{"id":"https://openalex.org/W4399423184","doi":"https://doi.org/10.1145/3652583.3658113","title":"PTAN: Principal Token-aware Adjacent Network for Compositional Temporal Grounding","display_name":"PTAN: Principal Token-aware Adjacent Network for Compositional Temporal Grounding","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399423184","doi":"https://doi.org/10.1145/3652583.3658113"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658113","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658113","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658113","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhuoyuan Wei","orcid":"https://orcid.org/0009-0001-6480-3457"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhuoyuan Wei","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0001-6480-3457","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101786662","display_name":"Xun Jiang","orcid":"https://orcid.org/0000-0003-2209-651X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Jiang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-2209-651X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037117576","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0002-9318-0084"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9318-0084","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074492050","display_name":"Fumin Shen","orcid":"https://orcid.org/0000-0001-7303-3231"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fumin Shen","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-7303-3231","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5685-3123","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47927246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"618","last_page":"627"},"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":0.9998000264167786,"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":0.9947999715805054,"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":0.8449710607528687},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.693122148513794},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5871853232383728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5726273059844971},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5434693098068237},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4924057722091675},{"id":"https://openalex.org/keywords/principal","display_name":"Principal (computer security)","score":0.4828679859638214},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.46771353483200073},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4486105144023895},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4479241371154785},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4316316843032837},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4161233901977539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8449710607528687},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.693122148513794},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5871853232383728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5726273059844971},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5434693098068237},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4924057722091675},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.4828679859638214},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.46771353483200073},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4486105144023895},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4479241371154785},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4316316843032837},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4161233901977539},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658113","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658113","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658113","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658113","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658113","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G67721616","display_name":null,"funder_award_id":"62222203, 62072080, 62306065","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399423184.pdf","grobid_xml":"https://content.openalex.org/works/W4399423184.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W2143017621","https://openalex.org/W2250539671","https://openalex.org/W2328078142","https://openalex.org/W2561715562","https://openalex.org/W2786209943","https://openalex.org/W2896457183","https://openalex.org/W2963017553","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2972073579","https://openalex.org/W2972884859","https://openalex.org/W2978223337","https://openalex.org/W2996094825","https://openalex.org/W2996132992","https://openalex.org/W2997429269","https://openalex.org/W3021087975","https://openalex.org/W3034257141","https://openalex.org/W3034743747","https://openalex.org/W3035339529","https://openalex.org/W3088744711","https://openalex.org/W3102877762","https://openalex.org/W3104739822","https://openalex.org/W3105009590","https://openalex.org/W3135367836","https://openalex.org/W3135773387","https://openalex.org/W3136588637","https://openalex.org/W3145807616","https://openalex.org/W3174966920","https://openalex.org/W3176201273","https://openalex.org/W3180476551","https://openalex.org/W3187433838","https://openalex.org/W3199096350","https://openalex.org/W3207454933","https://openalex.org/W3211883455","https://openalex.org/W4200635486","https://openalex.org/W4224314500","https://openalex.org/W4304083155","https://openalex.org/W4312245888","https://openalex.org/W4312402470","https://openalex.org/W4317796337","https://openalex.org/W4386038408","https://openalex.org/W4386057806","https://openalex.org/W4386071847","https://openalex.org/W4386076703","https://openalex.org/W4386083089","https://openalex.org/W4387968586","https://openalex.org/W4387968696","https://openalex.org/W4387969779","https://openalex.org/W4393108955","https://openalex.org/W4393148792"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4281476908","https://openalex.org/W4304700937"],"abstract_inverted_index":{"Compositional":[0],"temporal":[1],"grounding":[2],"(CTG)":[3],"aims":[4],"to":[5,49,57,70,131],"localize":[6],"the":[7,23,59,71,82,128,157],"most":[8],"relevant":[9],"segment":[10],"from":[11,41,127],"an":[12],"untrimmed":[13],"video":[14,52,66,123],"based":[15],"on":[16,156,185],"a":[17,79,103,180],"given":[18],"natural":[19],"language":[20],"sentence,":[21],"and":[22,62,76,170,176,192],"test":[24],"samples":[25],"for":[26,85,152],"this":[27],"task":[28],"contain":[29,94],"novel":[30,95,104],"components":[31],"not":[32],"seen":[33],"in":[34,179,207],"training.":[35],"However,":[36],"existing":[37],"CTG":[38,201],"methods":[39,46],"suffer":[40],"two":[42,186],"shortcomings:":[43],"(1)":[44,117],"Most":[45],"adopt":[47],"transformers":[48],"model":[50],"global":[51],"information":[53],"only,":[54],"thus":[55],"failing":[56],"balance":[58],"long-range":[60],"perception":[61],"regional":[63,148],"representation":[64],"of":[65,73,114,150],"sequences;":[67],"(2)":[68,142],"Due":[69],"lack":[72],"aligning":[74],"videos":[75,151],"sentences":[77,93],"at":[78,214],"fine-grained":[80,166],"level,":[81],"model's":[83],"capacity":[84],"compositional":[86,208],"generalization":[87],"is":[88,212],"limited,":[89],"particularly":[90],"when":[91],"query":[92],"components.":[96],"To":[97],"address":[98],"these":[99],"problems,":[100],"we":[101],"propose":[102],"method":[105,198],"called":[106],"Principal":[107,118,161],"Token-aware":[108],"Adjacent":[109],"Network":[110],"(PTAN),":[111],"which":[112,146],"consists":[113],"three":[115],"parts:":[116],"Temporal":[119],"Token":[120],"Recomposition":[121],"combining":[122],"clip-level":[124],"features":[125,136],"obtained":[126],"transformer":[129],"backbone":[130],"capture":[132],"more":[133],"significant":[134],"local":[135],"while":[137],"retaining":[138],"enough":[139],"contextual":[140],"information.":[141],"Regional":[143],"Semantic-Aware":[144,162],"Learning,":[145],"exploits":[147],"representations":[149],"cross-modal":[153],"semantic":[154],"alignment":[155,167],"feature":[158],"space.":[159],"(3)":[160],"Learning":[163],"that":[164,195],"facilitates":[165],"between":[168],"visual":[169,175],"textual":[171,177],"by":[172],"sensing":[173],"principal":[174],"tokens":[178],"self-supervised":[181],"manner.":[182],"Extensive":[183],"experiments":[184],"widely":[187],"used":[188],"benchmarks":[189],"(i.e.,":[190],"Charades-CG":[191],"ActivityNet-CG)":[193],"show":[194],"our":[196],"PTAN":[197],"outperforms":[199],"recent":[200],"state-of-the-art":[202],"methods,":[203],"achieving":[204],"remarkable":[205],"improvements":[206],"generalization.":[209],"Our":[210],"code":[211],"available":[213],"https://github.com/rushzy/PTAN.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}