"Wenzhe Hu","orcid":"https://orcid.org/0000-0002-7941-231X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhe Hu","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340794","display_name":"Xiaoliang Zhang","orcid":"https://orcid.org/0000-0001-9313-8428"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoliang Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066434602","display_name":"Heqian Qiu","orcid":"https://orcid.org/0000-0002-0963-0311"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heqian Qiu","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100617043","display_name":"Fanman Meng","orcid":"https://orcid.org/0000-0002-3016-2567"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanman Meng","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075737786","display_name":"Qingbo Wu","orcid":"https://orcid.org/0000-0003-2936-6340"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingbo Wu","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5067691968"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.917,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.75052246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"5400","last_page":"5412"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9980999827384949,"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":0.9911999702453613,"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/crowds","display_name":"Crowds","score":0.8879060745239258},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8842792510986328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8387709856033325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.556933581829071},{"id":"https://openalex.org/keywords/crowd-psychology","display_name":"Crowd psychology","score":0.4804506003856659},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4446066915988922},{"id":"https://openalex.org/keywords/crowd-simulation","display_name":"Crowd simulation","score":0.4345465898513794},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.42930179834365845},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41833949089050293},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37522321939468384},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3732304275035858},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36376428604125977},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13829612731933594},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1045106053352356}],"concepts":[{"id":"https://openalex.org/C2777852691","wikidata":"https://www.wikidata.org/wiki/Q13430821","display_name":"Crowds","level":2,"score":0.8879060745239258},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8842792510986328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8387709856033325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.556933581829071},{"id":"https://openalex.org/C44042526","wikidata":"https://www.wikidata.org/wiki/Q1355183","display_name":"Crowd psychology","level":2,"score":0.4804506003856659},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4446066915988922},{"id":"https://openalex.org/C45617602","wikidata":"https://www.wikidata.org/wiki/Q465266","display_name":"Crowd simulation","level":3,"score":0.4345465898513794},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.42930179834365845},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41833949089050293},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37522321939468384},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3732304275035858},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36376428604125977},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13829612731933594},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1045106053352356},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3192729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3192729","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/3"}],"awards":[{"id":"https://openalex.org/G3490299980","display_name":null,"funder_award_id":"61971095","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5032532683","display_name":null,"funder_award_id":"61831005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8361705632","display_name":null,"funder_award_id":"61871087","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1910776219","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2133459682","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2549599535","https://openalex.org/W2568262903","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2798542761","https://openalex.org/W2886641317","https://openalex.org/W2890531016","https://openalex.org/W2890718122","https://openalex.org/W2913618459","https://openalex.org/W2916798096","https://openalex.org/W2943885184","https://openalex.org/W2962954622","https://openalex.org/W2963062932","https://openalex.org/W2972897806","https://openalex.org/W2982553922","https://openalex.org/W2986670728","https://openalex.org/W2987327987","https://openalex.org/W3009270862","https://openalex.org/W3011692687","https://openalex.org/W3014352273","https://openalex.org/W3018388102","https://openalex.org/W3034399482","https://openalex.org/W3034638324","https://openalex.org/W3034655362","https://openalex.org/W3034984754","https://openalex.org/W3035284526","https://openalex.org/W3043370775","https://openalex.org/W3082231033","https://openalex.org/W3094673569","https://openalex.org/W3106859150","https://openalex.org/W3107492437","https://openalex.org/W3110700482","https://openalex.org/W3154362247","https://openalex.org/W3173961205","https://openalex.org/W3175108092","https://openalex.org/W3175126800","https://openalex.org/W3176694552","https://openalex.org/W3201782689","https://openalex.org/W3207460436","https://openalex.org/W6620707391","https://openalex.org/W6639432524","https://openalex.org/W6682631176","https://openalex.org/W6750697433"],"related_works":["https://openalex.org/W2189920449","https://openalex.org/W3096912411","https://openalex.org/W3043995842","https://openalex.org/W2077952221","https://openalex.org/W135395861","https://openalex.org/W2218711042","https://openalex.org/W2036586770","https://openalex.org/W2314427365","https://openalex.org/W172068003","https://openalex.org/W1970206276"],"abstract_inverted_index":{"Making":[0],"machines":[1],"endowed":[2],"with":[3],"eyes":[4],"and":[5,10,37,43,109,115,121,126,158,180],"brains":[6],"to":[7,23,68,78,87,138,167,199],"effectively":[8],"understand":[9],"analyze":[11],"crowd":[12,60,83,95,131,155,200],"scenes":[13,96,132,201],"is":[14,27,64,76],"of":[15,28,34,71,105,123,129],"paramount":[16],"importance":[17],"for":[18,31],"building":[19],"a":[20,46,94,145],"smart":[21],"city":[22],"serve":[24],"people.":[25],"This":[26],"far-reaching":[29],"significance":[30],"the":[32,69,103,124,127,130,185,191,203],"guidance":[33],"dense":[35],"crowds":[36],"accident":[38],"prevention,":[39],"such":[40],"as":[41,161],"crowding":[42],"stampedes.":[44],"As":[45],"typical":[47,113],"multimodal":[48,204],"scene":[49,61],"understanding":[50,62],"task,":[51],"image":[52],"captioning":[53,63],"has":[54,102],"always":[55],"attracted":[56],"widespread":[57],"attention.":[58],"However,":[59],"rarely":[65],"studied":[66],"due":[67],"unobtainability":[70],"related":[72,198],"datasets.":[73],"Therefore,":[74],"it":[75],"difficult":[77],"know":[79],"what":[80],"happens":[81],"in":[82,202],"scenes.":[84],"In":[85],"order":[86],"fill":[88],"this":[89,134],"research":[90],"gap,":[91],"we":[92,143],"propose":[93,144],"caption":[97,111],"dataset":[98,135,193],"named":[99],"CrowdCaption":[100,178,192],"which":[101],"advantages":[104],"crowd-topic":[106],"scenes,":[107],"comprehensive":[108],"complex":[110],"descriptions,":[112],"relationships":[114],"detailed":[116,170],"grounding":[117],"annotations.":[118],"The":[119],"complexity":[120],"diversity":[122],"descriptions":[125],"specificity":[128],"make":[133],"extremely":[136],"challenging":[137],"most":[139],"current":[140],"methods.":[141],"Thus,":[142],"Multi-hierarchical":[146],"Attribute":[147],"Guided":[148],"Crowd":[149],"Caption":[150],"Network":[151],"(MAGC)":[152],"based":[153],"on":[154,176],"objects,":[156],"actions,":[157],"status":[159],"(such":[160],"position,":[162],"dress,":[163],"posture,":[164],"etc.)":[165],"aiming":[166],"generate":[168],"crowd-specific":[169],"descriptions.":[171],"We":[172,189],"conduct":[173],"extensive":[174],"experiments":[175],"our":[177,181],"dataset,":[179],"proposed":[182],"method":[183],"reaches":[184],"state-of-the-art":[186],"(SoTA)":[187],"performance.":[188],"hope":[190],"can":[194],"assist":[195],"future":[196],"studies":[197],"domain.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}