{"id":"https://openalex.org/W4415708153","doi":"https://doi.org/10.1109/icme59968.2025.11209406","title":"Learning to Unify Audio, Visual and Text for Audio-Enhanced Visual Answer Localization","display_name":"Learning to Unify Audio, Visual and Text for Audio-Enhanced Visual Answer Localization","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708153","doi":"https://doi.org/10.1109/icme59968.2025.11209406"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":null,"display_name":"Zhibin Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibin Wen","raw_affiliation_strings":["Xi’an Jiaotong University,Systems Engineering Institute,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Systems Engineering Institute,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100781451","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-5635-2916"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9349,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80494427,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.972599983215332,"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":0.972599983215332,"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":0.007899999618530273,"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":0.0026000000070780516,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6811000108718872},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6105999946594238},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5796999931335449},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47909998893737793},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47589999437332153},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.35499998927116394},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.32690000534057617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7329000234603882},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6811000108718872},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6105999946594238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6011000275611877},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5796999931335449},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47589999437332153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41530001163482666},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32519999146461487},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.31769999861717224},{"id":"https://openalex.org/C175652121","wikidata":"https://www.wikidata.org/wiki/Q4379351","display_name":"Causal consistency","level":5,"score":0.304500013589859},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30320000648498535},{"id":"https://openalex.org/C137105694","wikidata":"https://www.wikidata.org/wiki/Q3407510","display_name":"Local consistency","level":4,"score":0.2992999851703644},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2963524571","https://openalex.org/W2973164670","https://openalex.org/W2997762001","https://openalex.org/W3025323587","https://openalex.org/W3034743747","https://openalex.org/W3088744711","https://openalex.org/W3132753749","https://openalex.org/W3211953751","https://openalex.org/W4205822631","https://openalex.org/W4285290969","https://openalex.org/W4312544061","https://openalex.org/W4327852044","https://openalex.org/W4360600216","https://openalex.org/W4372265847","https://openalex.org/W4372349424","https://openalex.org/W4387968116","https://openalex.org/W4393148542","https://openalex.org/W4399426547"],"related_works":[],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,169],"Visual":[3],"Answer":[4],"Localization":[5,63],"(VAL)":[6],"is":[7,174],"to":[8,43,70,93,135],"locate":[9],"a":[10,15,59,84,125],"video":[11],"segment":[12],"that":[13,66,145,156],"answers":[14],"given":[16],"question.":[17],"Existing":[18],"methods":[19,34],"either":[20],"focus":[21],"solely":[22],"on":[23,105],"visual":[24,28,73],"modality":[25,38,69],"or":[26],"integrate":[27],"and":[29,47,74,97,150],"subtitle":[30],"modalities.":[31,99],"However,":[32],"these":[33],"neglect":[35],"the":[36,51,78,94,113,139,146,167,170],"audio":[37,68,171],"in":[39,50],"videos,":[40],"consequently":[41],"leading":[42],"incomplete":[44],"input":[45],"information":[46],"poor":[48],"consistency":[49,111],"VAL":[52,79],"task.":[53,80],"In":[54],"this":[55],"paper,":[56],"we":[57,82,116],"propose":[58],"unified":[60],"Audio-Visual-Textual":[61,119],"Span":[62],"(AVTSL)":[64],"method":[65,159],"incorporates":[67],"augment":[71],"both":[72],"textual":[75],"representations":[76],"for":[77],"Specifically,":[81],"design":[83,117],"network":[85],"structure":[86],"with":[87],"three":[88],"interacting":[89],"predictors,":[90],"each":[91,132],"corresponding":[92],"audio,":[95],"visual,":[96],"text":[98],"Each":[100],"predictor":[101,134],"generates":[102,148],"predictions":[103],"based":[104],"its":[106],"respective":[107],"modality.":[108,172],"To":[109],"maintain":[110],"across":[112],"predicted":[114],"results,":[115],"an":[118],"Consistency":[120],"module.":[121],"This":[122,141],"module":[123],"utilizes":[124],"Dynamic":[126],"Triangular":[127],"Loss":[128],"(DTL)":[129],"function,":[130],"allowing":[131],"modality\u2019s":[133],"dynamically":[136],"learn":[137],"from":[138],"others.":[140],"collaborative":[142],"learning":[143],"ensures":[144],"model":[147],"consistent":[149],"comprehensive":[151],"answers.":[152],"Extensive":[153],"experiments":[154],"show":[155],"our":[157],"proposed":[158],"outperforms":[160],"several":[161],"state-of-the-art":[162],"(SOTA)":[163],"methods,":[164],"which":[165],"demonstrates":[166],"effectiveness":[168],"Code":[173],"available":[175],"at":[176],"https://github.com/binbin2xs/AVTSL.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-30T00:00:00"}