{"id":"https://openalex.org/W4416252183","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229232","title":"Diff-DETR: Differential Attention Transformer for Video Moment Retrieval and Highlight Detection","display_name":"Diff-DETR: Differential Attention Transformer for Video Moment Retrieval and Highlight Detection","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252183","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229232"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5050831943","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-2234-2437"},"institutions":[{"id":"https://openalex.org/I12615008","display_name":"Beijing Normal University - Hong Kong Baptist University United International College","ror":"https://ror.org/04snvc712","country_code":"CN","type":"education","lineage":["https://openalex.org/I12615008"]},{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Beijing Normal-Hong Kong Baptist University,Department of Computer Science,Zhuhai,China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal-Hong Kong Baptist University,Department of Computer Science,Zhuhai,China","institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017371410","display_name":"Rui Meng","orcid":"https://orcid.org/0000-0001-5902-1787"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]},{"id":"https://openalex.org/I12615008","display_name":"Beijing Normal University - Hong Kong Baptist University United International College","ror":"https://ror.org/04snvc712","country_code":"CN","type":"education","lineage":["https://openalex.org/I12615008"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Rui Meng","raw_affiliation_strings":["Beijing Normal-Hong Kong Baptist University,Guangdong Provincial/Zhuhai Key Laboratory of IRADS,Zhuhai,China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal-Hong Kong Baptist University,Guangdong Provincial/Zhuhai Key Laboratory of IRADS,Zhuhai,China","institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016755046","display_name":"Bingqing Qu","orcid":"https://orcid.org/0000-0002-2000-5090"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]},{"id":"https://openalex.org/I12615008","display_name":"Beijing Normal University - Hong Kong Baptist University United International College","ror":"https://ror.org/04snvc712","country_code":"CN","type":"education","lineage":["https://openalex.org/I12615008"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Bingqing Qu","raw_affiliation_strings":["Beijing Normal-Hong Kong Baptist University,Department of Computer Science,Zhuhai,China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal-Hong Kong Baptist University,Department of Computer Science,Zhuhai,China","institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050831943"],"corresponding_institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34611674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.947700023651123,"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":0.947700023651123,"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":0.015300000086426735,"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":0.009700000286102295,"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/encoder","display_name":"Encoder","score":0.695900022983551},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6470999717712402},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41260001063346863},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.3903999924659729},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3714999854564667},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.32749998569488525},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.3070000112056732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519000172615051},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.695900022983551},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6470999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4846999943256378},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320955","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W329267344","https://openalex.org/W1924343884","https://openalex.org/W1958932515","https://openalex.org/W2111078031","https://openalex.org/W2337252826","https://openalex.org/W2512435841","https://openalex.org/W2776277180","https://openalex.org/W2798354744","https://openalex.org/W2890502146","https://openalex.org/W2891456603","https://openalex.org/W2897091983","https://openalex.org/W2919974746","https://openalex.org/W2963524571","https://openalex.org/W2963662190","https://openalex.org/W2963729528","https://openalex.org/W2963919999","https://openalex.org/W2964089981","https://openalex.org/W2990503944","https://openalex.org/W2997429269","https://openalex.org/W3104862079","https://openalex.org/W3106775073","https://openalex.org/W3109316002","https://openalex.org/W3132753749","https://openalex.org/W3175082063","https://openalex.org/W3196253003","https://openalex.org/W3201832684","https://openalex.org/W3202168743","https://openalex.org/W4206905560","https://openalex.org/W4312544061","https://openalex.org/W4386083094","https://openalex.org/W4390873341","https://openalex.org/W4390873423","https://openalex.org/W4393148542","https://openalex.org/W4402352082","https://openalex.org/W4402753830","https://openalex.org/W4403780538"],"related_works":[],"abstract_inverted_index":{"Video":[0],"Moment":[1],"Retrieval":[2],"(MR)":[3],"and":[4,26,33,53,88,147,160,165,172],"Highlight":[5],"Detection":[6],"(HD)":[7],"have":[8],"drawn":[9],"significant":[10],"attention":[11,57,86,105],"due":[12],"to":[13,45,56,84,101,120,150],"the":[14,108,122,126],"growing":[15],"demand":[16],"for":[17,93],"advanced":[18],"video":[19,66],"understanding.":[20,153],"Previous":[21],"approaches":[22],"predominantly":[23],"conceptualize":[24],"MR":[25,171],"HD":[27,173],"as":[28],"unified":[29],"video-text":[30],"alignment":[31,92],"tasks":[32],"employ":[34],"transformer-based":[35],"architectures":[36],"with":[37,134],"multimodal":[38,127,132],"interaction":[39],"modules.":[40],"However,":[41],"these":[42,75],"methods":[43],"struggle":[44],"capture":[46],"contextualized":[47],"semantic":[48,123,140,152],"associations":[49],"in":[50,69,170],"long":[51],"videos":[52],"are":[54],"prone":[55],"noise,":[58],"where":[59],"transformers":[60],"may":[61],"disproportionately":[62],"focus":[63],"on":[64,156],"irrelevant":[65,112],"segments,":[67],"resulting":[68],"suboptimal":[70],"localization":[71],"accuracy.":[72],"To":[73],"address":[74],"issues,":[76],"we":[77,129],"propose":[78],"Diff-DETR,":[79],"a":[80,103,131,135],"novel":[81],"framework":[82],"designed":[83],"mitigate":[85],"noise":[87],"enhance":[89,151],"cross-modal":[90],"feature":[91],"precise":[94],"localization.":[95],"The":[96],"core":[97],"of":[98],"Diff-DETR":[99],"is":[100],"incorporate":[102],"differential":[104],"mechanism":[106],"into":[107],"transformer":[109],"decoder,":[110],"suppressing":[111],"signals":[113],"while":[114],"emphasizing":[115],"contextually":[116],"relevant":[117],"cues.":[118],"Furthermore,":[119],"enrich":[121],"relationships":[124],"within":[125],"embeddings,":[128],"design":[130],"encoder":[133],"large":[136],"language":[137],"model":[138],"(LLM)-based":[139],"enhancement":[141],"module,":[142],"which":[143],"seamlessly":[144],"merges":[145],"visual":[146],"textual":[148],"features":[149],"Extensive":[154],"experiments":[155],"QVHighlights,":[157],"TACoS,":[158],"Charades-STA,":[159],"TVSum":[161],"demonstrate":[162],"Diff-DETR\u2019s":[163],"efficacy":[164],"practicality,":[166],"achieving":[167],"state-of-the-art":[168],"performance":[169],"tasks.":[174]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}