{"id":"https://openalex.org/W4386066029","doi":"https://doi.org/10.1109/cvpr52729.2023.00209","title":"Top-Down Visual Attention from Analysis by Synthesis","display_name":"Top-Down Visual Attention from Analysis by Synthesis","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386066029","doi":"https://doi.org/10.1109/cvpr52729.2023.00209"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.00209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5061008701","display_name":"Baifeng Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baifeng Shi","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100328059","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0003-0203-9964"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8174,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.9496671,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2102","last_page":"2112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9998000264167786,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8106671571731567},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5132236480712891},{"id":"https://openalex.org/keywords/top-down-and-bottom-up-design","display_name":"Top-down and bottom-up design","score":0.4976353943347931},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.44949576258659363},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4210907518863678},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33974123001098633},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3254256844520569}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106671571731567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5132236480712891},{"id":"https://openalex.org/C135798126","wikidata":"https://www.wikidata.org/wiki/Q2167279","display_name":"Top-down and bottom-up design","level":2,"score":0.4976353943347931},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.44949576258659363},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4210907518863678},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33974123001098633},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3254256844520569},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52729.2023.00209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":93,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1540330701","https://openalex.org/W1562206072","https://openalex.org/W1610424060","https://openalex.org/W1773149199","https://openalex.org/W1913473716","https://openalex.org/W1929281213","https://openalex.org/W1933349210","https://openalex.org/W1959608418","https://openalex.org/W2023941922","https://openalex.org/W2026799324","https://openalex.org/W2095903216","https://openalex.org/W2099169325","https://openalex.org/W2100495367","https://openalex.org/W2100543212","https://openalex.org/W2107909451","https://openalex.org/W2108598243","https://openalex.org/W2112845172","https://openalex.org/W2118615399","https://openalex.org/W2122896223","https://openalex.org/W2125663122","https://openalex.org/W2130641533","https://openalex.org/W2136922672","https://openalex.org/W2147336195","https://openalex.org/W2147990838","https://openalex.org/W2149166988","https://openalex.org/W2151189852","https://openalex.org/W2186094539","https://openalex.org/W2192027282","https://openalex.org/W2323067647","https://openalex.org/W2340897893","https://openalex.org/W2463565445","https://openalex.org/W2560730294","https://openalex.org/W2565639579","https://openalex.org/W2575842049","https://openalex.org/W2737258237","https://openalex.org/W2745461083","https://openalex.org/W2947707615","https://openalex.org/W2962884579","https://openalex.org/W2963656855","https://openalex.org/W2963954913","https://openalex.org/W2976482801","https://openalex.org/W2997574889","https://openalex.org/W2998222781","https://openalex.org/W3037492894","https://openalex.org/W3043068949","https://openalex.org/W3094502228","https://openalex.org/W3110437118","https://openalex.org/W3112172934","https://openalex.org/W3131500599","https://openalex.org/W3137278571","https://openalex.org/W3138516171","https://openalex.org/W3159481202","https://openalex.org/W3166396011","https://openalex.org/W3170863103","https://openalex.org/W3177096435","https://openalex.org/W3190965961","https://openalex.org/W3211774562","https://openalex.org/W3213601271","https://openalex.org/W4214636423","https://openalex.org/W4224949214","https://openalex.org/W4225088380","https://openalex.org/W4247181578","https://openalex.org/W4288404646","https://openalex.org/W4307929721","https://openalex.org/W4309793872","https://openalex.org/W4312443924","https://openalex.org/W4312784228","https://openalex.org/W4312957757","https://openalex.org/W4313156423","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6640963894","https://openalex.org/W6676288269","https://openalex.org/W6679553861","https://openalex.org/W6681096077","https://openalex.org/W6719057275","https://openalex.org/W6739901393","https://openalex.org/W6757555829","https://openalex.org/W6763468762","https://openalex.org/W6774790973","https://openalex.org/W6780466186","https://openalex.org/W6783944145","https://openalex.org/W6784333009","https://openalex.org/W6790555728","https://openalex.org/W6791353385","https://openalex.org/W6796761347","https://openalex.org/W6797578546","https://openalex.org/W6799838802","https://openalex.org/W6803189269","https://openalex.org/W6810876023","https://openalex.org/W6811002592","https://openalex.org/W6846552135"],"related_works":["https://openalex.org/W1543048115","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W22958017","https://openalex.org/W2469287711","https://openalex.org/W4205302943","https://openalex.org/W2438475373","https://openalex.org/W2119949815","https://openalex.org/W2561132942"],"abstract_inverted_index":{"Current":[0],"attention":[1,24,42,60,77],"algorithms":[2],"(e.g.,":[3],"self-attention)":[4],"are":[5],"stimulus-driven":[6],"and":[7,46,78,123,142,165],"highlight":[8],"all":[9],"the":[10,27,48,148],"salient":[11],"objects":[12],"in":[13],"an":[14,84],"image.":[15],"However,":[16],"intelligent":[17],"agents":[18],"like":[19],"humans":[20],"often":[21],"guide":[22],"their":[23],"based":[25],"on":[26,34,136,161],"high-level":[28],"task":[29],"at":[30],"hand,":[31],"focusing":[32],"only":[33],"task-related":[35],"objects.":[36],"This":[37],"ability":[38],"of":[39,67],"task-guided":[40],"top-down":[41,59,99,103,115,126,149],"provides":[43],"task-adaptive":[44],"representation":[45],"helps":[47],"model":[49,118,166],"generalize":[50],"to":[51],"various":[52],"tasks.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,81],"consider":[58],"from":[61],"a":[62,72,90,97,114,156],"classic":[63],"Analysis-by-Synthesis":[64,108],"(AbS)":[65],"perspective":[66],"vision.":[68],"Prior":[69],"work":[70],"indicates":[71],"functional":[73],"equivalence":[74],"between":[75],"visual":[76,86],"sparse":[79,92],"reconstruction;":[80],"show":[82],"that":[83,88,119],"AbS":[85],"system":[87],"optimizes":[89],"similar":[91],"reconstruction":[93],"objective":[94],"modulated":[95,116],"by":[96],"goal-directed":[98],"signal":[100],"naturally":[101],"simulates":[102],"attention.":[104,127,150],"We":[105],"further":[106],"propose":[107],"Vision":[109],"Transformer":[110],"(AbSViT),":[111],"which":[112],"is":[113],"ViT":[117],"variationally":[120],"approximates":[121],"AbS,":[122],"achieves":[124],"controllable":[125],"For":[128],"real-world":[129],"applications,":[130],"AbSViT":[131,151],"consistently":[132],"improves":[133],"over":[134],"baselines":[135],"Vision-Language":[137],"tasks":[138],"such":[139],"as":[140,155],"VQA":[141],"zero-shot":[143],"retrieval":[144],"where":[145],"language":[146],"guides":[147],"can":[152],"also":[153],"serve":[154],"general":[157],"backbone,":[158],"improving":[159],"performance":[160],"classification,":[162],"semantic":[163],"segmentation,":[164],"robustness.":[167],"Project":[168],"page:":[169],"https://sites.google.com/view/absvit.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}