{"id":"https://openalex.org/W3083633269","doi":"https://doi.org/10.1109/access.2020.3021857","title":"Understanding Objects in Video: Object-Oriented Video Captioning via Structured Trajectory and Adversarial Learning","display_name":"Understanding Objects in Video: Object-Oriented Video Captioning via Structured Trajectory and Adversarial Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3083633269","doi":"https://doi.org/10.1109/access.2020.3021857","mag":"3083633269"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3021857","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3021857","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09186666.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09186666.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028293681","display_name":"Fangyi Zhu","orcid":"https://orcid.org/0000-0001-8072-4866"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyi Zhu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8072-4866","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101702810","display_name":"Jenq\u2013Neng Hwang","orcid":"https://orcid.org/0000-0002-8877-2421"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jenq-Neng Hwang","raw_affiliation_strings":["University of Washington, Seattle, USA"],"raw_orcid":"https://orcid.org/0000-0002-8877-2421","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039812471","display_name":"Zhanyu Ma","orcid":"https://orcid.org/0000-0003-2950-2488"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanyu Ma","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2950-2488","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658507","display_name":"Guang Chen","orcid":"https://orcid.org/0000-0002-1762-3648"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1762-3648","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445470","display_name":"Jun Guo","orcid":"https://orcid.org/0000-0001-9045-1339"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Guo","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9045-1339","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.9583,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.78008702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"169146","last_page":"169159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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":0.9936000108718872,"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":0.9169020652770996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8738542199134827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.647962212562561},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6215052008628845},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5776757001876831},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5684125423431396},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5623515844345093},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5560048222541809},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4641977548599243},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44878295063972473},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4411505162715912},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3587002754211426},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21177685260772705},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.07794034481048584}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9169020652770996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8738542199134827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.647962212562561},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6215052008628845},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5776757001876831},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5684125423431396},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5623515844345093},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5560048222541809},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4641977548599243},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44878295063972473},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4411505162715912},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3587002754211426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21177685260772705},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.07794034481048584},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3021857","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3021857","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09186666.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f27229505e5e4ead935efeb4c4ea6bfb","is_oa":true,"landing_page_url":"https://doaj.org/article/f27229505e5e4ead935efeb4c4ea6bfb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 169146-169159 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3021857","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3021857","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09186666.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3083633269.pdf","grobid_xml":"https://content.openalex.org/works/W3083633269.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1586939924","https://openalex.org/W1686810756","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2110933980","https://openalex.org/W2123301721","https://openalex.org/W2125389028","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2164290393","https://openalex.org/W2425121537","https://openalex.org/W2550553598","https://openalex.org/W2584992898","https://openalex.org/W2594785588","https://openalex.org/W2621571501","https://openalex.org/W2745461083","https://openalex.org/W2767073696","https://openalex.org/W2787241931","https://openalex.org/W2794022343","https://openalex.org/W2798793675","https://openalex.org/W2800791174","https://openalex.org/W2887712318","https://openalex.org/W2899879331","https://openalex.org/W2948358897","https://openalex.org/W2962681491","https://openalex.org/W2962793481","https://openalex.org/W2962808524","https://openalex.org/W2962934715","https://openalex.org/W2963073614","https://openalex.org/W2963107255","https://openalex.org/W2963150697","https://openalex.org/W2963446712","https://openalex.org/W2963576560","https://openalex.org/W2963616706","https://openalex.org/W2963630207","https://openalex.org/W2963758027","https://openalex.org/W2963767194","https://openalex.org/W2963916161","https://openalex.org/W2963942586","https://openalex.org/W2964018924","https://openalex.org/W2964024144","https://openalex.org/W2964241990","https://openalex.org/W2964350391","https://openalex.org/W2981648413","https://openalex.org/W4288083805","https://openalex.org/W4293584584","https://openalex.org/W4320013936","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6678262379","https://openalex.org/W6678815747","https://openalex.org/W6680145277","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6694260854","https://openalex.org/W6714414533","https://openalex.org/W6746282794","https://openalex.org/W6748692255","https://openalex.org/W6750227808"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Traditional":[0],"video":[1,64,90,104,271],"captioning":[2,65,105],"requests":[3],"a":[4,84],"holistic":[5],"description":[6],"of":[7,14,50,152,191,198,282],"the":[8,11,15,41,46,55,59,69,88,96,102,121,133,136,142,155,159,162,167,185,188,195,214,232,240,243,247,253,257,261,268,274,277,280,285],"video,":[9],"yet":[10],"detailed":[12],"descriptions":[13,33],"specific":[16],"objects":[17,30,287],"may":[18],"not":[19,75],"be":[20],"available.":[21],"Besides,":[22],"most":[23],"methods":[24,66],"adopt":[25],"frame-level":[26],"inter-tangled":[27],"features":[28,73,193,208],"among":[29,58,209],"and":[31,48,139,166,194,222,246,264,288],"ambiguous":[32],"during":[34],"training,":[35],"which":[36,92,213],"is":[37],"difficult":[38],"for":[39,270],"learning":[40,128,239],"vision-language":[42,143],"relationships.":[43],"Without":[44],"identifying":[45],"classes":[47],"locations":[49],"separate":[51],"objects,":[52,60,211],"neither":[53],"associating":[54],"transition":[56],"trajectories":[57],"these":[61],"data-driven":[62],"image-based":[63,180],"cannot":[67],"reason":[68,184],"activities":[70,134,186,290],"with":[71,109,212,267],"visual":[72,192,244,249],"only,":[74],"to":[76,112,130,183,205],"mention":[77],"performing":[78],"well":[79],"under":[80,145],"small-samples.":[81],"We":[82,100],"propose":[83],"novel":[85],"task,":[86,235],"namely":[87],"object-oriented":[89,103],"captioning,":[91],"focuses":[93],"on":[94,231,260],"understanding":[95],"videos":[97],"in":[98,291],"object-level.":[99],"re-annotate":[101],"dataset":[106,263],"(Object-Oriented":[107],"Captions)":[108],"object-sentence":[110],"pairs":[111],"facilitate":[113],"more":[114,220],"effective":[115],"cross-modal":[116],"learning.":[117],"Thereafter,":[118],"we":[119,236,255],"design":[120],"video-based":[122],"structured":[123,156,172],"trajectory":[124,157,173],"network":[125],"via":[126],"adversarial":[127,168,229],"(STraNet)":[129],"effectively":[131],"analyze":[132],"along":[135],"time":[137],"domain":[138],"proactively":[140],"capture":[141,206],"connections":[144],"small":[146],"datasets.":[147],"The":[148,170,201],"proposed":[149,258],"STraNet":[150,278],"consists":[151],"four":[153],"components:":[154],"representation,":[158],"attribute":[160,202],"explorer,":[161],"attribute-enhanced":[163],"caption":[164,216,233],"generator,":[165],"discriminator.":[169],"high-level":[171],"representation":[174],"provides":[175],"useful":[176],"supplement":[177],"over":[178],"previous":[179],"approaches,":[181],"allowing":[182],"from":[187],"temporal":[189],"evolution":[190],"dynamic":[196],"movement":[197],"spatial":[199],"locations.":[200],"explorer":[203],"helps":[204],"discriminative":[207],"different":[210],"subsequent":[215],"generator":[217],"can":[218,237],"generate":[219],"informative":[221],"accurate":[223],"descriptions.":[224],"Finally,":[225],"by":[226],"adding":[227],"an":[228],"discriminator":[230],"generation":[234],"improve":[238],"inter-relationships":[241],"between":[242],"contents":[245],"corresponding":[248],"words.":[250],"To":[251],"demonstrate":[252],"effectiveness,":[254],"evaluate":[256],"method":[259],"new":[262],"compare":[265],"it":[266],"state-of-the-arts":[269],"captioning.":[272],"From":[273],"experimental":[275],"results,":[276],"exhibits":[279],"ability":[281],"precisely":[283],"describing":[284],"concurrent":[286],"their":[289],"details.":[292]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}