{"id":"https://openalex.org/W4417073222","doi":"https://doi.org/10.1145/3743093.3771052","title":"Towards Better Detection in the Rain: A Task-Driven Deraining Framework with Semantic Guidance","display_name":"Towards Better Detection in the Rain: A Task-Driven Deraining Framework with Semantic Guidance","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073222","doi":"https://doi.org/10.1145/3743093.3771052"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3771052","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771052","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771052","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771052","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101105724","display_name":"Ya-Han Chang","orcid":"https://orcid.org/0009-0007-4713-251X"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ya-Han Chang","raw_affiliation_strings":["National Taipei University of Technology, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0007-4713-251X","affiliations":[{"raw_affiliation_string":"National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078313923","display_name":"Shih\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0001-7678-5308"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shih-Hsuan Yang","raw_affiliation_strings":["National Taipei University of Technology, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-7678-5308","affiliations":[{"raw_affiliation_string":"National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34670102,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.932699978351593,"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/T11019","display_name":"Image Enhancement Techniques","score":0.932699978351593,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.027699999511241913,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.00839999970048666,"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/object-detection","display_name":"Object detection","score":0.6775000095367432},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.597000002861023},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.531499981880188},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5249999761581421},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4659999907016754},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.45419999957084656},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3887999951839447},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.34439998865127563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797999978065491},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6775000095367432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6554999947547913},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.597000002861023},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5249999761581421},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.476500004529953},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26809999346733093}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3771052","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771052","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771052","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3771052","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771052","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771052","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324051","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073222.pdf","grobid_xml":"https://content.openalex.org/works/W4417073222.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W2082306445","https://openalex.org/W2102605133","https://openalex.org/W2108565186","https://openalex.org/W2154621477","https://openalex.org/W2209874411","https://openalex.org/W2340897893","https://openalex.org/W2466666260","https://openalex.org/W2509784253","https://openalex.org/W2559264300","https://openalex.org/W2740982616","https://openalex.org/W2884068670","https://openalex.org/W2954171777","https://openalex.org/W2963017889","https://openalex.org/W2963037989","https://openalex.org/W2963800716","https://openalex.org/W2964115968","https://openalex.org/W2967584026","https://openalex.org/W3115142864","https://openalex.org/W3138516171","https://openalex.org/W4214940715","https://openalex.org/W4225672218","https://openalex.org/W4226042837","https://openalex.org/W4386065769","https://openalex.org/W4386075800","https://openalex.org/W4394596823"],"related_works":[],"abstract_inverted_index":{"Object":[0],"detection":[1,26,66,101,114,181],"is":[2],"essential":[3],"for":[4],"intelligent":[5],"surveillance,":[6],"autonomous":[7],"driving,":[8],"and":[9,18,24,65,92,113,128,133,140,146,171,177],"outdoor":[10],"scene":[11],"understanding.":[12],"However,":[13],"rainy":[14],"conditions":[15],"introduce":[16],"raindrops":[17],"streaks":[19],"that":[20,43,60,108,120,164],"degrade":[21],"image":[22],"quality":[23,64],"reduce":[25],"accuracy.":[27,115,182],"Conventional":[28],"deraining":[29,58,78,105,176],"methods":[30],"optimize":[31],"perceptual":[32],"metrics":[33],"(e.g.,":[34],"PSNR,":[35],"SSIM),":[36],"producing":[37],"visually":[38],"pleasing":[39],"but":[40],"over-smoothed":[41],"results":[42,162],"harm":[44],"detection,":[45],"while":[46,135],"detection-oriented":[47,56],"approaches":[48],"often":[49],"sacrifice":[50],"visual":[51,63,169],"fidelity.":[52],"We":[53],"propose":[54],"a":[55],"single-image":[57],"framework":[59],"jointly":[61],"optimizes":[62],"robustness.":[67],"The":[68],"high-level":[69],"semantic":[70],"features":[71],"of":[72,158],"YOLO11":[73],"are":[74],"embedded":[75],"in":[76],"the":[77,81,124,142,156,159],"encoder,":[79],"enabling":[80],"network":[82],"to":[83,155],"focus":[84],"on":[85,117],"semantically":[86],"critical":[87],"regions,":[88],"preserve":[89],"object":[90,180],"details,":[91],"remove":[93],"rain":[94],"noise":[95],"without":[96],"harming":[97],"detection-relevant":[98],"structures.":[99],"Furthermore,":[100],"loss":[102],"directly":[103],"guides":[104],"optimization,":[106],"ensuring":[107,174],"output":[109],"enhances":[110],"both":[111],"fidelity":[112,170],"Experiments":[116],"RainCityscapes":[118],"show":[119],"our":[121,165],"method":[122],"achieves":[123],"highest":[125],"precision":[126],"(71.07%)":[127],"mAP50":[129],"(61.66%),":[130],"outperforming":[131],"RobustSIRR":[132],"Restormer,":[134],"maintaining":[136],"competitive":[137],"Recall":[138],"(56.65%)":[139],"achieving":[141],"best":[143],"SSIM":[144],"(0.9735)":[145],"lowest":[147],"LPIPS":[148],"(0.0274)":[149],"with":[150],"PSNR":[151],"(34.75":[152],"dB)":[153],"comparable":[154],"state":[157],"art.":[160],"These":[161],"demonstrate":[163],"approach":[166],"effectively":[167],"balances":[168],"task-oriented":[172],"performance,":[173],"high-quality":[175],"improving":[178],"downstream":[179]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-06T00:00:00"}