{"id":"https://openalex.org/W2766520430","doi":"https://doi.org/10.1145/3123266.3123327","title":"Catching the Temporal Regions-of-Interest for Video Captioning","display_name":"Catching the Temporal Regions-of-Interest for Video Captioning","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2766520430","doi":"https://doi.org/10.1145/3123266.3123327","mag":"2766520430"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3123327","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th 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/A5070359048","display_name":"Ziwei Yang","orcid":"https://orcid.org/0000-0001-9846-840X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziwei Yang","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031819155","display_name":"Yahong Han","orcid":"https://orcid.org/0000-0003-2768-1398"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahong Han","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023289847","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0002-2391-5372"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"153"},"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":0.9976000189781189,"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":0.996399998664856,"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":0.9599126577377319},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8783385157585144},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7312295436859131},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5226224064826965},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5058212280273438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49387913942337036},{"id":"https://openalex.org/keywords/region-of-interest","display_name":"Region of interest","score":0.4916561245918274},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22099536657333374},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07743260264396667}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9599126577377319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8783385157585144},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7312295436859131},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5226224064826965},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5058212280273438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49387913942337036},{"id":"https://openalex.org/C19609008","wikidata":"https://www.wikidata.org/wiki/Q2138203","display_name":"Region of interest","level":2,"score":0.4916561245918274},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22099536657333374},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07743260264396667},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123266.3123327","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"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":40,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1572567476","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1687846465","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2066134726","https://openalex.org/W2080672747","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2130942839","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2152984213","https://openalex.org/W2164290393","https://openalex.org/W2410323755","https://openalex.org/W2523937091","https://openalex.org/W2524558894","https://openalex.org/W2526273376","https://openalex.org/W2526544345","https://openalex.org/W2527145521","https://openalex.org/W2544271936","https://openalex.org/W2550553598","https://openalex.org/W2557264465","https://openalex.org/W2559542432","https://openalex.org/W2753335008","https://openalex.org/W2953022248","https://openalex.org/W2963119563","https://openalex.org/W2963149042","https://openalex.org/W2963576560","https://openalex.org/W2963630207","https://openalex.org/W2963843052","https://openalex.org/W2964241990","https://openalex.org/W2964308564","https://openalex.org/W3098682680"],"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":{"As":[0],"a":[1,39,58,71],"crucial":[2],"challenge":[3],"for":[4,66,131],"video":[5,12,20,35,68,97,132],"understanding,":[6],"exploiting":[7],"the":[8,24,105,112,138,145,161,170],"spatial-temporal":[9],"structure":[10,82],"of":[11,34,83,96,102,163],"has":[13],"attracted":[14],"much":[15],"attention":[16,60,106],"recently,":[17],"especially":[18],"on":[19,30,46,134,173],"captioning.":[21],"Inspired":[22],"by":[23],"insight":[25],"that":[26,154],"people":[27],"always":[28,110],"focus":[29,45],"certain":[31],"interested":[32,123],"regions":[33,124],"content,":[36],"we":[37,56,115],"propose":[38],"novel":[40],"approach":[41,168],"which":[42,91],"will":[43,92],"automatically":[44],"regions-of-interest":[47,65,87,157],"and":[48,86,99,144,166,180],"catch":[49,111],"their":[50],"temporal":[51,81,156],"structures.":[52],"In":[53],"our":[54,129,167],"approach,":[55],"utilize":[57],"specific":[59],"model":[61,107],"to":[62,79,120,122],"adaptively":[63],"select":[64],"each":[67],"frame.":[69],"Then":[70],"Dual":[72],"Memory":[73],"Recurrent":[74],"Model":[75],"(DMRM)":[76],"is":[77],"introduced":[78],"incorporate":[80],"global":[84],"features":[85,88],"in":[89],"parallel,":[90],"obtain":[93],"rough":[94],"understanding":[95],"content":[98],"particular":[100],"information":[101,158],"regions-of-interest.":[103],"Since":[104],"could":[108],"not":[109],"right":[113],"interests,":[114],"additionally":[116],"adopt":[117],"semantic":[118],"supervision":[119],"attend":[121],"more":[125],"correctly.":[126],"We":[127],"evaluate":[128],"method":[130],"captioning":[133],"two":[135],"public":[136],"benchmarks:":[137],"Microsoft":[139],"Video":[140,147],"Description":[141],"Corpus":[142],"(MSVD)":[143],"Montreal":[146],"Annotation":[148],"Dataset":[149],"(M-VAD).":[150],"The":[151],"experiments":[152],"demonstrate":[153],"catching":[155],"really":[159],"enhances":[160],"representation":[162],"input":[164],"videos":[165],"obtains":[169],"state-of-the-art":[171],"results":[172],"popular":[174],"evaluation":[175],"metrics":[176],"like":[177],"BLEU-4,":[178],"CIDEr,":[179],"METEOR.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}