{"id":"https://openalex.org/W7125807472","doi":"https://doi.org/10.1145/3779153.3779157","title":"SemTraMix: Semantic-Guided Transparent Foreground Generation and Cross-Class Composition for Image Augmentation","display_name":"SemTraMix: Semantic-Guided Transparent Foreground Generation and Cross-Class Composition for Image Augmentation","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W7125807472","doi":"https://doi.org/10.1145/3779153.3779157"},"language":null,"primary_location":{"id":"doi:10.1145/3779153.3779157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3779153.3779157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Big Data and Internet of Things","raw_type":"proceedings-article"},"type":"article","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/A5123999873","display_name":"Zhen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I145581781","display_name":"Chongqing Technology and Business University","ror":"https://ror.org/05hqf1284","country_code":"CN","type":"education","lineage":["https://openalex.org/I145581781"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Artificial Intelligence Lab, Chongqing Technology and Business University, Chongqing, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Lab, Chongqing Technology and Business University, Chongqing, Chongqing, China","institution_ids":["https://openalex.org/I145581781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124002258","display_name":"Yun Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I145581781","display_name":"Chongqing Technology and Business University","ror":"https://ror.org/05hqf1284","country_code":"CN","type":"education","lineage":["https://openalex.org/I145581781"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Jiang","raw_affiliation_strings":["Artificial Intelligence Lab, Chongqing Technology and Business University, Chongqing, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Lab, Chongqing Technology and Business University, Chongqing, Chongqing, China","institution_ids":["https://openalex.org/I145581781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123906936","display_name":"Hang Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I145581781","display_name":"Chongqing Technology and Business University","ror":"https://ror.org/05hqf1284","country_code":"CN","type":"education","lineage":["https://openalex.org/I145581781"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Gao","raw_affiliation_strings":["Artificial Intelligence Lab, Chongqing Technology and Business University, Chongqing, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Lab, Chongqing Technology and Business University, Chongqing, Chongqing, China","institution_ids":["https://openalex.org/I145581781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5123999873"],"corresponding_institution_ids":["https://openalex.org/I145581781"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71217191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"32"},"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":0.4731999933719635,"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":0.4731999933719635,"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":0.4657999873161316,"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":0.012500000186264515,"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/generalization","display_name":"Generalization","score":0.7322999835014343},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5960999727249146},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5486999750137329},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.44130000472068787},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.43230000138282776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4253000020980835},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4025000035762787}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7322999835014343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.678600013256073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6523000001907349},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5960999727249146},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5486999750137329},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5024999976158142},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4025000035762787},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.32739999890327454},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3779153.3779157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3779153.3779157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Big Data and Internet of Things","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":4,"referenced_works":["https://openalex.org/W2103828746","https://openalex.org/W2894737833","https://openalex.org/W4312747676","https://openalex.org/W4312933868"],"related_works":[],"abstract_inverted_index":{"In":[0],"data-scarce":[1],"or":[2],"class-imbalanced":[3],"scenarios,":[4],"data":[5],"augmentation":[6,43,94],"is":[7],"a":[8,41],"vital":[9],"strategy":[10],"to":[11,32],"enhance":[12],"the":[13],"generalization":[14],"of":[15],"image":[16],"classification":[17],"models.":[18],"While":[19],"diffusion-based":[20],"generative":[21],"approaches":[22],"offer":[23],"promising":[24],"diversity":[25],"and":[26,36,60,75],"visual":[27],"fidelity,":[28],"they":[29],"often":[30],"struggle":[31],"balance":[33],"semantic":[34,58,81],"faithfulness":[35],"sample":[37],"diversity.":[38],"We":[39],"propose":[40],"new":[42],"framework":[44],"that":[45,88],"synthesizes":[46],"class-conditional":[47],"transparent":[48],"foregrounds":[49],"using":[50,56],"Stable":[51],"Diffusion,":[52],"filters":[53],"high-quality":[54],"samples":[55,78],"CLIP-based":[57],"similarity,":[59],"overlays":[61],"them":[62],"on":[63,84],"real":[64],"images":[65],"from":[66],"different":[67],"classes.":[68],"This":[69],"cross-class":[70],"composition":[71],"method":[72],"produces":[73],"complex":[74],"diverse":[76],"training":[77],"while":[79],"maintaining":[80],"consistency.":[82],"Experiments":[83],"fine-grained":[85],"datasets":[86],"demonstrate":[87],"our":[89],"approach":[90],"significantly":[91],"outperforms":[92],"traditional":[93],"baselines.":[95]},"counts_by_year":[],"updated_date":"2026-01-28T23:18:48.515280","created_date":"2026-01-28T00:00:00"}