{"id":"https://openalex.org/W4402352082","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650814","title":"MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer","display_name":"MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352082","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650814"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5040712361","display_name":"Yifang Xu","orcid":"https://orcid.org/0009-0001-3738-789X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifang Xu","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021416936","display_name":"Yunzhuo Sun","orcid":"https://orcid.org/0009-0006-8122-7259"},"institutions":[{"id":"https://openalex.org/I4210165606","display_name":"Hubei Normal University","ror":"https://ror.org/056y3dw16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunzhuo Sun","raw_affiliation_strings":["Hubei Normal University,School of Physics and Electronics,China"],"affiliations":[{"raw_affiliation_string":"Hubei Normal University,School of Physics and Electronics,China","institution_ids":["https://openalex.org/I4210165606"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113373662","display_name":"Benxiang Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Benxiang Zhai","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111347031","display_name":"Youyao Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099297","display_name":"Jilian Technology Group (China)","ror":"https://ror.org/016q5ce10","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099297"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youyao Jia","raw_affiliation_strings":["Gosuncn Chuanglian Technology Co., Ltd.,China"],"affiliations":[{"raw_affiliation_string":"Gosuncn Chuanglian Technology Co., Ltd.,China","institution_ids":["https://openalex.org/I4210099297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046137144","display_name":"Sidan Du","orcid":"https://orcid.org/0000-0001-6432-3704"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sidan Du","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040712361"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":5.6828,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.97055089,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"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/T10531","display_name":"Advanced Vision and Imaging","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/T10531","display_name":"Advanced Vision and Imaging","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/modal","display_name":"Modal","score":0.6264324188232422},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5790610313415527},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5213931202888489},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1511070430278778},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14978402853012085},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1318196952342987},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12815803289413452}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6264324188232422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5790610313415527},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5213931202888489},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1511070430278778},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14978402853012085},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1318196952342987},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12815803289413452},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1924343884","https://openalex.org/W1927052826","https://openalex.org/W1958932515","https://openalex.org/W2250539671","https://openalex.org/W2337252826","https://openalex.org/W2512435841","https://openalex.org/W2619947201","https://openalex.org/W2896457183","https://openalex.org/W2904824998","https://openalex.org/W2908510526","https://openalex.org/W2919974746","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2966848258","https://openalex.org/W2990503944","https://openalex.org/W2991773160","https://openalex.org/W2997429269","https://openalex.org/W3034743747","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3104862079","https://openalex.org/W3106775073","https://openalex.org/W3133696297","https://openalex.org/W3168910151","https://openalex.org/W3178457761","https://openalex.org/W3196253003","https://openalex.org/W3199576129","https://openalex.org/W3200947677","https://openalex.org/W3201832684","https://openalex.org/W3210314917","https://openalex.org/W3211772574","https://openalex.org/W3213100861","https://openalex.org/W3214448253","https://openalex.org/W4205823555","https://openalex.org/W4221146106","https://openalex.org/W4287608901","https://openalex.org/W4292092982","https://openalex.org/W4312245888","https://openalex.org/W4312275869","https://openalex.org/W4312463400","https://openalex.org/W4312544061","https://openalex.org/W4312680331","https://openalex.org/W4312820606","https://openalex.org/W4327852044","https://openalex.org/W4376226279","https://openalex.org/W4385245566","https://openalex.org/W4389722225","https://openalex.org/W4392162962","https://openalex.org/W6637373629","https://openalex.org/W6640109428","https://openalex.org/W6757817989","https://openalex.org/W6767057606","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6785011006","https://openalex.org/W6790690058","https://openalex.org/W6791353385","https://openalex.org/W6798195429","https://openalex.org/W6804424445","https://openalex.org/W6809665764","https://openalex.org/W6841268915","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"With":[0],"the":[1,52,87,110],"increasing":[2],"demand":[3],"for":[4,75],"video":[5,7],"understanding,":[6],"moment":[8],"and":[9,26,56,70,112,117,126,139],"highlight":[10],"detection":[11],"(MHD)":[12],"has":[13],"emerged":[14],"as":[15],"a":[16,80,104],"critical":[17],"research":[18],"topic.":[19],"MHD":[20],"aims":[21],"to":[22,90,96],"localize":[23],"all":[24],"moments":[25],"predict":[27],"clip-wise":[28],"saliency":[29],"scores":[30],"simultaneously.":[31],"Despite":[32],"progress":[33],"made":[34],"by":[35],"existing":[36,133],"DETR-based":[37],"methods,":[38,135],"we":[39,66,78,102],"observe":[40],"that":[41,130],"these":[42],"methods":[43],"coarsely":[44],"fuse":[45],"features":[46],"from":[47],"different":[48],"modalities,":[49],"which":[50],"weakens":[51],"temporal":[53],"intra-modal":[54,93],"context":[55],"results":[57],"in":[58],"insufficient":[59],"cross-modal":[60,100,106],"interaction.":[61],"To":[62],"address":[63],"this":[64],"issue,":[65],"propose":[67],"MH-DETR":[68,131],"(Moment":[69],"Highlight":[71],"DEtection":[72],"TRansformer)":[73],"tailored":[74],"MHD.":[76],"Specifically,":[77],"introduce":[79],"simple":[81],"yet":[82],"efficient":[83],"pooling":[84],"operator":[85],"within":[86],"uni-modal":[88],"encoder":[89,111],"capture":[91],"global":[92],"context.":[94],"Moreover,":[95],"obtain":[97],"temporally":[98],"aligned":[99],"features,":[101],"design":[103],"plug-and-play":[105],"interaction":[107],"module":[108],"between":[109],"decoder,":[113],"seamlessly":[114],"integrating":[115],"visual":[116],"textual":[118],"features.":[119],"Comprehensive":[120],"experiments":[121],"on":[122],"QVHighlights,":[123],"Charades-STA,":[124],"Activity-Net,":[125],"TVSum":[127],"datasets":[128],"show":[129],"outperforms":[132],"state-of-the-art":[134],"demonstrating":[136],"its":[137],"effectiveness":[138],"superiority.":[140],"Our":[141],"code":[142],"is":[143],"available":[144],"at":[145],"https://github.com/YoucanBaby/MH-DETR.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}