{"id":"https://openalex.org/W4283375995","doi":"https://doi.org/10.1145/3512527.3531401","title":"Improve Image Captioning by Modeling Dynamic Scene Graph Extension","display_name":"Improve Image Captioning by Modeling Dynamic Scene Graph Extension","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4283375995","doi":"https://doi.org/10.1145/3512527.3531401"},"language":"en","primary_location":{"id":"doi:10.1145/3512527.3531401","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531401","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":"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/A5082756665","display_name":"Minghao Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghao Geng","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044948606","display_name":"Qingjie Zhao","orcid":"https://orcid.org/0000-0002-6955-4170"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingjie Zhao","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.3698,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66139081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"398","last_page":"406"},"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":0.9934999942779541,"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":0.9869999885559082,"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/closed-captioning","display_name":"Closed captioning","score":0.8345065116882324},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8118699789047241},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.7700773477554321},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6603571772575378},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.658708930015564},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5360169410705566},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5190904140472412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48157691955566406},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41693758964538574},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3619510531425476},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.32706159353256226},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3087688386440277}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8345065116882324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8118699789047241},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.7700773477554321},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6603571772575378},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.658708930015564},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5360169410705566},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5190904140472412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48157691955566406},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41693758964538574},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3619510531425476},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32706159353256226},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3087688386440277},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/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":1,"locations":[{"id":"doi:10.1145/3512527.3531401","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512527.3531401","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":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1593271688","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2077069816","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2575842049","https://openalex.org/W2600463316","https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963184176","https://openalex.org/W2963536419","https://openalex.org/W2965597639","https://openalex.org/W2986670728","https://openalex.org/W3034538190","https://openalex.org/W3034655362","https://openalex.org/W3034733309","https://openalex.org/W3034984754","https://openalex.org/W3035017890","https://openalex.org/W3035284526","https://openalex.org/W3035531911","https://openalex.org/W3093088671","https://openalex.org/W3103651098","https://openalex.org/W3175824375"],"related_works":["https://openalex.org/W2547835662","https://openalex.org/W2743087755","https://openalex.org/W4283375995","https://openalex.org/W4281560470","https://openalex.org/W2952688802","https://openalex.org/W4289542422","https://openalex.org/W3093329502","https://openalex.org/W4309636587","https://openalex.org/W4224251870","https://openalex.org/W4319792240"],"abstract_inverted_index":{"Recently,":[0],"scene":[1,41,53,71,91,99,132],"graph":[2,29,42,54,72,92,114,133],"generation":[3],"methods":[4,38],"have":[5],"been":[6],"used":[7],"in":[8,18,124,158],"image":[9,135],"captioning":[10,136],"to":[11,40,67,94,115,130],"encode":[12],"the":[13,19,23,28,49,69,75,83,112,117,140,150,155],"objects":[14,104],"and":[15,86],"their":[16],"relationships":[17,106],"encoder-decoder":[20],"framework,":[21],"where":[22],"decoder":[24],"selects":[25],"part":[26],"of":[27,90],"nodes":[30,93],"as":[31],"input":[32],"for":[33],"word":[34],"inference.":[35],"However,":[36],"current":[37],"attend":[39],"relying":[43],"on":[44,143],"ambiguous":[45],"language":[46],"information,":[47],"neglecting":[48],"strong":[50],"connections":[51],"between":[52],"nodes.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,102],"propose":[60],"a":[61,97,159],"Scene":[62],"Graph":[63],"Extension":[64],"(SGE)":[65],"architecture":[66],"model":[68,80],"dynamic":[70],"extension":[73],"using":[74],"partly":[76],"generated":[77,84,113],"sentence.":[78],"Our":[79,120],"first":[81],"uses":[82],"words":[85],"previous":[87],"attention":[88],"results":[89,147],"make":[95],"up":[96],"partial":[98],"graph.":[100],"Then":[101],"choose":[103],"or":[105],"that":[107,126,149],"has":[108],"close":[109],"connection":[110],"with":[111],"infer":[116],"next":[118],"word.":[119],"SGE":[121,152],"is":[122,128],"appealing":[123],"view":[125],"it":[127],"pluggable":[129],"any":[131],"based":[134],"method.":[137],"We":[138],"conduct":[139],"extensive":[141],"experiments":[142],"MSCOCO":[144],"dataset.":[145],"The":[146],"shows":[148],"proposed":[151],"significantly":[153],"outperforms":[154],"baselines,":[156],"resulting":[157],"state-of-the-art":[160],"performance":[161],"under":[162],"most":[163],"metrics.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}