{"id":"https://openalex.org/W4402980167","doi":"https://doi.org/10.1109/icme57554.2024.10687973","title":"Exploring Iterative Refinement with Diffusion Models for Video Grounding","display_name":"Exploring Iterative Refinement with Diffusion Models for Video Grounding","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980167","doi":"https://doi.org/10.1109/icme57554.2024.10687973"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5102775568","display_name":"Xiao Liang","orcid":"https://orcid.org/0000-0002-4382-059X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiao Liang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034429048","display_name":"Tao Shi","orcid":"https://orcid.org/0000-0003-4725-2857"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Shi","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071972923","display_name":"Yaoyuan Liang","orcid":"https://orcid.org/0009-0002-6708-458X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoyuan Liang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055826027","display_name":"Te Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Te Tao","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110667772","display_name":"Shao-Luo Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shao-Luo Huang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102775568"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54288561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9513999819755554,"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":0.9513999819755554,"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":0.9199000000953674,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9114999771118164,"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/computer-science","display_name":"Computer science","score":0.7485573291778564},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5786641836166382},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3576367497444153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485573291778564},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5786641836166382},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3576367497444153},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2111078031","https://openalex.org/W2894280539","https://openalex.org/W2962766617","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2970898753","https://openalex.org/W2997429269","https://openalex.org/W3035640828","https://openalex.org/W3132753749","https://openalex.org/W3174490084","https://openalex.org/W4312544061","https://openalex.org/W4386083094","https://openalex.org/W4390873752","https://openalex.org/W6679045638","https://openalex.org/W6739901393","https://openalex.org/W6779823529","https://openalex.org/W6783713337"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Video":[0],"grounding":[1,68],"aims":[2],"to":[3,13,99,111,156],"localize":[4],"the":[5,22,34,43,75,88,100,113,117,128,136,143],"target":[6,35,76,101,114,129],"moment":[7],"in":[8,37,42,87,116],"an":[9],"untrimmed":[10],"video":[11,67],"corresponding":[12],"a":[14,26,38,46,59,70,104],"given":[15],"sentence":[16],"query.":[17],"Existing":[18],"methods":[19,159],"typically":[20],"select":[21],"best":[23],"prediction":[24,50],"from":[25,80,131],"set":[27],"of":[28,45],"predefined":[29],"proposals":[30],"or":[31],"directly":[32],"regress":[33],"span":[36,77,102,115,130],"single-shot":[39],"manner,":[40],"resulting":[41],"absence":[44],"systematical":[47],"and":[48,84,109,148,165],"well-crafted":[49],"refinement":[51],"process.":[52,91,120],"In":[53,121],"this":[54],"paper,":[55],"we":[56],"propose":[57],"DiffusionVG,":[58],"novel":[60],"framework":[61],"with":[62,103],"diffusion":[63,90,107,119,139],"models":[64],"that":[65],"formulates":[66],"as":[69],"conditional":[71],"generative":[72],"task,":[73],"where":[74],"is":[78],"generated":[79],"Gaussian":[81,132],"noise":[82,98,133],"inputs":[83,134],"iteratively":[85],"refined":[86],"reverse":[89,118,138],"During":[92],"training,":[93],"Diffusion":[94,123],"VG":[95,124],"progressively":[96],"adds":[97],"fixed":[105],"forward":[106],"process":[108,140],"learns":[110],"recover":[112],"inference,":[122],"can":[125],"effectively":[126],"generate":[127],"by":[135],"learned":[137],"conditioned":[141],"on":[142,160],"video-sentence":[144],"representations.":[145],"Without":[146],"bells":[147],"whistles,":[149],"our":[150],"DiffusionVG":[151],"demonstrates":[152],"superior":[153],"performance":[154],"compared":[155],"existing":[157],"state-of-the-art":[158],"mainstream":[161],"Charades-STA,":[162],"ActivityNet":[163],"Captions,":[164],"TACoS":[166],"benchmarks.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}