{"id":"https://openalex.org/W4404032492","doi":"https://doi.org/10.1109/icccnt61001.2024.10724421","title":"Enhancing Image Representation for Caption Generation Using Graph Convolutional Networks","display_name":"Enhancing Image Representation for Caption Generation Using Graph Convolutional Networks","publication_year":2024,"publication_date":"2024-06-24","ids":{"openalex":"https://openalex.org/W4404032492","doi":"https://doi.org/10.1109/icccnt61001.2024.10724421"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt61001.2024.10724421","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icccnt61001.2024.10724421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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/A5067077845","display_name":"P.S Pavan","orcid":null},"institutions":[{"id":"https://openalex.org/I106826634","display_name":"Jain University","ror":"https://ror.org/01cnqpt53","country_code":"IN","type":"education","lineage":["https://openalex.org/I106826634"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"P.S Pavan","raw_affiliation_strings":["JAIN (Deemed to be University),School of Engineering and Technology,Department of Civil Engineering,Bangalore,Karnataka,India"],"affiliations":[{"raw_affiliation_string":"JAIN (Deemed to be University),School of Engineering and Technology,Department of Civil Engineering,Bangalore,Karnataka,India","institution_ids":["https://openalex.org/I106826634"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090944141","display_name":"Rupa Sarkar","orcid":"https://orcid.org/0000-0003-0014-2239"},"institutions":[{"id":"https://openalex.org/I106826634","display_name":"Jain University","ror":"https://ror.org/01cnqpt53","country_code":"IN","type":"education","lineage":["https://openalex.org/I106826634"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rupa Sarkar","raw_affiliation_strings":["ARKA JAIN University,Department of English,Jamshedpur,Jharkhand,India"],"affiliations":[{"raw_affiliation_string":"ARKA JAIN University,Department of English,Jamshedpur,Jharkhand,India","institution_ids":["https://openalex.org/I106826634"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019403525","display_name":"Deeplata Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125057","display_name":"Vivekananda Global University","ror":"https://ror.org/038mz4r36","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210125057"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Deeplata Sharma","raw_affiliation_strings":["Vivekananda Global University,Department of Chemistry,Jaipur,India"],"affiliations":[{"raw_affiliation_string":"Vivekananda Global University,Department of Chemistry,Jaipur,India","institution_ids":["https://openalex.org/I4210125057"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067077845"],"corresponding_institution_ids":["https://openalex.org/I106826634"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19657715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9983000159263611,"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":0.9962000250816345,"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":0.7910626530647278},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5912298560142517},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5771188139915466},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5385614037513733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5225505232810974},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3418717086315155},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.24054384231567383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910626530647278},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5912298560142517},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5771188139915466},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5385614037513733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5225505232810974},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3418717086315155},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.24054384231567383},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccnt61001.2024.10724421","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icccnt61001.2024.10724421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W4251905560","https://openalex.org/W4312309345","https://openalex.org/W4367396320","https://openalex.org/W4379163448","https://openalex.org/W4379792233","https://openalex.org/W4383265267","https://openalex.org/W4383428982","https://openalex.org/W4385769909","https://openalex.org/W4385848185","https://openalex.org/W4389445914","https://openalex.org/W4396918479","https://openalex.org/W4409147225"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Graph":[0],"convolutional":[1,51],"networks":[2,52],"(GCNs)":[3,53],"have":[4],"emerged":[5],"as":[6],"an":[7],"effective":[8],"approach":[9],"for":[10,25,104],"photograph":[11,45,133],"illustration":[12,46,72],"and":[13,54,106,137],"caption-era":[14],"obligations.":[15],"In":[16],"this":[17,146],"paper,":[18],"we":[19],"gift":[20],"a":[21,34,43,55],"singular":[22],"GCN":[23],"architecture":[24,38,110],"photo":[26,71],"caption":[27,56,77],"technology":[28],"that":[29,97,108,117],"models":[30],"visible":[31],"relationships":[32],"in":[33,82,145],"photo.":[35],"The":[36],"proposed":[37],"consists":[39],"of":[40,85,123,128,141],"essential":[41],"additives:":[42],"kernel-based":[44],"based":[47,59],"totally":[48],"on":[49,60,93],"graph":[50],"generator":[57],"primarily":[58],"the":[61,69,76,83,99,120,126,139],"generated":[62,70],"picture":[63],"representation.":[64],"To":[65],"generate":[66,102],"image":[67],"captions,":[68],"is":[73,80],"fed":[74],"to":[75,101],"generator,":[78],"which":[79],"skilled":[81],"use":[84,127],"supervised":[86],"brand":[87],"new.":[88],"We":[89],"compare":[90],"our":[91,109],"method":[92],"commonly":[94],"used":[95],"datasets":[96],"require":[98],"ability":[100],"captions":[103],"pix":[105],"demonstrate":[107],"achieves":[111],"overall":[112,135],"performance.":[113],"Our":[114],"outcomes":[115],"show":[116],"by":[118],"exploiting":[119],"nearby":[121],"structure":[122],"modern-day":[124],"images,":[125],"GCNs":[129],"can":[130],"successfully":[131],"improve":[132],"captioning":[134],"performance":[136],"imply":[138],"path":[140],"state-of-the-art":[142],"future":[143],"research":[144],"field.":[147]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}