{"id":"https://openalex.org/W4283390379","doi":"https://doi.org/10.1145/3512527.3531379","title":"Improving Image Captioning via Enhancing Dual-Side Context Awareness","display_name":"Improving Image Captioning via Enhancing Dual-Side Context Awareness","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283390379","doi":"https://doi.org/10.1145/3512527.3531379"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531379","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","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/A5044936257","display_name":"Yiqi Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiqi Gao","raw_affiliation_strings":["Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387149","display_name":"Ning Wang","orcid":"https://orcid.org/0000-0002-4937-6784"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Wang","raw_affiliation_strings":["Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077386763","display_name":"Wei Suo","orcid":"https://orcid.org/0000-0002-8283-8637"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Suo","raw_affiliation_strings":["Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055917672","display_name":"Mengyang Sun","orcid":"https://orcid.org/0000-0003-0638-3295"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyang Sun","raw_affiliation_strings":["Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396097","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-9218-9132"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University & National Engineering Lab for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5044936257"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.0066,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76535157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"389","last_page":"397"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9977999925613403,"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":0.9968000054359436,"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":0.8304909467697144},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7546959519386292},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6880264282226562},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6539526581764221},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6500163078308105},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6152858734130859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5051150918006897},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42812857031822205},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38243287801742554},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1520032286643982},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09794861078262329},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07891371846199036},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07087311148643494}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304909467697144},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7546959519386292},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6880264282226562},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6539526581764221},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6500163078308105},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6152858734130859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5051150918006897},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42812857031822205},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38243287801742554},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1520032286643982},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09794861078262329},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07891371846199036},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07087311148643494},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512527.3531379","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4888510474","display_name":null,"funder_award_id":"No. U19B2037, No. 61876152","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5353464696","display_name":null,"funder_award_id":"No. 2021JCW-03","funder_id":"https://openalex.org/F4320336567","funder_display_name":"Natural Science Basic Research Program of Shaanxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336567","display_name":"Natural Science Basic Research Program of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2194775991","https://openalex.org/W2463955103","https://openalex.org/W2506483933","https://openalex.org/W2600463316","https://openalex.org/W2624317482","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2904551248","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W2998988444","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3035497460","https://openalex.org/W3102371147","https://openalex.org/W3167939936","https://openalex.org/W3175824375"],"related_works":["https://openalex.org/W2547835662","https://openalex.org/W4312845724","https://openalex.org/W4312545247","https://openalex.org/W4224046780","https://openalex.org/W1504288058","https://openalex.org/W4384210086","https://openalex.org/W2331674254","https://openalex.org/W4364297074","https://openalex.org/W2167293474","https://openalex.org/W3042897387"],"abstract_inverted_index":{"Recent":[0],"work":[1,11],"on":[2,17,33,50,179],"visual":[3],"question":[4],"answering":[5],"demonstrate":[6],"that":[7],"grid":[8,48,113,117],"features":[9],"can":[10],"as":[12,14,54,56],"well":[13,55],"region":[15,104,107],"feature":[16,49,118],"vision":[18],"language":[19],"tasks.":[20],"In":[21,73],"the":[22,37,43,51,57,64,97],"meantime,":[23],"transformer-based":[24],"model":[25],"and":[26,144,150,156],"its":[27],"variants":[28],"have":[29],"shown":[30],"remarkable":[31],"performance":[32],"image":[34],"captioning.":[35],"However,":[36],"object-contextual":[38],"information":[39,60,84,125,159],"missing":[40,61],"caused":[41],"by":[42,81],"single":[44],"granularity":[45],"nature":[46],"of":[47,68],"encoder":[52,88],"side,":[53,89,134],"future":[58,157],"contextual":[59,83,124,158],"due":[62],"to":[63],"left2right":[65,143],"decoding":[66,139,146],"paradigm":[67],"transformer":[69],"decoder,":[70],"remains":[71],"unexplored.":[72],"this":[74,115],"work,":[75],"we":[76,90,135],"tackle":[77],"these":[78,165],"two":[79,109,166],"problems":[80],"enhancing":[82],"at":[85,87,132],"dual-side:(i)":[86],"propose":[91],"Context-Aware":[92,173],"Self-Attention":[93],"module,":[94],"in":[95,141],"which":[96,142],"key/value":[98],"is":[99],"expanded":[100],"with":[101,119,128,168],"adjacent":[102],"rectangle":[103],"where":[105],"each":[106],"contains":[108],"or":[110],"more":[111],"aggregated":[112],"features;":[114],"enables":[116],"varying":[120],"granularity,":[121],"storing":[122],"adequate":[123],"for":[126],"object":[127],"different":[129],"scale.":[130],"(ii)":[131],"decoder":[133],"incorporate":[136],"a":[137,169,176],"dual-way":[138],"strategy,":[140],"right2left":[145],"are":[147],"conducted":[148],"simultaneously":[149],"interactively.":[151],"It":[152],"utilizes":[153],"both":[154],"past":[155],"when":[160],"generates":[161],"current":[162],"word.":[163],"Combining":[164],"modules":[167],"vanilla":[170],"transformer,":[171],"our":[172],"Transformer(CATNet)":[174],"achieves":[175],"new":[177],"state-of-the-art":[178],"MSCOCO":[180],"benchmark.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}