{"id":"https://openalex.org/W4402980567","doi":"https://doi.org/10.1109/icme57554.2024.10687765","title":"Top-Down Guidance Based ViT-CNN Network Considering Theme Information for Image Aesthetic Assessment","display_name":"Top-Down Guidance Based ViT-CNN Network Considering Theme Information for Image Aesthetic Assessment","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980567","doi":"https://doi.org/10.1109/icme57554.2024.10687765"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5036035213","display_name":"Sumei Li","orcid":"https://orcid.org/0000-0002-4793-3161"},"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":"Sumei Li","raw_affiliation_strings":["Tianjin University,School of Electrical and Information Engineering,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,School of Electrical and Information Engineering,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595042","display_name":"Xiaofei He","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":"Xiaofei He","raw_affiliation_strings":["Tianjin University,School of Electrical and Information Engineering,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,School of Electrical and Information Engineering,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111346949","display_name":"Hangwei Liang","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":"Hangwei Liang","raw_affiliation_strings":["Tianjin University,School of Electrical and Information Engineering,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,School of Electrical and Information Engineering,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036035213"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.643,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79467319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14254","display_name":"Digital Media and Visual Art","score":0.9451000094413757,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T14254","display_name":"Digital Media and Visual Art","score":0.9451000094413757,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.9406999945640564,"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/theme","display_name":"Theme (computing)","score":0.7448896169662476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6833717823028564},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5472332239151001},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4108114540576935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3659830093383789},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3561892509460449},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32903265953063965},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1859152913093567}],"concepts":[{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.7448896169662476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833717823028564},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5472332239151001},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4108114540576935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3659830093383789},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3561892509460449},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32903265953063965},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1859152913093567}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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":24,"referenced_works":["https://openalex.org/W1511924373","https://openalex.org/W1994739392","https://openalex.org/W2019377328","https://openalex.org/W2078807908","https://openalex.org/W2604528050","https://openalex.org/W2754213847","https://openalex.org/W2897926040","https://openalex.org/W2904572228","https://openalex.org/W2931027027","https://openalex.org/W2963163009","https://openalex.org/W3003957020","https://openalex.org/W3093185587","https://openalex.org/W3171472210","https://openalex.org/W4214745154","https://openalex.org/W4214932255","https://openalex.org/W4285606417","https://openalex.org/W4293057409","https://openalex.org/W4312353506","https://openalex.org/W4322576760","https://openalex.org/W4379034640","https://openalex.org/W4385245566","https://openalex.org/W4385444101","https://openalex.org/W4386159014","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W1876039949","https://openalex.org/W2351167057","https://openalex.org/W570509144","https://openalex.org/W2356772582","https://openalex.org/W1499778516","https://openalex.org/W4200264008","https://openalex.org/W2739095861","https://openalex.org/W1992606257","https://openalex.org/W2356359262","https://openalex.org/W2335128010"],"abstract_inverted_index":{"Image":[0],"Aesthetic":[1],"Assessment":[2],"(IAA)":[3],"is":[4,9,75,130],"a":[5,29,49,66],"challenging":[6],"task":[7],"that":[8,146],"closely":[10],"tied":[11],"to":[12,77,89,114,132],"human":[13],"aesthetic":[14,116],"experience.":[15],"In":[16,95],"this":[17],"paper,":[18],"inspired":[19],"by":[20],"Top-Down":[21,30],"guidance":[22,40,72,81],"and":[23,59,68,136,153],"visual":[24,137],"attention":[25,71],"mechanism,":[26],"we":[27,47],"propose":[28],"Guidance":[31],"based":[32],"ViT-CNN":[33],"network":[34,51,105],"considering":[35,97],"theme":[36,101,109,121,125,134],"information.":[37],"Considering":[38],"the":[39,80,98,103,147],"of":[41,55,85,92,100],"global":[42,67,83],"information":[43,110,113],"on":[44],"local":[45,69,90],"information,":[46,102,122],"construct":[48],"two-stream":[50],"structure.":[52],"It":[53],"consists":[54],"Vision":[56],"Transformer":[57],"(ViT)":[58],"Convolutional":[60],"Neural":[61],"Network":[62],"(CNN)":[63],"streams.":[64],"Meanwhile,":[65],"feature":[70,126],"module":[73,128],"(GLFAGM)":[74],"proposed":[76,104,131,148],"better":[78,119,151],"realize":[79],"from":[82,139],"features":[84,91,135,138],"ViT":[86],"stream":[87],"down":[88],"CNN":[93,140],"stream.":[94,141],"addition,":[96],"importance":[99],"utilizes":[106],"more":[107],"comprehensive":[108],"as":[111],"auxiliary":[112],"achieve":[115],"assessment.":[117],"To":[118],"utilize":[120],"an":[123],"attentionbased":[124],"fusion":[127],"(ATFFM)":[129],"integrate":[133],"The":[142],"experimental":[143],"results":[144],"show":[145],"method":[149],"achieves":[150],"performance":[152],"outperforms":[154],"some":[155],"state-of-the-art":[156],"methods.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}