{"id":"https://openalex.org/W4415707984","doi":"https://doi.org/10.1109/icme59968.2025.11210145","title":"EAV-Mamba: Efficient Audio-Visual Representation Learning for Weakly-Supervised Temporal Action Localization","display_name":"EAV-Mamba: Efficient Audio-Visual Representation Learning for Weakly-Supervised Temporal Action Localization","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707984","doi":"https://doi.org/10.1109/icme59968.2025.11210145"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210145","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":"https://openalex.org/A5101433173","display_name":"Quan Zhang","orcid":"https://orcid.org/0009-0000-6862-9022"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Quan Zhang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007733194","display_name":"Jinwei Fang","orcid":"https://orcid.org/0000-0002-1664-0024"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinwei Fang","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071078581","display_name":"Yuxin Qi","orcid":"https://orcid.org/0000-0003-4762-2715"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Qi","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016314811","display_name":"Mingyang Wan","orcid":"https://orcid.org/0000-0002-1536-3643"},"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":"Mingyang Wan","raw_affiliation_strings":["Xi'an Jiaotong University","ByteDance Inc"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102203027","display_name":"Guojun Ma","orcid":"https://orcid.org/0000-0002-1401-9613"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojun Ma","raw_affiliation_strings":["Tsinghua University","ByteDance Inc"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078138280","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0003-1354-4886"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Zhang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101456902","display_name":"Chun Yuan","orcid":"https://orcid.org/0000-0002-3590-6676"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yuan","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101433173"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33692491,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.5777999758720398,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.5777999758720398,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.13019999861717224,"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":0.09539999812841415,"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/action","display_name":"Action (physics)","score":0.6229000091552734},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6047999858856201},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5586000084877014},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4932999908924103},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.47049999237060547},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41760000586509705},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3799000084400177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250999808311462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6967999935150146},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6229000091552734},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6047999858856201},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5586000084877014},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4932999908924103},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.47049999237060547},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3749000132083893},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.34850001335144043},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3264000117778778},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2903999984264374}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210145","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2895240652","https://openalex.org/W2963022469","https://openalex.org/W2963524571","https://openalex.org/W2964109005","https://openalex.org/W2964216549","https://openalex.org/W2984619425","https://openalex.org/W2988098865","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3034623254","https://openalex.org/W3056617467","https://openalex.org/W3095669214","https://openalex.org/W3097664769","https://openalex.org/W3173698268","https://openalex.org/W3177433885","https://openalex.org/W3189379416","https://openalex.org/W3202825210","https://openalex.org/W3214808272","https://openalex.org/W4312317576","https://openalex.org/W4372260211","https://openalex.org/W4381198912","https://openalex.org/W4385767637","https://openalex.org/W4386057765","https://openalex.org/W4386066210","https://openalex.org/W4386071527","https://openalex.org/W4388188327","https://openalex.org/W4390872976","https://openalex.org/W4390873021","https://openalex.org/W4393154133","https://openalex.org/W4393159954","https://openalex.org/W4402660085","https://openalex.org/W4409346508","https://openalex.org/W4409365836"],"related_works":[],"abstract_inverted_index":{"Weakly":[0],"supervised":[1,43,132],"temporal":[2,44,60,115,133],"action":[3,45,61,66,116,134],"localization":[4,46,50,62,117,135],"aims":[5],"to":[6,8],"learn":[7],"locate":[9],"actions":[10],"in":[11,130],"videos":[12],"from":[13],"video-level":[14],"or":[15],"point-level":[16],"labels,":[17],"avoiding":[18],"the":[19,41,79],"need":[20],"for":[21,57],"costly":[22],"frame-level":[23],"annotations.":[24],"Unlike":[25],"previous":[26],"work":[27],"that":[28,68,120],"relies":[29],"solely":[30],"on":[31,86,111],"visual":[32,55],"modality":[33],"information,":[34],"we":[35,76,94],"propose":[36,77],"incorporating":[37],"audio":[38,53,71],"information":[39,56],"into":[40],"weakly":[42,131],"task.":[47],"While":[48],"audio-visual":[49,81,91,124],"tasks":[51],"combine":[52],"and":[54,105,127],"video":[58],"localization,":[59],"often":[63],"deals":[64],"with":[65],"categories":[67],"have":[69],"weak":[70],"cues.":[72],"To":[73],"address":[74],"this,":[75],"EAV-Mamba,":[78],"first":[80],"perception":[82,92,125],"modeling":[83,126],"method":[84],"based":[85],"Mamba.":[87],"Leveraging":[88],"Mamba\u2019s":[89],"powerful":[90],"capabilities,":[93],"developed":[95],"modules":[96],"such":[97],"as":[98],"Audio-Perceptive":[99,102],"Flow":[100],"Enhancement,":[101,104],"RGB":[103],"Audio":[106],"Self-Perceptive":[107],"Enhancement.":[108],"Extensive":[109],"experiments":[110],"two":[112],"publicly":[113],"available":[114],"datasets":[118],"demonstrate":[119],"EAV-Mamba":[121],"achieves":[122],"efficient":[123],"state-of-the-art":[128],"performance":[129],"tasks.":[136]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}