{"id":"https://openalex.org/W4306317683","doi":"https://doi.org/10.1145/3511808.3557382","title":"Look Twice as Much as You Say","display_name":"Look Twice as Much as You Say","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317683","doi":"https://doi.org/10.1145/3511808.3557382"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557382","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557382","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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/A5100390391","display_name":"Chunhui Zhang","orcid":"https://orcid.org/0000-0002-6380-3340"},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chunhui Zhang","raw_affiliation_strings":["Brandeis University, Waltham, MA, USA"],"affiliations":[{"raw_affiliation_string":"Brandeis University, Waltham, MA, USA","institution_ids":["https://openalex.org/I6902469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091518548","display_name":"Chao Huang","orcid":"https://orcid.org/0009-0003-3740-4500"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chao Huang","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103745727","display_name":"Youhuan Li","orcid":"https://orcid.org/0000-0002-0650-0458"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youhuan Li","raw_affiliation_strings":["Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000755750","display_name":"Xiangliang Zhang","orcid":"https://orcid.org/0000-0002-3574-5665"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangliang Zhang","raw_affiliation_strings":["University of Notre Dame, South Bend, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, South Bend, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586436","display_name":"Yanfang Ye","orcid":"https://orcid.org/0000-0001-8376-7239"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanfang Ye","raw_affiliation_strings":["University of Notre Dame, South Bend, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, South Bend, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022275632","display_name":"Chuxu Zhang","orcid":"https://orcid.org/0000-0002-8349-7926"},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuxu Zhang","raw_affiliation_strings":["Brandeis University, Waltham, MA, USA"],"affiliations":[{"raw_affiliation_string":"Brandeis University, Waltham, MA, USA","institution_ids":["https://openalex.org/I6902469"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100390391"],"corresponding_institution_ids":["https://openalex.org/I6902469"],"apc_list":null,"apc_paid":null,"fwci":0.2397,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58498503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2519","last_page":"2528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9891999959945679,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9872999787330627,"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/computer-science","display_name":"Computer science","score":0.8516983389854431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6802781820297241},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6612517833709717},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4727918803691864},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4705786108970642},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4649461805820465},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4552416503429413},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44559410214424133},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.42406490445137024},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.42390161752700806},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4102303385734558},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3999258577823639},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3973885774612427},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.360001802444458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8516983389854431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6802781820297241},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6612517833709717},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4727918803691864},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4705786108970642},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4649461805820465},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4552416503429413},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44559410214424133},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.42406490445137024},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.42390161752700806},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4102303385734558},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3999258577823639},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3973885774612427},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.360001802444458},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3511808.3557382","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557382","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:hub.hku.hk:10722/320896","is_oa":false,"landing_page_url":"https://hub.hku.hk/handle/10722/320896","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference_Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1975577448","display_name":null,"funder_award_id":"2018-75-CX- 0032","funder_id":"https://openalex.org/F4320337430","funder_display_name":"National Institute of Justice"},{"id":"https://openalex.org/G950613815","display_name":null,"funder_award_id":"IIS- 2209814","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337430","display_name":"National Institute of Justice","ror":"https://ror.org/00v8p7w89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W2077069816","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2745461083","https://openalex.org/W2963048642","https://openalex.org/W2963101956","https://openalex.org/W2963170456","https://openalex.org/W2963743213","https://openalex.org/W2965857891","https://openalex.org/W3034655362","https://openalex.org/W3034733309","https://openalex.org/W3034984754","https://openalex.org/W3036446966","https://openalex.org/W3099152386","https://openalex.org/W3107848485","https://openalex.org/W3153332739","https://openalex.org/W3153965221","https://openalex.org/W3173955760","https://openalex.org/W3174377922","https://openalex.org/W3200170138","https://openalex.org/W4285601291"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Images":[0],"are":[1],"commonly":[2],"used":[3],"for":[4,39,47,85,205],"various":[5],"information":[6,114],"and":[7,13,32,94,104,112,130,159,177,228],"knowledge":[8],"applications,":[9],"such":[10],"as":[11,30,34,69,118,141,154],"advertising":[12],"recommendation.":[14],"Automating":[15],"image":[16,22,29,48,87,117,207],"caption":[17,49,88,208],"generation":[18,103,209],"will":[19],"significantly":[20],"improve":[21],"accessibility.":[23],"This":[24],"cross-modal":[25],"task,":[26],"which":[27,57,65,190],"takes":[28],"input":[31],"text":[33,140,184],"output,":[35],"however,":[36],"is":[37,134,198],"difficult":[38],"learning.":[40,169],"Though":[41],"prior":[42],"methods":[43],"achieve":[44],"good":[45],"performance":[46],"generation,":[50],"they":[51],"rely":[52],"on":[53,126,217],"either":[54],"supervised":[55,227],"learning":[56,64,146],"requires":[58],"sufficient":[59],"labeled":[60,213],"data":[61],"or":[62],"unsupervised":[63],"needs":[66],"external":[67],"dataset":[68,219],"language":[70],"pivot.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75,98,149,171,200],"propose":[76],"SGCL,":[77,148],"a":[78,122],"novel":[79],"Scene":[80],"Graph":[81],"Contrastive":[82],"Learning":[83],"model":[84,162,192,204],"self-supervised":[86],"generation.":[89],"SGCL":[90,222],"adopts":[91],"the":[92,116,161,173,178,183,187,195,203,206],"pre-training":[93,196],"fine-tuning":[95],"pipeline.":[96],"Specifically,":[97],"first":[99],"apply":[100],"scene":[101,110,151],"graph":[102,111,127,152],"objection":[105],"detection":[106],"method":[107],"to":[108,137,181],"encode":[109],"visual":[113],"in":[115,147,186],"feature":[119],"representation.":[120],"Later,":[121],"decoder":[123,188],"network":[124,129,133],"based":[125],"attention":[128],"recurrent":[131],"neural":[132],"further":[135,201],"designed":[136],"generate":[138],"sequential":[139],"caption.":[142],"To":[143],"enable":[144],"contrastive":[145,155,168],"design":[150],"augmentations":[153],"views":[156],"of":[157],"images":[158],"train":[160],"effectively":[163],"without":[164],"ground-truth":[165],"labels":[166],"through":[167],"Additionally,":[170],"introduce":[172],"pre-trained":[174],"word":[175],"embedding":[176],"context":[179],"projector":[180],"enrich":[182],"representation":[185],"network,":[189],"benefits":[191],"pre-training.":[193],"Once":[194],"phase":[197],"finished,":[199],"fine-tune":[202],"task":[210],"with":[211],"limited":[212],"data.":[214],"Extensive":[215],"experiments":[216],"benchmark":[218],"demonstrate":[220],"that":[221],"outperforms":[223],"state-of-the-art":[224],"models":[225],"(both":[226],"unsupervised).":[229]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}