{"id":"https://openalex.org/W7207651998","doi":"https://doi.org/10.48550/arxiv.2609.02529","title":"Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and Difference-Fusion Framework","display_name":"Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and Difference-Fusion Framework","publication_year":2026,"publication_date":"2026-09-02","ids":{"openalex":"https://openalex.org/W7207651998","doi":"https://doi.org/10.48550/arxiv.2609.02529"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.02529","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02529","pdf_url":"https://arxiv.org/pdf/2609.02529","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.02529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134169536","display_name":"Yan Zhong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong, Yan","raw_affiliation_strings":["Douyin , ByteDance Inc","Peking University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Douyin , ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]},{"raw_affiliation_string":"Peking University , Beijing , China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149584957","display_name":"Gefei Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Gefei","raw_affiliation_strings":["Douyin , ByteDance Inc","Peking University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Douyin , ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]},{"raw_affiliation_string":"Peking University , Beijing , China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019828916","display_name":"Qiufang Ma","orcid":"https://orcid.org/0000-0002-5710-4033","observed_orcids":["https://orcid.org/0000-0002-5710-4033"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Qiufang","raw_affiliation_strings":["Douyin , ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Douyin , ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138714501","display_name":"Zhen Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zhen","raw_affiliation_strings":["Douyin , ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Douyin , ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149861624","display_name":"Zhiwei Fan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan, Zhiwei","raw_affiliation_strings":["Douyin , ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Douyin , ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149772817","display_name":"Lei Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi, Lei","raw_affiliation_strings":["Communication University of China , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China , Beijing , China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5149572637","display_name":"Tingting Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Tingting","raw_affiliation_strings":["Douyin , ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Douyin , ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.8720999956130981,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.8720999956130981,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.10350000113248825,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.006500000134110451,"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/user-generated-content","display_name":"user-generated content","score":0.7319999933242798},{"id":"https://openalex.org/keywords/image-quality-assessment","display_name":"image quality assessment","score":0.8090000152587891},{"id":"https://openalex.org/keywords/fine-grained-localization","display_name":"fine-grained localization","score":0.6349999904632568},{"id":"https://openalex.org/keywords/image-restoration","display_name":"image restoration","score":0.4180000126361847},{"id":"https://openalex.org/keywords/social-media-images","display_name":"social media images","score":0.5040000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7031999826431274},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.635200023651123},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6227999925613403},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6195999979972839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5860000252723694},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.555899977684021},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5296000242233276},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5012000203132629},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.4964999854564667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44269999861717224},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4081000089645386},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.02529","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02529","pdf_url":"https://arxiv.org/pdf/2609.02529","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.02529","doi":"https://doi.org/10.48550/arxiv.2609.02529","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.02529","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.02529","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02529","pdf_url":"https://arxiv.org/pdf/2609.02529","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7207651998.pdf","grobid_xml":"https://content.openalex.org/works/W7207651998.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415539247","https://openalex.org/W2763586388","https://openalex.org/W4414197101","https://openalex.org/W2964822960","https://openalex.org/W3176730391","https://openalex.org/W7164828052","https://openalex.org/W2913508739","https://openalex.org/W4414458641","https://openalex.org/W4409653247","https://openalex.org/W4414199060"],"abstract_inverted_index":{"Image":[0],"enhancement":[1,63],"and":[2,11,30,36,53,85,108,136,172,197,209],"restoration":[3],"have":[4],"become":[5],"standard":[6],"back-end":[7],"operations":[8],"on":[9,45],"short-video":[10],"social":[12],"media":[13],"platforms":[14],"to":[15,55],"boost":[16],"UGC":[17,81],"visual":[18,25],"experience.":[19],"Yet":[20],"these":[21],"processes":[22],"inevitably":[23],"introduce":[24],"anomalies--especially":[26],"in":[27,65,143,153],"faces,":[28],"texts,":[29],"textures--that":[31],"directly":[32],"undermine":[33],"perceptual":[34],"fidelity":[35],"viewer":[37],"trust.":[38],"While":[39],"existing":[40],"IQA":[41],"methods":[42],"perform":[43],"well":[44],"classic":[46],"distortions,":[47],"they":[48],"target":[49],"holistic":[50],"quality":[51],"assessment":[52],"fail":[54],"capture":[56],"the":[57,87,96,148,192,198],"specific,":[58],"localized":[59],"anomalies":[60],"caused":[61],"by":[62],"algorithms":[64],"real-world":[66],"UGC.":[67],"To":[68,146],"bridge":[69],"this":[70,154,189,195],"gap,":[71],"we":[72,112,157],"formally":[73],"define":[74],"a":[75,114,159],"new":[76,155],"task-quality":[77],"Anomaly":[78,116],"Perception":[79,117],"for":[80,104,120,188,202],"image":[82,205],"Enhancement":[83],"(UEAP),":[84],"contribute":[86],"first":[88],"UEAP":[89],"benchmark":[90],"dataset,":[91],"named":[92],"UEAP-4k,":[93],"curated":[94],"from":[95,185],"real":[97],"business":[98],"scenarios.":[99,145],"It":[100],"provides":[101],"fine-grained":[102],"annotations":[103],"anomaly":[105,141,206],"categories,":[106],"localization":[107],"severity":[109],"levels.":[110],"Furthermore,":[111],"propose":[113,158],"Difference-Fusion":[115],"Method":[118],"(DFAP-UGC)":[119],"wild":[121],"UGC-enhanced":[122,204],"images,":[123],"which":[124],"leverages":[125],"explicit":[126],"problem-reference":[127],"difference":[128],"fusion":[129],"with":[130],"dense":[131],"spatial":[132],"querying,":[133],"regional":[134],"verification,":[135],"quality-aware":[137],"ranking,":[138],"enabling":[139],"robust":[140,203],"identification":[142],"challenging":[144],"handle":[147],"inherent":[149],"coupling":[150],"of":[151,194,200],"subtasks":[152],"task,":[156,190],"Locality-Aware":[160],"Dynamic":[161],"Task":[162],"Prioritization":[163],"(LADTP)":[164],"training":[165],"strategy":[166],"that":[167,179],"enables":[168],"effective":[169],"end-to-end":[170],"learning":[171],"eliminates":[173],"multi-stage":[174],"overhead.":[175],"Extensive":[176],"experiments":[177],"show":[178],"our":[180],"method":[181],"outperforms":[182],"baselines":[183],"adapted":[184],"classical":[186],"approaches":[187],"validating":[191],"value":[193],"dataset":[196],"superior":[199],"DFAP-UGC":[201],"perception.":[207],"Code":[208],"data":[210],"will":[211],"be":[212],"public.":[213]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-04T00:00:00"}