{"id":"https://openalex.org/W4392904768","doi":"https://doi.org/10.1109/icassp48485.2024.10447985","title":"Segment Anything Model Meets Image Harmonization","display_name":"Segment Anything Model Meets Image Harmonization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904768","doi":"https://doi.org/10.1109/icassp48485.2024.10447985"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5045279290","display_name":"Haoxing Chen","orcid":"https://orcid.org/0000-0001-6637-8741"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoxing Chen","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101649330","display_name":"Yaohui Li","orcid":"https://orcid.org/0000-0002-6732-4961"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaohui Li","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101878836","display_name":"Zhangxuan Gu","orcid":"https://orcid.org/0000-0002-2102-2693"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhangxuan Gu","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056204625","display_name":"Zhuoer Xu","orcid":"https://orcid.org/0009-0000-4316-5364"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuoer Xu","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100582842","display_name":"Jun Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Lan","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076835782","display_name":"Huaxiong Li","orcid":"https://orcid.org/0000-0003-0395-1525"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaxiong Li","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2630","last_page":"2634"},"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":0.9993000030517578,"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":0.9993000030517578,"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":0.9980999827384949,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.763791024684906},{"id":"https://openalex.org/keywords/harmonization","display_name":"Harmonization","score":0.7207590341567993},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6781225800514221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6756755709648132},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5937597155570984},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5786002278327942},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.558426022529602},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5511599779129028},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4843522310256958},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.46507927775382996},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4233432412147522},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4116279184818268},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41133254766464233},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3869471549987793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10458916425704956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.763791024684906},{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.7207590341567993},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6781225800514221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6756755709648132},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5937597155570984},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5786002278327942},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.558426022529602},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5511599779129028},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4843522310256958},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.46507927775382996},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4233432412147522},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4116279184818268},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41133254766464233},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3869471549987793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10458916425704956},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":27,"referenced_works":["https://openalex.org/W2465552163","https://openalex.org/W2556945219","https://openalex.org/W2960974111","https://openalex.org/W2962737447","https://openalex.org/W3008540959","https://openalex.org/W3034684802","https://openalex.org/W3169823210","https://openalex.org/W3171358896","https://openalex.org/W3171714858","https://openalex.org/W4214738329","https://openalex.org/W4214919319","https://openalex.org/W4225322336","https://openalex.org/W4312502952","https://openalex.org/W4312698476","https://openalex.org/W4312926745","https://openalex.org/W4312966374","https://openalex.org/W4360594859","https://openalex.org/W4377131045","https://openalex.org/W4386071487","https://openalex.org/W4387609219","https://openalex.org/W4387968695","https://openalex.org/W4390873174","https://openalex.org/W4390873462","https://openalex.org/W4390874575","https://openalex.org/W4402774219","https://openalex.org/W6852832621","https://openalex.org/W6854034207"],"related_works":["https://openalex.org/W2006073222","https://openalex.org/W2488916264","https://openalex.org/W2323573032","https://openalex.org/W198625436","https://openalex.org/W1908077024","https://openalex.org/W2095388346","https://openalex.org/W2379751185","https://openalex.org/W2379404183","https://openalex.org/W2004509987","https://openalex.org/W2185986540"],"abstract_inverted_index":{"Image":[0],"harmonization":[1,120],"is":[2,58],"a":[3,93],"crucial":[4],"technique":[5],"in":[6],"image":[7,119],"composition":[8],"that":[9,67,84],"aims":[10],"to":[11,60,71,99],"seamlessly":[12],"match":[13],"the":[14,18,36,47,62,87,101,113],"background":[15,42,108],"by":[16,92],"adjusting":[17],"foreground":[19,40,106],"of":[20,105,115],"composite":[21],"images.":[22],"Current":[23],"methods":[24],"adopt":[25],"either":[26],"global-level":[27],"or":[28],"pixel-level":[29,50],"feature":[30,33,51],"matching.":[31],"Global-level":[32],"matching":[34,52],"ignores":[35],"proximity":[37],"prior,":[38],"treating":[39],"and":[41,107],"as":[43],"separate":[44],"entities.":[45],"On":[46],"other":[48],"hand,":[49],"loses":[53],"contextual":[54],"information.":[55],"Therefore,":[56],"it":[57],"necessary":[59],"use":[61],"information":[63],"from":[64],"semantic":[65,88],"maps":[66,90],"describe":[68],"different":[69],"objects":[70],"guide":[72,100],"harmonization.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77],"propose":[78],"Semantic-guided":[79],"Region-aware":[80],"Instance":[81],"Normalization":[82],"(SRIN)":[83],"can":[85],"utilize":[86],"segmentation":[89],"output":[91],"pre-trained":[94],"Segment":[95],"Anything":[96],"Model":[97],"(SAM)":[98],"visual":[102],"consistency":[103],"learning":[104],"features.":[109],"Abundant":[110],"experiments":[111],"demonstrate":[112],"superiority":[114],"our":[116],"method":[117],"for":[118],"over":[121],"state-of-the-art":[122],"methods.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}