{"id":"https://openalex.org/W3093363913","doi":"https://doi.org/10.1145/3394171.3414008","title":"Exploring Language Prior for Mode-Sensitive Visual Attention Modeling","display_name":"Exploring Language Prior for Mode-Sensitive Visual Attention Modeling","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093363913","doi":"https://doi.org/10.1145/3394171.3414008","mag":"3093363913"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3414008","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3414008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086915673","display_name":"Xuying Zhang","orcid":"https://orcid.org/0009-0009-3070-8767"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuying Zhang","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014628588","display_name":"Liujuan Cao","orcid":"https://orcid.org/0000-0002-7645-9606"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liujuan Cao","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716576","display_name":"Yongjian Wu","orcid":"https://orcid.org/0000-0003-2007-6929"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjian Wu","raw_affiliation_strings":["Youtu Lab, Tencent, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent, Xiamen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112601777","display_name":"Feiyue Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyue Huang","raw_affiliation_strings":["Youtu Lab, Tencent, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent, Xiamen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4199","last_page":"4207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.996999979019165,"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/closed-captioning","display_name":"Closed captioning","score":0.8776470422744751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8546725511550903},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.6103436946868896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.55784672498703},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.532439112663269},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5179771184921265},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5056030750274658},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4700835049152374},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.45265454053878784},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42562389373779297},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4251704812049866},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33247846364974976},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23351752758026123}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8776470422744751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8546725511550903},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.6103436946868896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.55784672498703},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.532439112663269},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5179771184921265},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5056030750274658},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4700835049152374},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.45265454053878784},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42562389373779297},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4251704812049866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33247846364974976},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23351752758026123},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3414008","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3414008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1934890906","https://openalex.org/W2055111849","https://openalex.org/W2064675550","https://openalex.org/W2086791339","https://openalex.org/W2133589685","https://openalex.org/W2138046011","https://openalex.org/W2139047169","https://openalex.org/W2144764737","https://openalex.org/W2192271525","https://openalex.org/W2288514685","https://openalex.org/W2336525740","https://openalex.org/W2378845821","https://openalex.org/W2738450183","https://openalex.org/W2745461083","https://openalex.org/W2753232960","https://openalex.org/W2884775172","https://openalex.org/W2895420168","https://openalex.org/W2962159375","https://openalex.org/W2969316698"],"related_works":["https://openalex.org/W4320016076","https://openalex.org/W2795359650","https://openalex.org/W2783914607","https://openalex.org/W4307856881","https://openalex.org/W2901467237","https://openalex.org/W2911868273","https://openalex.org/W2547835662","https://openalex.org/W3183824823","https://openalex.org/W3008515501","https://openalex.org/W2997279317"],"abstract_inverted_index":{"Modeling":[0],"human":[1,13],"visual":[2,33,70],"attention":[3,59,82,105,128],"mechanism":[4],"is":[5],"a":[6,41,84,103,131],"fundamental":[7],"problem":[8],"for":[9,24,45,99,118],"the":[10,49,54,66,69,72,75,78,93,100,113,139,146,149],"understanding":[11],"of":[12,58,81,102,115,148],"vision,":[14],"which":[15,90],"has":[16],"also":[17],"been":[18],"demonstrated":[19],"as":[20,29],"an":[21,124],"important":[22],"module":[23],"various":[25],"multimedia":[26],"applications":[27],"such":[28],"image":[30],"captioning":[31,97],"and":[32,47,56,77,121,142],"question":[34],"answering.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39,91],"propose":[40],"new":[42],"probabilistic":[43],"framework":[44,110],"attention,":[46],"introduce":[48],"concept":[50],"ofmode":[51],"to":[52,130],"model":[53,86,129],"flexibility":[55],"adaptability":[57],"modulation":[60],"in":[61],"complex":[62],"environments.":[63],"We":[64],"characterize":[65],"correlations":[67],"between":[68],"input,":[71],"activated":[73],"mode,":[74],"saliency":[76],"spatial":[79],"allocation":[80],"via":[83],"graphical":[85],"representation,":[87],"based":[88],"on":[89,138],"explore":[92],"lingual":[94],"guidance":[95],"from":[96],"data":[98],"implementation":[101],"mode-sensitive":[104],"(MSA)":[106],"model.":[107],"The":[108],"proposed":[109,150],"explicitly":[111],"justifies":[112],"usage":[114],"center":[116],"bias":[117],"fixation":[119],"prediction":[120],"can":[122],"convert":[123],"arbitrary":[125],"learning-based":[126],"backbone":[127],"more":[132],"robust":[133],"multi-mode":[134],"version.":[135],"Experimental":[136],"results":[137],"York120,":[140],"MIT1003":[141],"PASCAL":[143],"datasets":[144],"demonstrate":[145],"effectiveness":[147],"method.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}