{"id":"https://openalex.org/W7124436090","doi":"https://doi.org/10.48550/arxiv.2601.10369","title":"Fine-Grained Human Pose Editing Assessment via Layer-Selective MLLMs","display_name":"Fine-Grained Human Pose Editing Assessment via Layer-Selective MLLMs","publication_year":2026,"publication_date":"2026-01-15","ids":{"openalex":"https://openalex.org/W7124436090","doi":"https://doi.org/10.48550/arxiv.2601.10369"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.10369","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.10369","pdf_url":"https://arxiv.org/pdf/2601.10369","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.10369","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123197090","display_name":"Ningyu Sun","orcid":null,"observed_orcids":[]},"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":"Sun, Ningyu","raw_affiliation_strings":["Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121114476","display_name":"Zhaolin Cai","orcid":null,"observed_orcids":[]},"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":"Cai, Zhaolin","raw_affiliation_strings":["Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123249870","display_name":"Zitong Xu","orcid":null,"observed_orcids":[]},"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":"Xu, Zitong","raw_affiliation_strings":["Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123194060","display_name":"Peihang Chen","orcid":null,"observed_orcids":[]},"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":"Chen, Peihang","raw_affiliation_strings":["Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124924793","display_name":"Huiyu Duan","orcid":null,"observed_orcids":[]},"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":"Duan, Huiyu","raw_affiliation_strings":["Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123247644","display_name":"Yichao Yan","orcid":null,"observed_orcids":[]},"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":"Yan, Yichao","raw_affiliation_strings":["Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043405654","display_name":"Xiongkuo Min","orcid":"https://orcid.org/0000-0001-5693-0416","observed_orcids":["https://orcid.org/0000-0001-5693-0416"]},"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":"Min, Xiongkuo","raw_affiliation_strings":["Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123194688","display_name":"Xiaokang Yang","orcid":null,"observed_orcids":[]},"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":"Yang, Xiaokang","raw_affiliation_strings":["Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Network Engineering , Shanghai Jiao Tong University {jiaotong870810 , xuzitong , ph4.66 ,","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6547999978065491,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6547999978065491,"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":0.3253999948501587,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.003000000026077032,"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/image-quality-assessment","display_name":"image quality assessment","score":0.5170000195503235},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.8149999976158142},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928000092506409},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7839999794960022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6262999773025513},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5267999768257141},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5259000062942505},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4154999852180481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4113999903202057},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.3573000133037567},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.35519999265670776},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26489999890327454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.10369","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.10369","pdf_url":"https://arxiv.org/pdf/2601.10369","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.10369","doi":"https://doi.org/10.48550/arxiv.2601.10369","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.10369","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:2601.10369","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.10369","pdf_url":"https://arxiv.org/pdf/2601.10369","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124436090.pdf","grobid_xml":"https://content.openalex.org/works/W7124436090.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4414458387"],"related_works":["https://openalex.org/W4412889713","https://openalex.org/W7129014956","https://openalex.org/W6967051638","https://openalex.org/W4415310644","https://openalex.org/W7155632314","https://openalex.org/W7147400264","https://openalex.org/W7216393413","https://openalex.org/W7220815370","https://openalex.org/W4415540372","https://openalex.org/W4417094407"],"abstract_inverted_index":{"Text-guided":[0],"human":[1],"pose":[2,99],"editing":[3,55],"has":[4],"gained":[5],"significant":[6],"traction":[7],"in":[8,106],"AIGC":[9],"applications.":[10],"However,it":[11],"remains":[12],"plagued":[13],"by":[14],"structural":[15],"anomalies":[16],"and":[17,61,84,110,121],"generative":[18],"artifacts.":[19],"Existing":[20],"evaluation":[21],"metrics":[22],"often":[23],"isolate":[24],"authenticity":[25,59,108],"detection":[26,109,120],"from":[27,52],"quality":[28,63,112,122],"assessment,":[29],"failing":[30],"to":[31],"provide":[32],"fine-grained":[33],"insights":[34],"into":[35],"pose-specific":[36],"inconsistencies.":[37],"To":[38],"address":[39],"these":[40],"limitations,":[41],"we":[42,66,92],"introduce":[43],"HPE-Bench,":[44],"a":[45,68,85],"specialized":[46],"benchmark":[47],"comprising":[48],"1,700":[49],"standardized":[50],"samples":[51],"17":[53],"state-of-the-art":[54],"models,":[56],"offering":[57],"both":[58,107],"labels":[60],"multi-dimensional":[62,111],"scores.":[64],"Furthermore,":[65],"propose":[67],"unified":[69],"framework":[70,102],"based":[71],"on":[72],"layer-selective":[73],"multimodal":[74],"large":[75],"language":[76],"models":[77],"(MLLMs).":[78],"By":[79],"employing":[80],"contrastive":[81],"LoRA":[82],"tuning":[83],"novel":[86],"layer":[87,97],"sensitivity":[88],"analysis":[89],"(LSA)":[90],"mechanism,":[91],"identify":[93],"the":[94,116],"optimal":[95],"feature":[96],"for":[98],"evaluation.":[100],"Our":[101],"achieves":[103],"superior":[104],"performance":[105],"regression,":[113],"effectively":[114],"bridging":[115],"gap":[117],"between":[118],"forensic":[119],"assessment.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-01-17T00:00:00"}