{"id":"https://openalex.org/W7117108071","doi":"https://doi.org/10.1145/3786606","title":"Cross-modal Representation Shift Refinement for Point-supervised Video Moment Retrieval","display_name":"Cross-modal Representation Shift Refinement for Point-supervised Video Moment Retrieval","publication_year":2025,"publication_date":"2025-12-24","ids":{"openalex":"https://openalex.org/W7117108071","doi":"https://doi.org/10.1145/3786606"},"language":"en","primary_location":{"id":"doi:10.1145/3786606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3786606","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-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/A5100366746","display_name":"Kun Wang","orcid":"https://orcid.org/0009-0008-4856-8806"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0008-4856-8806","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yupeng Hu","orcid":"https://orcid.org/0000-0002-5653-8286"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupeng Hu","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-5653-8286","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121185177","display_name":"Hao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0003-1026-4499","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiang Shao","orcid":"https://orcid.org/0009-0003-1789-0935"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Shao","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0003-1789-0935","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1177,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81131383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"44","issue":"3","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9803000092506409,"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":0.9803000092506409,"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":0.004699999932199717,"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":0.00430000014603138,"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/key","display_name":"Key (lock)","score":0.6161999702453613},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.592199981212616},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5803999900817871},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5526999831199646},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.48730000853538513},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4377000033855438},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4169999957084656},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4129999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9203000068664551},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6161999702453613},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.592199981212616},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5803999900817871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5683000087738037},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5526999831199646},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4975999891757965},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4596000015735626},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4169999957084656},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.32820001244544983},{"id":"https://openalex.org/C7044111","wikidata":"https://www.wikidata.org/wiki/Q15844891","display_name":"Temporal annotation","level":5,"score":0.31839999556541443},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C2985933255","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Text retrieval","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C2985727698","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Semantic annotation","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2655999958515167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3786606","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5847885608673096,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5509480633","display_name":null,"funder_award_id":"62276155 and 62576195","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2111078031","https://openalex.org/W2151834591","https://openalex.org/W2250539671","https://openalex.org/W2897628926","https://openalex.org/W2904119337","https://openalex.org/W2962869524","https://openalex.org/W2963524571","https://openalex.org/W3035339529","https://openalex.org/W3157181916","https://openalex.org/W3174026887","https://openalex.org/W3207886649","https://openalex.org/W4214582399","https://openalex.org/W4289639375","https://openalex.org/W4386453436","https://openalex.org/W4387461044","https://openalex.org/W4389921502","https://openalex.org/W4392207775","https://openalex.org/W4392910965","https://openalex.org/W4399087926","https://openalex.org/W4401544324","https://openalex.org/W4408325474","https://openalex.org/W4412394892"],"related_works":[],"abstract_inverted_index":{"Video":[0],"Moment":[1],"Retrieval":[2],"(VMR)":[3],"aims":[4],"to":[5,41,66,108,125,131],"retrieve":[6],"temporal":[7,110],"moments":[8],"in":[9],"videos":[10],"that":[11,137],"align":[12],"with":[13,74,93],"natural":[14],"language":[15],"queries,":[16],"a":[17,35,82,120],"task":[18],"requiring":[19],"cross-modal":[20,57],"reasoning":[21],"between":[22],"video":[23],"and":[24,71,89,112],"text.":[25],"Among":[26],"various":[27],"supervision":[28,54],"paradigms,":[29],"point-supervised":[30],"VMR":[31],"has":[32],"emerged":[33],"as":[34,106],"practical":[36],"solution,":[37],"leveraging":[38],"single-frame":[39],"annotations":[40],"significantly":[42],"reduce":[43],"annotation":[44,145],"costs":[45,146],"while":[46,143],"maintaining":[47],"competitive":[48],"retrieval":[49,141],"performance.":[50],"However,":[51],"this":[52],"sparse":[53],"approach":[55],"induces":[56],"representation":[58],"shift.":[59],"This":[60],"shift":[61],"complicates":[62],"the":[63],"model\u2019s":[64],"ability":[65],"accurately":[67],"capture":[68],"action":[69],"sequences":[70],"associate":[72],"text":[73],"visual":[75],"content.":[76],"To":[77],"tackle":[78],"this,":[79],"we":[80],"propose":[81],"novel":[83],"framework":[84],"called":[85],"pseuDo":[86],"fRame-based":[87],"tempOral":[88],"semaNtic":[90],"rEfinement":[91],"(DRONE)":[92],"two":[94],"key":[95],"modules:":[96],"(1)":[97],"Pseudo-Frame":[98],"Temporal":[99],"Alignment":[100],"(PTA),":[101],"which":[102,118],"embeds":[103],"textual":[104],"queries":[105],"pseudo-frames":[107],"enhance":[109],"coherence,":[111],"(2)":[113],"Curriculum-Guided":[114],"Semantic":[115],"Refinement":[116],"(CSR),":[117],"uses":[119],"progressive":[121],"contrastive":[122],"learning":[123],"strategy":[124],"refine":[126],"semantic":[127],"representations":[128],"from":[129],"easy":[130],"hard":[132],"cases.":[133],"Extensive":[134],"experiments":[135],"show":[136],"DRONE":[138],"achieves":[139],"effective":[140],"performance":[142],"keeping":[144],"low.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-12-24T00:00:00"}