{"id":"https://openalex.org/W4408354353","doi":"https://doi.org/10.1109/icassp49660.2025.10890183","title":"Text-Infused Audio-Visual Video Parsing with Semantic-Aware Multimodal Contrastive Learning","display_name":"Text-Infused Audio-Visual Video Parsing with Semantic-Aware Multimodal Contrastive Learning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354353","doi":"https://doi.org/10.1109/icassp49660.2025.10890183"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5030474289","display_name":"Pengcheng Zhao","orcid":"https://orcid.org/0000-0003-3774-5113"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengcheng Zhao","raw_affiliation_strings":["Hefei University of Technology,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101845614","display_name":"Yanxiang Chen","orcid":"https://orcid.org/0000-0001-7974-6494"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxiang Chen","raw_affiliation_strings":["Hefei University of Technology,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059530979","display_name":"Dan Guo","orcid":"https://orcid.org/0000-0003-2594-254X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["Hefei University of Technology,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024061393","display_name":"Yuanzhi Yao","orcid":"https://orcid.org/0000-0003-1965-7670"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhi Yao","raw_affiliation_strings":["Hefei University of Technology,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030474289"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04302097,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9914000034332275,"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":0.9914000034332275,"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":0.9883000254631042,"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/T11309","display_name":"Music and Audio Processing","score":0.9812999963760376,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8993703126907349},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7410617470741272},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.551383376121521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5509379506111145},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41131845116615295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8993703126907349},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7410617470741272},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.551383376121521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5509379506111145},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41131845116615295}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2963155035","https://openalex.org/W3118120400","https://openalex.org/W3175335326","https://openalex.org/W3175514052","https://openalex.org/W4226206782","https://openalex.org/W4304083155","https://openalex.org/W4309660795","https://openalex.org/W4312864739","https://openalex.org/W4313123347","https://openalex.org/W4372260201","https://openalex.org/W4372260310","https://openalex.org/W4385245566","https://openalex.org/W4386065882","https://openalex.org/W4389065381","https://openalex.org/W4393154284","https://openalex.org/W4399474077","https://openalex.org/W4403386295","https://openalex.org/W4403791730","https://openalex.org/W4403998639","https://openalex.org/W4409365689","https://openalex.org/W4409367415","https://openalex.org/W6631190155","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6763701032","https://openalex.org/W6776700526","https://openalex.org/W6791353385","https://openalex.org/W6804185262","https://openalex.org/W6851397930","https://openalex.org/W6852742819","https://openalex.org/W6857566609","https://openalex.org/W6874869417"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W4381248170","https://openalex.org/W3189621521","https://openalex.org/W2173794830","https://openalex.org/W1502858101","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"Audio-Visual":[1],"Video":[2],"Parsing":[3,74],"task":[4],"aims":[5],"to":[6,96,109,144],"recognize":[7],"events":[8,57],"occurring":[9],"in":[10,20,51],"video":[11,22],"segments":[12],"for":[13,115],"each":[14,116],"modality.":[15,64],"Presently,":[16],"the":[17,31,52,60,78,89,98,105,133,137,145],"excellent":[18],"performance":[19,139],"handling":[21],"parsing":[23],"is":[24,94],"shown":[25],"by":[26,103],"generating":[27],"pseudo":[28],"labels":[29],"at":[30],"segment":[32,45,101,113],"level.":[33],"However,":[34],"these":[35],"approaches":[36],"still":[37],"suffer":[38],"from":[39],"adequate":[40],"semantic":[41],"learning":[42],"of":[43,54,62,140],"fine-grained":[44],"features,":[46],"which":[47,82],"can":[48,83],"cause":[49],"errors":[50],"prediction":[53],"those":[55],"ambiguous":[56],"and":[58,91],"affect":[59],"predictions":[61],"another":[63],"To":[65],"tackle":[66],"this":[67],"issue,":[68],"we":[69,118],"propose":[70,119],"a":[71,120,126],"novel":[72,121],"Text-Infused":[73],"Network":[75],"(TIPNet).":[76],"Specifically,":[77],"event":[79],"text":[80],"modality,":[81,117],"offer":[84],"more":[85,111],"precise":[86],"semantics":[87],"than":[88],"audio":[90],"visual":[92],"modalities,":[93],"introduced":[95],"enhance":[97],"event-related":[99],"audio/visual":[100],"features":[102,114],"encoding":[104],"cross-modal":[106],"interactions.":[107],"Furthermore,":[108],"obtain":[110],"discriminative":[112],"multimodal":[122],"contrastive":[123],"loss":[124],"with":[125],"semantic-aware":[127],"weighting":[128],"mechanism.":[129],"Experimental":[130],"results":[131],"on":[132],"benchmark":[134],"dataset":[135],"demonstrate":[136],"superior":[138],"our":[141],"approach":[142],"compared":[143],"state-of-the-art":[146],"methods.":[147]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}