{"id":"https://openalex.org/W4304080717","doi":"https://doi.org/10.1145/3503161.3547782","title":"Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization","display_name":"Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080717","doi":"https://doi.org/10.1145/3503161.3547782"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547782","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547782","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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/A5078220957","display_name":"Daizong Liu","orcid":"https://orcid.org/0000-0001-8179-4508"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daizong Liu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059045087","display_name":"Wei Hu","orcid":"https://orcid.org/0000-0002-9860-0922"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Hu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4536","last_page":"4545"},"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":0.9973000288009644,"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":0.9933000206947327,"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/computer-science","display_name":"Computer science","score":0.783696174621582},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.7208200693130493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6420645713806152},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5900317430496216},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4736016094684601},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43558356165885925},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4164556860923767},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3531203269958496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12328159809112549}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.783696174621582},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.7208200693130493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6420645713806152},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5900317430496216},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4736016094684601},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43558356165885925},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4164556860923767},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3531203269958496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12328159809112549},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547782","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547782","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1536680647","https://openalex.org/W1905882502","https://openalex.org/W1927052826","https://openalex.org/W2111078031","https://openalex.org/W2247513039","https://openalex.org/W2250539671","https://openalex.org/W2337252826","https://openalex.org/W2489434015","https://openalex.org/W2520141964","https://openalex.org/W2620365397","https://openalex.org/W2740757571","https://openalex.org/W2799263800","https://openalex.org/W2890502146","https://openalex.org/W2894280539","https://openalex.org/W2948958195","https://openalex.org/W2962764817","https://openalex.org/W2962869524","https://openalex.org/W2963017553","https://openalex.org/W2963109634","https://openalex.org/W2963393391","https://openalex.org/W2963524571","https://openalex.org/W2963735856","https://openalex.org/W2963914122","https://openalex.org/W2963916161","https://openalex.org/W2964051675","https://openalex.org/W2964089981","https://openalex.org/W2964345792","https://openalex.org/W2970898753","https://openalex.org/W2997429269","https://openalex.org/W2997762001","https://openalex.org/W2998712570","https://openalex.org/W3025323587","https://openalex.org/W3034743747","https://openalex.org/W3035339529","https://openalex.org/W3035640828","https://openalex.org/W3092739351","https://openalex.org/W3098232790","https://openalex.org/W3101429639","https://openalex.org/W3173602377","https://openalex.org/W3174490084","https://openalex.org/W3175082063","https://openalex.org/W3176182290","https://openalex.org/W3180476551","https://openalex.org/W3200255008","https://openalex.org/W3200924860","https://openalex.org/W3211772574","https://openalex.org/W4221148502","https://openalex.org/W4221154629","https://openalex.org/W4221167018","https://openalex.org/W4304086137","https://openalex.org/W4365799947"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W1573812202","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,16,29,40,62,80,86,90,146,151,156,164,188,205],"problem":[4],"of":[5,54,64,129],"natural":[6],"language":[7],"video":[8,66,157],"localization":[9,57],"(NLVL).":[10],"Almost":[11],"all":[12],"existing":[13],"works":[14],"follow":[15],"\"only":[17],"look":[18],"once\"":[19],"framework":[20,123],"that":[21,46,199],"exploits":[22],"a":[23,116,120,130,135],"single":[24],"model":[25,91],"to":[26,71,84,145,204],"directly":[27],"capture":[28,93],"complex":[30],"cross-":[31],"and":[32,38,75,114,134,149,175,208],"self-modal":[33],"relations":[34],"among":[35],"video-query":[36],"pairs":[37],"retrieve":[39],"relevant":[41],"segment.":[42],"However,":[43],"we":[44,118],"argue":[45],"these":[47],"methods":[48,207],"have":[49],"overlooked":[50],"two":[51],"indispensable":[52],"characteristics":[53],"an":[55,168],"ideal":[56],"method:":[58],"1)":[59],"Frame-differentiable:":[60],"considering":[61],"imbalance":[63],"positive/negative":[65],"frames,":[67],"it":[68,178],"is":[69,202],"effective":[70],"highlight":[72],"positive":[73],"frames":[74,99,183],"weaken":[76],"negative":[77],"ones":[78],"during":[79],"localization.":[81],"2)":[82],"Boundary-precise:":[83],"predict":[85],"exact":[87],"segment":[88,170,212],"boundary,":[89],"should":[92],"more":[94,210],"fine-grained":[95],"differences":[96],"between":[97],"consecutive":[98],"since":[100],"their":[101],"variations":[102],"are":[103],"often":[104],"smooth.":[105],"To":[106],"this":[107,173],"end,":[108],"inspired":[109],"by":[110,179],"how":[111],"humans":[112],"perceive":[113],"localize":[115],"segment,":[117],"propose":[119],"two-step":[121],"human-like":[122],"called":[124],"Skimming-Locating-Perusing":[125],"(SLP).":[126],"SLP":[127,201],"consists":[128],"Skimming-and-Locating":[131],"(SL)":[132],"module":[133,142,166],"Bi-directional":[136],"Perusing":[137],"(BP)":[138],"module.":[139],"The":[140],"SL":[141],"first":[143],"refers":[144],"query":[147],"semantic":[148],"selects":[150],"best":[152],"matched":[153],"frame":[154,186],"from":[155],"while":[158],"filtering":[159],"out":[160],"irrelevant":[161],"frames.":[162],"Then,":[163],"BP":[165],"constructs":[167],"initial":[169],"based":[171],"on":[172,194],"frame,":[174],"dynamically":[176],"updates":[177],"exploring":[180],"its":[181],"adjacent":[182],"until":[184],"no":[185],"shares":[187],"same":[189],"activity":[190],"semantic.":[191],"Experimental":[192],"results":[193],"three":[195],"challenging":[196],"benchmarks":[197],"show":[198],"our":[200],"superior":[203],"state-of-the-art":[206],"localizes":[209],"precise":[211],"boundaries.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}