{"id":"https://openalex.org/W4379806215","doi":"https://doi.org/10.1145/3591106.3592286","title":"Dual-Stream Multimodal Learning for Topic-Adaptive Video Highlight Detection","display_name":"Dual-Stream Multimodal Learning for Topic-Adaptive Video Highlight Detection","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806215","doi":"https://doi.org/10.1145/3591106.3592286"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592286","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","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/A5027577933","display_name":"Ziwei Xiong","orcid":"https://orcid.org/0009-0001-7041-5936"},"institutions":[{"id":"https://openalex.org/I31683504","display_name":"Beijing Forestry University","ror":"https://ror.org/04xv2pc41","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I31683504","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziwei Xiong","raw_affiliation_strings":["Beijing Forestry University, China"],"raw_orcid":"https://orcid.org/0009-0001-7041-5936","affiliations":[{"raw_affiliation_string":"Beijing Forestry University, China","institution_ids":["https://openalex.org/I31683504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101635388","display_name":"Han Wang","orcid":"https://orcid.org/0009-0001-0884-2603"},"institutions":[{"id":"https://openalex.org/I31683504","display_name":"Beijing Forestry University","ror":"https://ror.org/04xv2pc41","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I31683504","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Wang","raw_affiliation_strings":["Beijing Forestry University, China"],"raw_orcid":"https://orcid.org/0009-0001-0884-2603","affiliations":[{"raw_affiliation_string":"Beijing Forestry University, China","institution_ids":["https://openalex.org/I31683504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027577933"],"corresponding_institution_ids":["https://openalex.org/I31683504"],"apc_list":null,"apc_paid":null,"fwci":0.2355,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49869489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"272","last_page":"279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T11439","display_name":"Video Analysis and Summarization","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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":0.998199999332428,"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":0.8759496808052063},{"id":"https://openalex.org/keywords/snippet","display_name":"Snippet","score":0.7986915111541748},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6055307388305664},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5900446772575378},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5368810892105103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5363774299621582},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5006570816040039},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4770483374595642},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46667611598968506},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41627609729766846},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.41042694449424744},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3390050530433655},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33784645795822144},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17000091075897217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8759496808052063},{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.7986915111541748},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6055307388305664},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5900446772575378},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5368810892105103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5363774299621582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5006570816040039},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4770483374595642},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46667611598968506},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41627609729766846},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.41042694449424744},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3390050530433655},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33784645795822144},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17000091075897217},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592286","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W329267344","https://openalex.org/W1546418874","https://openalex.org/W1904325426","https://openalex.org/W1924343884","https://openalex.org/W2119738097","https://openalex.org/W2120645068","https://openalex.org/W2121746860","https://openalex.org/W2143800062","https://openalex.org/W2194345886","https://openalex.org/W2467794422","https://openalex.org/W2737677090","https://openalex.org/W2766630207","https://openalex.org/W2781922022","https://openalex.org/W2797074994","https://openalex.org/W2798970487","https://openalex.org/W2898447949","https://openalex.org/W2919974746","https://openalex.org/W2963729528","https://openalex.org/W3035265375","https://openalex.org/W3105607218","https://openalex.org/W3185341429","https://openalex.org/W3196253003","https://openalex.org/W3198377975","https://openalex.org/W3201832684","https://openalex.org/W3214448253","https://openalex.org/W3216156094","https://openalex.org/W4285606530","https://openalex.org/W4312407537","https://openalex.org/W4312480274","https://openalex.org/W4312544061","https://openalex.org/W4312558481","https://openalex.org/W4312563428","https://openalex.org/W4312680331","https://openalex.org/W4312693115","https://openalex.org/W4313186260","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W1607713096","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314"],"abstract_inverted_index":{"This":[0],"paper":[1],"targets":[2],"at":[3],"topic-adaptive":[4,152,187],"video":[5,15,139,199],"highlight":[6,62,119,153,188,200],"detection,":[7],"aiming":[8],"to":[9,34,67,103,149,196],"identify":[10],"the":[11,25,38,68,96,113,118,138,164,175,197],"moments":[12],"in":[13],"a":[14,58,79,82,86,89,126,131,183,210],"described":[16],"by":[17,64,209],"arbitrary":[18],"text":[19,73],"inputs.":[20],"The":[21],"fundamental":[22],"challenge":[23],"is":[24,32,81],"availability":[26],"of":[27,40,71,91,99,115,166],"annotated":[28],"training":[29],"data.":[30,159],"It":[31],"costly":[33],"further":[35,157],"scale":[36],"up":[37],"number":[39],"topic-level":[41],"categories":[42],"which":[43,136],"requires":[44],"manually":[45],"identifying":[46],"and":[47,94,109,145,181],"labeling":[48],"corresponding":[49],"highlights.":[50],"To":[51],"overcome":[52],"this":[53,116],"challenge,":[54],"our":[55,147,167,193,203],"method":[56,168,177,204],"provides":[57],"new":[59],"perspective":[60],"on":[61,169],"detection":[63,120,154,201],"attaching":[65],"importance":[66],"semantic":[69,110,142],"information":[70],"topic":[72,87],"rather":[74],"than":[75],"simply":[76],"classifying":[77],"whether":[78],"snippet":[80],"highlight.Specifically,":[83],"we":[84],"decompose":[85],"into":[88],"set":[90],"key":[92],"concepts":[93],"utilize":[95],"remarkable":[97],"ability":[98],"visual-language":[100],"pre-trained":[101,194],"models":[102],"learn":[104],"knowledge":[105],"from":[106],"both":[107],"videos":[108],"language.":[111],"With":[112],"merits":[114],"reformulation,":[117],"task":[121],"can":[122],"be":[123],"modeled":[124],"as":[125],"snippet-text":[127],"matching":[128],"problem":[129],"within":[130],"dual-stream":[132],"multimodal":[133],"learning":[134],"framework,":[135],"strengthens":[137],"representation":[140],"with":[141],"language":[143],"supervision":[144],"enables":[146],"model":[148,195],"accomplish":[150],"open-set":[151,198],"without":[155],"any":[156],"labeled":[158],"Our":[160],"empirical":[161],"evaluation":[162],"shows":[163],"effectiveness":[165],"several":[170],"publicly":[171],"available":[172],"datasets,":[173],"where":[174],"proposed":[176],"outperforms":[178,205],"competitive":[179],"baselines":[180],"achieves":[182],"novel":[184],"state-of-the-art":[185],"for":[186],"detection.":[189],"Further,":[190],"when":[191],"transferring":[192],"task,":[202],"prior":[206],"supervised":[207],"work":[208],"substantial":[211],"margin.":[212]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}