{"id":"https://openalex.org/W2474538275","doi":null,"title":"ViCom: Benchmark and Methods for Video Comprehension.","display_name":"ViCom: Benchmark and Methods for Video Comprehension.","publication_year":2016,"publication_date":"2016-06-23","ids":{"openalex":"https://openalex.org/W2474538275","mag":"2474538275"},"language":"en","primary_location":{"id":"mag:2474538275","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1606.07373","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1606.07373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016319243","display_name":"Du Tran","orcid":"https://orcid.org/0000-0001-9673-7194","observed_orcids":["https://orcid.org/0000-0001-9673-7194"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du Tran","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9673-7194","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054437548","display_name":"Manohar Paluri","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manohar Paluri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082736347","display_name":"Lorenzo Torresani","orcid":"https://orcid.org/0000-0002-6924-7285","observed_orcids":["https://orcid.org/0000-0002-6924-7285"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lorenzo Torresani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9351000189781189,"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":0.9351000189781189,"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":0.039500001817941666,"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":0.018200000748038292,"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/video-understanding","display_name":"video understanding","score":0.996999979019165},{"id":"https://openalex.org/keywords/audio-description","display_name":"audio description","score":0.5929999947547913},{"id":"https://openalex.org/keywords/video-captioning","display_name":"video captioning","score":0.8799999952316284},{"id":"https://openalex.org/keywords/benchmark-design","display_name":"benchmark design","score":0.5690000057220459},{"id":"https://openalex.org/keywords/performance-indicators","display_name":"performance indicators","score":0.5299999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633387088775635},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7579593658447266},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7140002250671387},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6595451831817627},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.6211116313934326},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5508173704147339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5223425626754761},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5201545357704163},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4492453932762146},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42179974913597107},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37841513752937317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37421345710754395},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10441303253173828},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2474538275","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1606.07373","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2474538275","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1606.07373","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W1536680647","https://openalex.org/W1572567476","https://openalex.org/W1686810756","https://openalex.org/W1880262756","https://openalex.org/W1902237438","https://openalex.org/W1903029394","https://openalex.org/W1927052826","https://openalex.org/W1933349210","https://openalex.org/W2010399676","https://openalex.org/W2026418062","https://openalex.org/W2068611653","https://openalex.org/W2078238240","https://openalex.org/W2094116030","https://openalex.org/W2096733369","https://openalex.org/W2111078031","https://openalex.org/W2117539524","https://openalex.org/W2119799051","https://openalex.org/W2134670479","https://openalex.org/W2139501017","https://openalex.org/W2153579005","https://openalex.org/W2156303437","https://openalex.org/W2161612652","https://openalex.org/W2161969291","https://openalex.org/W2163605009","https://openalex.org/W2164290393","https://openalex.org/W2187089797","https://openalex.org/W2190067570","https://openalex.org/W2250384498","https://openalex.org/W2308045930","https://openalex.org/W2493916176","https://openalex.org/W2526286384","https://openalex.org/W2735159761","https://openalex.org/W2914699769","https://openalex.org/W2950726992","https://openalex.org/W3141200356"],"related_works":["https://openalex.org/W2681668958","https://openalex.org/W7151779066","https://openalex.org/W6891851223","https://openalex.org/W7147062200","https://openalex.org/W4417132154","https://openalex.org/W7083340253","https://openalex.org/W4402502234","https://openalex.org/W4409360981","https://openalex.org/W7213937304","https://openalex.org/W7221771890"],"abstract_inverted_index":{"While":[0],"there":[1],"is":[2,56,60,100],"overall":[3],"agreement":[4],"that":[5,196],"future":[6],"technology":[7],"for":[8,20,42,118,172,216],"organizing,":[9],"browsing":[10],"and":[11,39,104,190,206],"searching":[12],"videos":[13],"hinges":[14],"on":[15,33,200,213],"the":[16,34,65,81,92,112,217,225],"development":[17],"of":[18,24,51,83,94,123,187,211,219,224],"methods":[19],"high-level":[21],"semantic":[22,66,114],"understanding":[23,47,90,223],"video,":[25],"so":[26],"far":[27],"no":[28],"consensus":[29],"has":[30,76],"been":[31,77],"reached":[32],"best":[35],"way":[36],"to":[37,79,135,144,169],"train":[38],"assess":[40],"models":[41],"this":[43,71,119,145,173,188,214],"task.":[44,174],"Casting":[45],"video":[46,85,89,124,181,230],"as":[48,58,91,152],"a":[49,153,165,179,193,208,221],"form":[50],"action":[52],"or":[53,68,96],"event":[54],"categorization":[55],"problematic":[57],"it":[59],"not":[61],"fully":[62],"clear":[63],"what":[64],"classes":[67],"abstractions":[69],"in":[70],"domain":[72],"should":[73],"be.":[74],"Language":[75],"exploited":[78],"sidestep":[80],"problem":[82],"defining":[84],"categories,":[86],"by":[87,137,229],"formulating":[88],"task":[93,156],"captioning":[95],"description.":[97],"However,":[98],"language":[99],"highly":[101],"complex,":[102],"redundant":[103],"sometimes":[105],"ambiguous.":[106],"Many":[107],"different":[108],"captions":[109],"may":[110],"express":[111],"same":[113],"concept.":[115],"To":[116],"account":[117],"ambiguity,":[120],"quantitative":[121],"evaluation":[122],"description":[125],"requires":[126],"sophisticated":[127],"metrics,":[128],"whose":[129],"performance":[130,160,199],"scores":[131],"are":[132],"typically":[133],"hard":[134],"interpret":[136],"humans.":[138],"\r\nThis":[139],"paper":[140],"provides":[141],"four":[142],"contributions":[143],"problem.":[146],"First,":[147],"we":[148,163,176,191,204],"formulate":[149],"Video":[150],"Comprehension":[151],"new":[154,226],"well-defined":[155],"with":[157,184],"an":[158,185],"easy-to-interpret":[159],"measure.":[161],"Second,":[162],"describe":[164],"general":[166],"semi-automatic":[167],"procedure":[168,189],"create":[170],"benchmarks":[171],"Third,":[175],"publicly":[177],"release":[178],"large-scale":[180],"benchmark":[182,215],"created":[183],"implementation":[186],"include":[192],"human":[194,198],"study":[195],"assesses":[197],"our":[201],"dataset.":[202],"Finally,":[203],"propose":[205],"test":[207],"varied":[209],"collection":[210],"approaches":[212],"purpose":[218],"gaining":[220],"better":[222],"challenges":[227],"posed":[228],"comprehension.":[231]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-07-22T00:00:00"}