{"id":"https://openalex.org/W3090108315","doi":"https://doi.org/10.1109/icarm49381.2020.9195335","title":"Modeling coherence and diversity for image paragraph captioning","display_name":"Modeling coherence and diversity for image paragraph captioning","publication_year":2020,"publication_date":"2020-09-14","ids":{"openalex":"https://openalex.org/W3090108315","doi":"https://doi.org/10.1109/icarm49381.2020.9195335","mag":"3090108315"},"language":"en","primary_location":{"id":"doi:10.1109/icarm49381.2020.9195335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm49381.2020.9195335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","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/A5083237219","display_name":"Xiangheng He","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangheng He","raw_affiliation_strings":["School of Automation, Control Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Control Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010863275","display_name":"Xinde Li","orcid":"https://orcid.org/0000-0002-1529-4537"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinde Li","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.1709,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47440209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"242","issue":null,"first_page":"634","last_page":"639"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9866999983787537,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.982699990272522,"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":0.9253326654434204},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.9176143407821655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8039633631706238},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7800672054290771},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6021984219551086},{"id":"https://openalex.org/keywords/repetition","display_name":"Repetition (rhetorical device)","score":0.5690052509307861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5689358115196228},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4973650276660919},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4544017016887665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4320591688156128},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4227406084537506},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.41572535037994385},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22134578227996826},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09035113453865051},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.057350099086761475}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9253326654434204},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.9176143407821655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039633631706238},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7800672054290771},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6021984219551086},{"id":"https://openalex.org/C2776141515","wikidata":"https://www.wikidata.org/wiki/Q1274479","display_name":"Repetition (rhetorical device)","level":2,"score":0.5690052509307861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5689358115196228},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4973650276660919},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4544017016887665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4320591688156128},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4227406084537506},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.41572535037994385},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22134578227996826},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09035113453865051},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.057350099086761475},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarm49381.2020.9195335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm49381.2020.9195335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W648786980","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W1990524510","https://openalex.org/W2101105183","https://openalex.org/W2119717200","https://openalex.org/W2133512280","https://openalex.org/W2154652894","https://openalex.org/W2277195237","https://openalex.org/W2549599535","https://openalex.org/W2605045867","https://openalex.org/W2613718673","https://openalex.org/W2808663243","https://openalex.org/W2890585349","https://openalex.org/W2890781596","https://openalex.org/W2896348597","https://openalex.org/W2897544947","https://openalex.org/W2938603906","https://openalex.org/W2949811425","https://openalex.org/W2951684117","https://openalex.org/W2963084599","https://openalex.org/W2964546107","https://openalex.org/W2965112138","https://openalex.org/W6621543089","https://openalex.org/W6639102338","https://openalex.org/W6682631176"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4321098257"],"abstract_inverted_index":{"Image":[0],"paragraph":[1,74],"captioning":[2],"task":[3],"aims":[4],"to":[5],"provide":[6],"detailed":[7],"and":[8,34,53,55,86],"objective":[9],"multi-sentence":[10],"descriptions":[11],"of":[12,22,25,31,80,89,111,114],"a":[13],"target":[14],"image.":[15],"Existing":[16],"models":[17],"suffer":[18],"from":[19],"the":[20,23,28,62,72,78,87,105],"problems":[21],"monotony":[24],"sentence":[26,32],"structure,":[27],"mechanical":[29],"repetition":[30],"meanings":[33],"stiff":[35],"inter-sentence":[36],"transitions":[37],"in":[38,61,109],"paragraph-level":[39],"descriptions.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"consider":[45],"modeling":[46],"human":[47],"concerned":[48],"evaluation":[49,117],"criteria,":[50],"namely,":[51],"diversity":[52],"coherence,":[54],"use":[56],"them":[57],"as":[58],"explicit":[59],"rewards":[60],"proposed":[63],"Reinforcement":[64],"Learning":[65],"based":[66],"training":[67],"strategy.":[68],"Ablation":[69],"study":[70],"on":[71],"standard":[73,116],"description":[75],"dataset":[76],"shows":[77],"necessity":[79],"leveraging":[81],"Self-critical":[82],"Sequence":[83],"Training":[84],"strategy":[85],"effectiveness":[88],"our":[90,102],"novel":[91],"designed":[92],"reward":[93],"combined":[94],"with":[95],"CIDEr.":[96],"Final":[97],"experimental":[98],"results":[99],"show":[100],"that":[101],"model":[103,108],"improves":[104],"current":[106],"state-of-the-art":[107],"terms":[110],"four":[112],"out":[113],"six":[115],"metrics.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}