{"id":"https://openalex.org/W3196371147","doi":"https://doi.org/10.1145/3460426.3463637","title":"Neural Symbolic Representation Learning for Image Captioning","display_name":"Neural Symbolic Representation Learning for Image Captioning","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3196371147","doi":"https://doi.org/10.1145/3460426.3463637","mag":"3196371147"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3463637","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 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/A5100457091","display_name":"Xiaomei Wang","orcid":"https://orcid.org/0000-0002-8190-5076"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaomei Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017116858","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-7331-6132"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Fu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Xue","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100457091"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.4803,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.64939542,"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":"312","last_page":"321"},"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":0.9912999868392944,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9912999868392944,"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":0.8953631520271301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7744866609573364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6166344285011292},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5559096932411194},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5095282196998596},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5092069506645203},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.49777987599372864},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4365781843662262},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4041309952735901},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33866727352142334},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.29902201890945435}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8953631520271301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7744866609573364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6166344285011292},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5559096932411194},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5095282196998596},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5092069506645203},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.49777987599372864},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4365781843662262},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4041309952735901},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33866727352142334},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29902201890945435},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460426.3463637","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1585497795","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1998020572","https://openalex.org/W2019004430","https://openalex.org/W2108598243","https://openalex.org/W2173180041","https://openalex.org/W2250378130","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2575842049","https://openalex.org/W2579549467","https://openalex.org/W2600463316","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2767577934","https://openalex.org/W2795151422","https://openalex.org/W2885013662","https://openalex.org/W2886970679","https://openalex.org/W2887585070","https://openalex.org/W2888166343","https://openalex.org/W2890531016","https://openalex.org/W2896426063","https://openalex.org/W2950579554","https://openalex.org/W2962681491","https://openalex.org/W2962799512","https://openalex.org/W2962918138","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963260436","https://openalex.org/W2963536419","https://openalex.org/W2963738360","https://openalex.org/W2963743213","https://openalex.org/W2963992143","https://openalex.org/W2965597639","https://openalex.org/W2965697393","https://openalex.org/W2968101724","https://openalex.org/W2979747405","https://openalex.org/W2981951787","https://openalex.org/W2981994675","https://openalex.org/W2982026686","https://openalex.org/W2982174019","https://openalex.org/W2982212456","https://openalex.org/W2986670728","https://openalex.org/W2990397898","https://openalex.org/W2992478697","https://openalex.org/W3035284526","https://openalex.org/W3103651098","https://openalex.org/W3105136412"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Traditional":[0],"image":[1,34,59,87,90,100,182,231],"captioning":[2,91,232],"models":[3],"mainly":[4],"rely":[5],"on":[6,198,227],"one":[7,12],"encoder-decoder":[8],"architecture":[9,21],"to":[10,27,55,77,101,213,216],"generate":[11],"natural":[13],"sentence":[14],"for":[15,88],"a":[16,98,175],"given":[17,99,181],"image.":[18,51],"Such":[19],"an":[20,109],"mostly":[22],"uses":[23],"deep":[24],"neural":[25,30,66,82,102,139,186,189,208],"networks":[26],"extract":[28],"the":[29,33,37,50,58,63,74,79,86,89,106,114,117,121,124,134,138,147,167,170,180,185,193,200,206,228],"representations":[31,67,151],"of":[32,39,81,85,108,169,179],"while":[35],"ignoring":[36],"information":[38],"abstractive":[40,70,118],"concepts":[41,119],"as":[42,44,152,154],"well":[43,153],"their":[45,155],"intertwined":[46],"relationships":[47,125],"conveyed":[48],"in":[49,105],"To":[52],"this":[53],"end,":[54],"comprehensively":[56],"characterize":[57],"content":[60],"and":[61,68,96,120,149,188,202],"bridge":[62],"gap":[64],"between":[65,126],"high-level":[69],"concepts,":[71],"we":[72],"make":[73],"first":[75,94],"attempt":[76],"investigate":[78],"ability":[80],"symbolic":[83,103,140,190,209],"representation":[84,104,141,187,210],"task.":[92,233],"We":[93],"parse":[95],"convert":[97],"form":[107],"attributed":[110,135],"relational":[111,136],"graph,":[112,137],"with":[113,146,192,219,224],"nodes":[115],"denoting":[116],"branches":[122],"indicating":[123],"connected":[127],"nodes,":[128],"respectively.":[129],"By":[130],"performing":[131],"computations":[132],"over":[133],"evolves":[142],"step":[143,160],"by":[144,161,183],"step,":[145],"node":[148],"branch":[150],"corresponding":[156],"importance":[157],"weights":[158],"transiting":[159],"step.":[162],"Empirically,":[163],"extensive":[164],"experiments":[165],"validate":[166],"effectiveness":[168],"proposed":[171,207],"method.":[172],"It":[173],"enables":[174],"more":[176],"comprehensive":[177],"understanding":[178],"integrating":[184],"representation,":[191],"state-of-the-art":[194],"results":[195],"being":[196],"achieved":[197],"both":[199],"MSCOCO":[201],"Flickr30k":[203],"datasets.":[204],"Besides,":[205],"is":[211],"demonstrated":[212],"better":[214],"generalize":[215],"other":[217],"domains":[218],"significant":[220],"performance":[221],"improvements":[222],"compared":[223],"existing":[225],"methods":[226],"cross":[229],"domain":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}