{"id":"https://openalex.org/W4410859483","doi":"https://doi.org/10.1145/3708657.3708748","title":"Controllable and Diverse Image Captioning via Keyword-Driven Diffusion Networks","display_name":"Controllable and Diverse Image Captioning via Keyword-Driven Diffusion Networks","publication_year":2024,"publication_date":"2024-11-21","ids":{"openalex":"https://openalex.org/W4410859483","doi":"https://doi.org/10.1145/3708657.3708748"},"language":"en","primary_location":{"id":"doi:10.1145/3708657.3708748","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708657.3708748","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3708657.3708748","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 10th International Conference on Communication and Information Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3708657.3708748","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022809356","display_name":"Mingxuan Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingxuan Pan","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China, and Beijing National Research Center for Information Science and Technology (BNRist), Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China, and Beijing National Research Center for Information Science and Technology (BNRist), Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346266","display_name":"Yali Li","orcid":"https://orcid.org/0000-0002-6629-7228"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yali Li","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China, and Beijing National Research Center for Information Science and Technology (BNRist), Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China, and Beijing National Research Center for Information Science and Technology (BNRist), Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019612977","display_name":"Simin Li","orcid":"https://orcid.org/0000-0001-6355-2978"},"institutions":[{"id":"https://openalex.org/I2801345734","display_name":"China Academy of Engineering Physics","ror":"https://ror.org/039vqpp67","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2801345734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simin Li","raw_affiliation_strings":["Institute of Electronic Engineering, China Academy of Engineering Physics, Mianyang, Sichuan, China"],"affiliations":[{"raw_affiliation_string":"Institute of Electronic Engineering, China Academy of Engineering Physics, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I2801345734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030965866","display_name":"Shengjin Wang","orcid":"https://orcid.org/0000-0001-7809-1932"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengjin Wang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China, and Beijing National Research Center for Information Science and Technology (BNRist), Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, Beijing, China, and Beijing National Research Center for Information Science and Technology (BNRist), Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022809356"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31261055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"555","last_page":"563"},"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":0.9987000226974487,"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":0.9904000163078308,"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":0.9578742980957031},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7337252497673035},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6232568621635437},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5733940601348877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.390522837638855},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33387789130210876}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9578742980957031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7337252497673035},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6232568621635437},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5733940601348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.390522837638855},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33387789130210876},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3708657.3708748","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708657.3708748","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3708657.3708748","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 10th International Conference on Communication and Information Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3708657.3708748","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3708657.3708748","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3708657.3708748","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 10th International Conference on Communication and Information Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410859483.pdf","grobid_xml":"https://content.openalex.org/works/W4410859483.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2896348597","https://openalex.org/W2954841306","https://openalex.org/W2962968835","https://openalex.org/W2986670728","https://openalex.org/W2997591391","https://openalex.org/W3034655362","https://openalex.org/W3115793887","https://openalex.org/W3170494780","https://openalex.org/W3174046981","https://openalex.org/W3205981128","https://openalex.org/W3210150990","https://openalex.org/W4213019668","https://openalex.org/W4288073012","https://openalex.org/W4372260594","https://openalex.org/W4386072307"],"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":{"Image":[0],"captioning":[1,36],"is":[2],"the":[3,23,29],"task":[4],"of":[5,31],"understanding":[6,27],"visual":[7],"elements":[8],"and":[9,15,28,50],"their":[10],"relationships":[11],"in":[12,18,25],"an":[13],"image":[14,26,35],"expressing":[16],"them":[17],"natural":[19],"language.However,":[20],"due":[21],"to":[22,46],"ambiguity":[24],"diversity":[30],"language":[32],"expressions,":[33],"current":[34],"models,":[37],"which":[38],"are":[39],"primarily":[40],"based":[41],"on":[42],"autoregressive":[43],"methods,":[44],"struggle":[45],"generate":[47],"richer":[48],"descriptions":[49],"often":[51],"deviate":[52],"from":[53],"ICCIP":[54],"2024,":[55,58],"November":[56],"21-24,":[57],"Lingshui,":[59],"China":[60]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
