{"id":"https://openalex.org/W7160140871","doi":"https://doi.org/10.1016/j.neunet.2026.109063","title":"TDP-DETR: Temporal dynamics perception framework for video moment retrieval and highlight detection","display_name":"TDP-DETR: Temporal dynamics perception framework for video moment retrieval and highlight detection","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7160140871","doi":"https://doi.org/10.1016/j.neunet.2026.109063","pmid":"https://pubmed.ncbi.nlm.nih.gov/42102552"},"language":"en","primary_location":{"id":"doi:10.1016/j.neunet.2026.109063","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.109063","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neunet.2026.109063","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135104685","display_name":"Huilin An","orcid":null},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I49232843","display_name":"Changchun University","ror":"https://ror.org/02an57k10","country_code":"CN","type":"education","lineage":["https://openalex.org/I49232843"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huilin An","raw_affiliation_strings":["College of Software,Jilin University, Changchun, 130012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Software,Jilin University, Changchun, 130012, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I49232843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012016681","display_name":"Zefan Zhang","orcid":"https://orcid.org/0000-0001-5627-050X"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210108141","display_name":"Ministry of Education","ror":"https://ror.org/01hw7wf62","country_code":"IR","type":"government","lineage":["https://openalex.org/I4210108141"]}],"countries":["CN","IR"],"is_corresponding":false,"raw_author_name":"Zefan Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Ministry of Education, Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University, Changchun, 130012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Ministry of Education, Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University, Changchun, 130012, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4210108141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048628032","display_name":"Shijie Jiang","orcid":"https://orcid.org/0000-0002-2808-9559"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210108141","display_name":"Ministry of Education","ror":"https://ror.org/01hw7wf62","country_code":"IR","type":"government","lineage":["https://openalex.org/I4210108141"]}],"countries":["CN","IR"],"is_corresponding":false,"raw_author_name":"Shijie Jiang","raw_affiliation_strings":["College of Computer Science and Technology, Ministry of Education, Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University, Changchun, 130012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Ministry of Education, Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University, Changchun, 130012, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4210108141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123244901","display_name":"Kehua Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I49232843","display_name":"Changchun University","ror":"https://ror.org/02an57k10","country_code":"CN","type":"education","lineage":["https://openalex.org/I49232843"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kehua Zhu","raw_affiliation_strings":["College of Software,Jilin University, Changchun, 130012, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Software,Jilin University, Changchun, 130012, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I49232843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135220431","display_name":"Tian Bai","orcid":"https://orcid.org/0000-0001-8060-4725"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tian Bai","raw_affiliation_strings":["College of Computer Science and Technology, Ministry of Education, Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University, Changchun, 130012, China. Electronic address: baitian@jlu.edu.cn"],"raw_orcid":"https://orcid.org/0000-0001-8060-4725","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Ministry of Education, Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University, Changchun, 130012, China. Electronic address: baitian@jlu.edu.cn","institution_ids":["https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5135220431"],"corresponding_institution_ids":["https://openalex.org/I194450716"],"apc_list":{"value":3350,"currency":"USD","value_usd":3350},"apc_paid":{"value":3350,"currency":"USD","value_usd":3350},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.55979011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"202","issue":null,"first_page":"109063","last_page":"109063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.39320001006126404,"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/T11439","display_name":"Video Analysis and Summarization","score":0.39320001006126404,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.36489999294281006,"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":0.1388999968767166,"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/dynamics","display_name":"Dynamics (music)","score":0.654699981212616},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.5952000021934509},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4571000039577484},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39469999074935913},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2784000039100647},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.27379998564720154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7239999771118164},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.654699981212616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6521999835968018},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5952000021934509},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45730000734329224},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2578999996185303}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014796","descriptor_name":"Visual Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1016/j.neunet.2026.109063","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.109063","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},{"id":"pmid:42102552","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42102552","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural networks : the official journal of the International Neural Network Society","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1016/j.neunet.2026.109063","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.109063","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.42866450548171997,"display_name":"Reduced inequalities"}],"awards":[],"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":13,"referenced_works":["https://openalex.org/W2111078031","https://openalex.org/W3094550259","https://openalex.org/W3210314917","https://openalex.org/W4225547367","https://openalex.org/W4296262844","https://openalex.org/W4312941859","https://openalex.org/W4386766790","https://openalex.org/W4393150296","https://openalex.org/W4400810332","https://openalex.org/W4401567339","https://openalex.org/W7128543721","https://openalex.org/W7128765248","https://openalex.org/W7133237598"],"related_works":[],"abstract_inverted_index":{"Video":[0],"Moment":[1],"Retrieval":[2],"(VMR)":[3],"and":[4,14,29,52,92,119,154],"Highlight":[5],"Detection":[6],"(HD)":[7],"aim":[8],"to":[9,41,55,112,149],"localize":[10],"query-relevant":[11],"temporal":[12,22,84,90,93,96,107,124,130],"segments":[13],"evaluate":[15],"clip-level":[16],"saliency":[17],"within":[18],"untrimmed":[19],"videos.":[20],"Accurate":[21],"boundary":[23,56,127],"perception":[24,57,138],"is":[25],"essential":[26],"for":[27,104,126],"VMR":[28],"HD.":[30],"While":[31],"current":[32],"models":[33,82],"have":[34],"made":[35],"significant":[36],"progress,":[37],"they":[38],"still":[39],"struggle":[40],"achieve":[42],"precise":[43],"action":[44,83,105,114,135,143,151,159],"semantic":[45,62],"alignment":[46],"with":[47],"temporally":[48],"dynamic":[49,101],"video":[50],"content":[51],"are":[53],"prone":[54],"bias":[58],"when":[59],"action-related":[60],"visual":[61],"cues":[63],"experience":[64],"fluctuations":[65],"in":[66],"specific":[67],"frames.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72,98,132],"propose":[73],"a":[74,100,123],"Temporal":[75],"Dynamics":[76],"Perception":[77],"DEtection":[78],"TRansformer":[79],"(TDP-DETR)":[80],"that":[81,140,168],"dynamics":[85],"from":[86,116],"two":[87],"complementary":[88],"perspectives:":[89],"persistence":[91,115],"progression.":[94],"For":[95,129],"persistence,":[97],"introduce":[99],"masking":[102],"strategy":[103],"duration-aware":[106],"modeling,":[108],"enabling":[109],"the":[110,147],"model":[111,148],"infer":[113],"query":[117],"semantics":[118],"incorporate":[120],"it":[121],"as":[122],"prior":[125],"prediction.":[128],"progression,":[131],"design":[133],"an":[134],"state":[136,144],"difference":[137],"module":[139],"captures":[141],"frame-to-frame":[142],"variations,":[145],"allowing":[146],"perceive":[150],"progression":[152],"speed":[153],"thereby":[155],"improve":[156],"anticipation":[157],"of":[158],"boundaries.":[160],"Extensive":[161],"experiments":[162],"on":[163],"three":[164],"MR/HD":[165],"benchmarks":[166],"demonstrate":[167],"our":[169],"method":[170],"consistently":[171],"outperforms":[172],"existing":[173],"state-of-the-art":[174],"approaches.":[175],"Our":[176],"code":[177],"will":[178],"be":[179],"public":[180],"soon.":[181]},"counts_by_year":[],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2026-05-05T00:00:00"}
