{"id":"https://openalex.org/W4415536238","doi":"https://doi.org/10.1145/3746027.3755838","title":"AFFIR: Dual-Modal Attention Feature Fusion for Scene Text Image Retargeting","display_name":"AFFIR: Dual-Modal Attention Feature Fusion for Scene Text Image Retargeting","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536238","doi":"https://doi.org/10.1145/3746027.3755838"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5101975457","display_name":"Gang Pan","orcid":"https://orcid.org/0000-0003-2155-4689"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gang Pan","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000148171","display_name":"Liming Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Pan","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114031956","display_name":"Haiting Mi","orcid":"https://orcid.org/0009-0003-5068-958X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongze Mi","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108441590","display_name":"Rihua Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongyu Xiong","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108891681","display_name":"Jiahao Wang","orcid":"https://orcid.org/0009-0000-5496-9720"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101797290","display_name":"Di Sun","orcid":"https://orcid.org/0000-0003-2793-7066"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Sun","raw_affiliation_strings":["College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin, China","institution_ids":["https://openalex.org/I132369690"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101975457"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30313297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5277","last_page":"5285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9988999962806702,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9988999962806702,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965999722480774,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9905999898910522,"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/seam-carving","display_name":"Seam carving","score":0.9343000054359436},{"id":"https://openalex.org/keywords/retargeting","display_name":"Retargeting","score":0.7314000129699707},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6154000163078308},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5562999844551086},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49149999022483826},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4641000032424927},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.45669999718666077},{"id":"https://openalex.org/keywords/clarity","display_name":"CLARITY","score":0.40290001034736633}],"concepts":[{"id":"https://openalex.org/C23746413","wikidata":"https://www.wikidata.org/wiki/Q1141379","display_name":"Seam carving","level":3,"score":0.9343000054359436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800000011920929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7664999961853027},{"id":"https://openalex.org/C2780575108","wikidata":"https://www.wikidata.org/wiki/Q7316652","display_name":"Retargeting","level":2,"score":0.7314000129699707},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6154000163078308},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5848000049591064},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.45669999718666077},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.3328000009059906},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.31220000982284546},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.30979999899864197},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1982471090","https://openalex.org/W2018377917","https://openalex.org/W2132610780","https://openalex.org/W2887779050","https://openalex.org/W2905365360","https://openalex.org/W3120524049"],"related_works":[],"abstract_inverted_index":{"Image":[0],"retargeting":[1,123,177],"technique":[2],"aims":[3],"to":[4,13,67,176],"adjust":[5],"and":[6,18,28,83,129,145,189,213],"reorganize":[7],"the":[8,40,48,70,78,87,92,98,109,121,161,168],"content":[9,191],"of":[10,51,72,80,86,100,111,179],"original":[11],"images":[12,27,178],"fit":[14],"different":[15],"display":[16],"sizes":[17],"visual":[19,84,215],"requirements.":[20],"Text":[21,128],"elements":[22],"frequently":[23],"appear":[24],"in":[25,33,57,125,170,208,226],"real-world":[26],"play":[29],"a":[30,43,115,137,156,219],"crucial":[31],"role":[32],"conveying":[34],"information.":[35],"Existing":[36],"algorithms":[37],"often":[38],"treat":[39],"image":[41,106,122,130,146,190],"as":[42],"whole":[44],"during":[45],"retargeting,":[46],"neglecting":[47],"unique":[49],"features":[50,131,147],"textual":[52,59,101,211],"content.":[53],"This":[54,172],"oversight":[55],"results":[56,163],"missing":[58],"information":[60,81,185],"or":[61],"distorted":[62],"character":[63],"structures,":[64],"ultimately":[65],"failing":[66],"effectively":[68],"preserve":[69],"integrity":[71],"text":[73,144,188],"regions,":[74],"thereby":[75],"affecting":[76],"both":[77,187,210],"efficiency":[79],"transmission":[82],"quality":[85],"final":[88],"image.":[89],"To":[90],"address":[91],"aforementioned":[93],"issues,":[94],"we":[95],"start":[96],"from":[97,186],"perception":[99],"content,":[102],"which":[103,142],"guides":[104],"retargeted":[105,162],"generation":[107],"through":[108,148],"fusion":[110,140],"attention":[112,149],"features.":[113],"Specifically,":[114],"Transformer-based":[116],"model":[117,169],"is":[118,174,192],"employed":[119],"for":[120,222],"tasks":[124],"this":[126],"study.":[127],"are":[132,164],"extracted":[133],"separately,":[134],"accompanied":[135],"by":[136],"dual-modal":[138],"feature":[139],"strategy,":[141,159],"integrates":[143],"maps":[150],"generated.":[151],"The":[152],"training":[153,158],"process":[154],"adopts":[155],"cyclic":[157],"where":[160],"fed":[165],"back":[166],"into":[167],"reverse.":[171],"approach":[173],"applicable":[175],"various":[180],"sizes,":[181],"ensuring":[182],"that":[183,201],"detailed":[184],"accurately":[193],"preserved.":[194],"Extensive":[195],"evaluations":[196],"on":[197],"benchmark":[198],"datasets":[199],"demonstrate":[200],"our":[202],"method":[203],"significantly":[204],"outperforms":[205],"existing":[206],"techniques":[207],"maintaining":[209],"clarity":[212],"overall":[214],"quality,":[216],"making":[217],"it":[218],"promising":[220],"solution":[221],"advanced":[223],"multimedia":[224],"applications":[225],"computer":[227],"science.":[228]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}