{"id":"https://openalex.org/W4408354680","doi":"https://doi.org/10.1109/icassp49660.2025.10890723","title":"Advancing Dark Action Recognition via Modality Fusion and Dark-to-Light Diffusion Model","display_name":"Advancing Dark Action Recognition via Modality Fusion and Dark-to-Light Diffusion Model","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354680","doi":"https://doi.org/10.1109/icassp49660.2025.10890723"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890723","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":"conference-paper","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/A5058981456","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-9117-0619"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Fudan University,School of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100297334","display_name":"Zhen Xing","orcid":"https://orcid.org/0009-0008-0050-6323"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Xing","raw_affiliation_strings":["Fudan University,School of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026167547","display_name":"Zuxuan Wu","orcid":"https://orcid.org/0000-0002-8689-5807"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["Fudan University,School of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.991599977016449,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6607966423034668},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4617817997932434},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4520435929298401},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.43584713339805603},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4253312945365906},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3946777284145355},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.29856306314468384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2777271866798401}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6607966423034668},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4617817997932434},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4520435929298401},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.43584713339805603},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4253312945365906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3946777284145355},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.29856306314468384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2777271866798401},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890723","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1983364832","https://openalex.org/W2130155081","https://openalex.org/W2883429621","https://openalex.org/W2904170036","https://openalex.org/W2962934715","https://openalex.org/W2963155035","https://openalex.org/W2987861506","https://openalex.org/W3015735225","https://openalex.org/W3034572008","https://openalex.org/W3035731588","https://openalex.org/W3137609883","https://openalex.org/W3155072588","https://openalex.org/W3173484326","https://openalex.org/W3177337242","https://openalex.org/W3182700213","https://openalex.org/W3185046724","https://openalex.org/W4214614183","https://openalex.org/W4306831165","https://openalex.org/W4312263092","https://openalex.org/W4312560592","https://openalex.org/W4312933868","https://openalex.org/W4317496742","https://openalex.org/W4381198761","https://openalex.org/W4382467086","https://openalex.org/W4386071476","https://openalex.org/W4390871944","https://openalex.org/W4390873027","https://openalex.org/W4390873054","https://openalex.org/W4390873135","https://openalex.org/W4390874610","https://openalex.org/W4402667906","https://openalex.org/W4404106419","https://openalex.org/W6600983433","https://openalex.org/W6755037456","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6846313647","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"Recognizing":[0],"human":[1],"actions":[2],"under":[3],"low":[4],"illumination":[5],"is":[6,45],"challenging":[7],"due":[8],"to":[9,30,63,106],"the":[10,33,52,69,75,89,97,109,117,121,127,133,157],"limited":[11],"high-quality":[12],"data":[13],"and":[14,38,113,116,129,140,151],"weak":[15],"recognition":[16,40,99,122],"backbones.":[17],"To":[18,73],"this":[19],"end,":[20],"we":[21,60,81,95],"propose":[22],"Modality":[23],"Fusion":[24],"Dark-to-Light":[25],"(MFDL),":[26],"a":[27,46,84],"two-stage":[28],"framework":[29],"simultaneously":[31],"enhance":[32],"invisibility":[34],"of":[35,120,135],"poorly-lit":[36],"videos":[37],"strengthen":[39],"performance.":[41],"Our":[42],"initial":[43],"stage":[44],"pixel-wise":[47],"diffusion":[48,90],"model":[49,91],"that":[50],"converts":[51],"dark":[53,114],"frames":[54,67],"into":[55,88],"their":[56],"brightened":[57],"counterparts.":[58],"Specifically,":[59],"apply":[61],"ControlNet":[62],"produce":[64],"preliminarily":[65],"recovered":[66],"as":[68],"additional":[70],"constraint":[71],"priors.":[72],"ensure":[74],"temporal":[76],"consistency":[77,119],"between":[78,111],"neighboring":[79],"frames,":[80],"furthur":[82],"integrate":[83],"specific":[85],"spatial-temporal":[86,118],"attention":[87],"during":[92],"sampling.":[93],"Subsequently,":[94],"equip":[96],"action":[98],"backbone":[100],"with":[101],"custom":[102],"modality":[103],"fusion":[104],"modules":[105],"promote":[107],"both":[108,138,149],"interaction":[110],"light":[112],"modalities":[115],"architecture.":[123],"Extensive":[124],"experiments":[125],"on":[126,148,159],"ARID":[128],"Dark48":[130],"benchmarks":[131],"validate":[132],"effectiveness":[134],"our":[136],"approach,":[137],"quantitative":[139],"qualitative.":[141],"In":[142],"particular,":[143],"MFDL":[144],"achieves":[145],"state-of-the-art":[146],"results":[147],"datasets":[150],"exhibits":[152],"an":[153],"9.06%":[154],"improvement":[155],"over":[156],"baseline":[158],"Dark48.":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}