{"id":"https://openalex.org/W4392543396","doi":"https://doi.org/10.1109/tip.2024.3372469","title":"Unsupervised Modality-Transferable Video Highlight Detection With Representation Activation Sequence Learning","display_name":"Unsupervised Modality-Transferable Video Highlight Detection With Representation Activation Sequence Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392543396","doi":"https://doi.org/10.1109/tip.2024.3372469","pmid":"https://pubmed.ncbi.nlm.nih.gov/38451754"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3372469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3372469","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.09401","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078082551","display_name":"Tingtian Li","orcid":"https://orcid.org/0000-0001-9124-2600"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingtian Li","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9124-2600","affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067395825","display_name":"Zixun Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixun Sun","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102999463","display_name":"Xinyu Xiao","orcid":"https://orcid.org/0000-0003-4895-632X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Xiao","raw_affiliation_strings":["Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":1.2978,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78887263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"33","issue":null,"first_page":"1911","last_page":"1922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T11439","display_name":"Video Analysis and Summarization","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/T10531","display_name":"Advanced Vision and Imaging","score":0.9984999895095825,"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":0.9958000183105469,"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":0.7927085161209106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6828573942184448},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6434159278869629},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5624884366989136},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5412946939468384},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5252413749694824},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4768042266368866},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4368554651737213},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.427223801612854},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40063074231147766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3387484550476074},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32421764731407166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7927085161209106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6828573942184448},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6434159278869629},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5624884366989136},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5412946939468384},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5252413749694824},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4768042266368866},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4368554651737213},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.427223801612854},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40063074231147766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3387484550476074},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32421764731407166},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2024.3372469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3372469","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:38451754","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38451754","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":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null},{"id":"pmh:oai:arXiv.org:2403.09401","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.09401","pdf_url":"https://arxiv.org/pdf/2403.09401","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.09401","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.09401","pdf_url":"https://arxiv.org/pdf/2403.09401","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392543396.pdf"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W329267344","https://openalex.org/W1900913856","https://openalex.org/W1904325426","https://openalex.org/W1924343884","https://openalex.org/W1926243429","https://openalex.org/W1927052826","https://openalex.org/W1958932515","https://openalex.org/W1966872876","https://openalex.org/W1976806664","https://openalex.org/W2115245686","https://openalex.org/W2139009685","https://openalex.org/W2143419558","https://openalex.org/W2155635849","https://openalex.org/W2170095155","https://openalex.org/W2194345886","https://openalex.org/W2251324968","https://openalex.org/W2255466643","https://openalex.org/W2395579298","https://openalex.org/W2467794422","https://openalex.org/W2508457857","https://openalex.org/W2517959782","https://openalex.org/W2560468004","https://openalex.org/W2574952845","https://openalex.org/W2625136576","https://openalex.org/W2737677090","https://openalex.org/W2776277180","https://openalex.org/W2788321336","https://openalex.org/W2890952074","https://openalex.org/W2896457183","https://openalex.org/W2897091983","https://openalex.org/W2903758693","https://openalex.org/W2915977493","https://openalex.org/W2919974746","https://openalex.org/W2937914723","https://openalex.org/W2963684088","https://openalex.org/W2963691181","https://openalex.org/W2963722008","https://openalex.org/W2963729528","https://openalex.org/W2963919999","https://openalex.org/W2982223350","https://openalex.org/W2986407524","https://openalex.org/W3035046783","https://openalex.org/W3094520012","https://openalex.org/W3106645934","https://openalex.org/W3106775073","https://openalex.org/W3109316002","https://openalex.org/W3138516171","https://openalex.org/W3153980448","https://openalex.org/W3171125843","https://openalex.org/W3177241885","https://openalex.org/W3197449311","https://openalex.org/W3202168743","https://openalex.org/W4239147634","https://openalex.org/W4312693115","https://openalex.org/W4313156423","https://openalex.org/W4385245566","https://openalex.org/W6677302653","https://openalex.org/W6685352114","https://openalex.org/W6718046261","https://openalex.org/W6741832134","https://openalex.org/W6780218876","https://openalex.org/W6791353385","https://openalex.org/W6793736971"],"related_works":["https://openalex.org/W3174759195","https://openalex.org/W2905271011","https://openalex.org/W3167013339","https://openalex.org/W4287121366","https://openalex.org/W3164948662","https://openalex.org/W4289536128","https://openalex.org/W3153597579","https://openalex.org/W4298151006","https://openalex.org/W4390871823","https://openalex.org/W60493759"],"abstract_inverted_index":{"Identifying":[0],"highlight":[1,53,79,101,199],"moments":[2],"of":[3,13,26,39,44,108,158],"raw":[4],"video":[5],"materials":[6],"is":[7,165,194],"crucial":[8],"for":[9,52,77,170],"improving":[10],"the":[11,23,105,109,113,131,135,140,148,175,188,198,206],"efficiency":[12],"editing":[14],"videos":[15,38,57],"that":[16,48,205],"are":[17],"pervasive":[18],"on":[19],"internet":[20],"platforms.":[21],"However,":[22],"extensive":[24],"work":[25],"manually":[27],"labeling":[28],"footage":[29],"has":[30],"created":[31],"obstacles":[32],"to":[33,37,62,124,146,196,213],"applying":[34],"supervised":[35],"methods":[36],"unseen":[40],"categories.":[41],"The":[42,81,191,201],"absence":[43],"an":[45,155],"audio":[46,136,152],"modality":[47,133],"contains":[49],"valuable":[50],"cues":[51],"detection":[54],"in":[55],"many":[56],"also":[58],"makes":[59],"it":[60],"difficult":[61],"use":[63,139],"multimodal":[64],"strategies.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69,103,138],"propose":[70,112],"a":[71,95],"novel":[72],"model":[73,83,178],"with":[74,86,120,134,182],"cross-modal":[75,176],"perception":[76],"unsupervised":[78,100],"detection.":[80],"proposed":[82,207],"learns":[84],"representations":[85,107,181],"visual-audio":[87,184],"level":[88],"semantics":[89,185],"from":[90],"image-audio":[91],"pair":[92],"data":[93],"via":[94],"self-reconstruction":[96],"task.":[97],"To":[98,129],"achieve":[99],"detection,":[102],"investigate":[104],"latent":[106],"network":[110],"and":[111,151],"representation":[114,127,171],"activation":[115],"sequence":[116,162],"learning":[117,123,143],"(RASL)":[118],"module":[119,145,193],"k-point":[121],"contrastive":[122,142],"learn":[125,147],"significant":[126],"activations.":[128],"connect":[130],"visual":[132,150,189],"modality,":[137],"symmetric":[141],"(SCL)":[144],"paired":[149,183],"representations.":[153],"Furthermore,":[154],"auxiliary":[156],"task":[157],"masked":[159],"feature":[160],"vector":[161],"(FVS)":[163],"reconstruction":[164],"simultaneously":[166],"conducted":[167],"during":[168],"pretraining":[169],"enhancement.":[172],"During":[173],"inference,":[174],"pretrained":[177],"can":[179],"generate":[180],"given":[186],"only":[187],"modality.":[190],"RASL":[192],"used":[195],"output":[197],"scores.":[200],"experimental":[202],"results":[203],"show":[204],"framework":[208],"achieves":[209],"superior":[210],"performance":[211],"compared":[212],"other":[214],"state-of-the-art":[215],"approaches.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}