{"id":"https://openalex.org/W4283361723","doi":"https://doi.org/10.1145/3512527.3531396","title":"Joint Modality Synergy and Spatio-temporal Cue Purification for Moment Localization","display_name":"Joint Modality Synergy and Spatio-temporal Cue Purification for Moment Localization","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283361723","doi":"https://doi.org/10.1145/3512527.3531396"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531396","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","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/A5103173665","display_name":"Xingyu Shen","orcid":"https://orcid.org/0000-0002-0248-5588"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Shen","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing, National University of Defense Technology,College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing, National University of Defense Technology,College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060251766","display_name":"Long Lan","orcid":"https://orcid.org/0000-0002-4238-8985"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Lan","raw_affiliation_strings":["Institute for Quantum Information and State Key Laboratory of High Performance Computing, National University of Defense Technology, College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Quantum Information and State Key Laboratory of High Performance Computing, National University of Defense Technology, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004941473","display_name":"Huibin Tan","orcid":"https://orcid.org/0000-0003-4060-8793"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huibin Tan","raw_affiliation_strings":["Institute for Quantum Information and State Key Laboratory of High Performance Computing, National University of Defense Technology, College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Quantum Information and State Key Laboratory of High Performance Computing, National University of Defense Technology, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368865","display_name":"Xiang Zhang","orcid":"https://orcid.org/0000-0002-5201-3802"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Zhang","raw_affiliation_strings":["Institute for Quantum Information and State Key Laboratory of High Performance Computing, National University of Defense Technology, College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Quantum Information and State Key Laboratory of High Performance Computing, National University of Defense Technology, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072150649","display_name":"Xurui Ma","orcid":"https://orcid.org/0009-0001-8459-9414"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xurui Ma","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing, National University of Defense Technology, College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing, National University of Defense Technology, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061811574","display_name":"Zhigang Luo","orcid":"https://orcid.org/0000-0002-7552-201X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Luo","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing, National University of Defense Technology, College of Computer, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing, National University of Defense Technology, College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"369","last_page":"379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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":0.9817000031471252,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8153311610221863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7599999904632568},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.592962384223938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5827658176422119},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5554140210151672},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5412293672561646},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4205652177333832},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2489977478981018}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8153311610221863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599999904632568},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.592962384223938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827658176422119},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5554140210151672},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5412293672561646},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4205652177333832},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2489977478981018},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512527.3531396","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3151452821","display_name":null,"funder_award_id":"61906210","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1942126453","https://openalex.org/W2798354744","https://openalex.org/W2890502146","https://openalex.org/W2897628926","https://openalex.org/W2951748488","https://openalex.org/W2963393391","https://openalex.org/W2963916161","https://openalex.org/W2970231061","https://openalex.org/W2979156252","https://openalex.org/W2997429269","https://openalex.org/W2997762001","https://openalex.org/W2998495542","https://openalex.org/W2998841681","https://openalex.org/W3034743747","https://openalex.org/W3104893896","https://openalex.org/W3120889656","https://openalex.org/W3155721152","https://openalex.org/W3175402857"],"related_works":["https://openalex.org/W4206669594","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W3111983280","https://openalex.org/W3164468573","https://openalex.org/W2035950535","https://openalex.org/W2351555819","https://openalex.org/W2372268542"],"abstract_inverted_index":{"Currently,":[0],"many":[1],"approaches":[2,177],"to":[3,40,84,99,151],"the":[4,64,86,106,156,175],"sentence":[5],"query":[6,19],"based":[7],"moment":[8],"location":[9],"(SQML)":[10],"task":[11],"emphasize":[12],"(inter-)modality":[13],"interaction":[14,35,53],"between":[15],"video":[16,66,144],"and":[17,50,58,117,148,167],"language":[18],"via":[20],"transformer-based":[21],"cross-attention":[22,115],"or":[23],"contrastive":[24],"learning.":[25,119],"However,":[26],"they":[27],"could":[28,36],"still":[29],"face":[30],"two":[31,88,158],"issues:":[32],"1)":[33],"modality":[34,41,47,52,74,94,102,108,123],"be":[37,127],"unexpectedly":[38],"friendly":[39],"specific":[42,48,103,124],"learning":[43],"that":[44],"merely":[45],"learns":[46],"patterns,":[49],"2)":[51],"easily":[54],"confuses":[55],"spatio-temporal":[56,77],"cues":[57,62,137],"ultimately":[59],"makes":[60],"time":[61,136],"in":[63,130,138],"original":[65,139],"ambiguous.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,141],"propose":[72],"a":[73,91,121,131,179],"synergy":[75,95],"with":[76,111],"cue":[78],"purification":[79],"method":[80],"(MS2P)":[81],"for":[82],"SQML":[83],"address":[85],"above":[87],"issues.":[89],"Particularly,":[90],"conceptually":[92],"simple":[93],"strategy":[96],"is":[97],"explored":[98],"keep":[100],"features":[101],"while":[104],"absorbing":[105],"other":[107],"complementary":[109],"information":[110],"both":[112],"carefully":[113],"designed":[114],"unit":[116],"non-contrastive":[118],"As":[120],"result,":[122],"semantics":[125],"can":[126],"calibrated":[128],"progressively":[129],"safer":[132],"way.":[133],"To":[134],"preserve":[135],"video,":[140],"further":[142],"purify":[143],"representation":[145],"into":[146],"spatial":[147],"temporal":[149],"parts":[150],"enhance":[152],"localization":[153],"resolution":[154],"by":[155,178],"proposed":[157],"light-weight":[159],"sentence-aware":[160],"filtering":[161],"operations.":[162],"Experiments":[163],"on":[164],"Charades-STA,":[165],"TACoS,":[166],"ActivityNet":[168],"Caption":[169],"datasets":[170],"show":[171],"our":[172],"model":[173],"outperforms":[174],"state-of-the-art":[176],"large":[180],"margin.":[181]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
