{"id":"https://openalex.org/W4399423183","doi":"https://doi.org/10.1145/3652583.3658112","title":"SamCap: Energy-based Controllable Image Captioning by Gradient-Based Sampling","display_name":"SamCap: Energy-based Controllable Image Captioning by Gradient-Based Sampling","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399423183","doi":"https://doi.org/10.1145/3652583.3658112"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658112","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658112","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658112","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","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/10.1145/3652583.3658112","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090027536","display_name":"Yuchen Niu","orcid":"https://orcid.org/0009-0007-9719-7549"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuchen Niu","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043953250","display_name":"Min Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhu","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004301353","display_name":"Zhihua Wei","orcid":"https://orcid.org/0000-0002-5937-3907"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Wei","raw_affiliation_strings":["Department of Computer Science and Technology, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090027536"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49495528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"608","last_page":"617"},"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":0.9962000250816345,"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":0.9914000034332275,"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":0.955907940864563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7512485980987549},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6189459562301636},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6159080266952515},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5786488652229309},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5693867206573486},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5642766952514648},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5450801849365234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5230860710144043},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43559786677360535},{"id":"https://openalex.org/keywords/control-signal","display_name":"Control signal","score":0.4279961884021759},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41211026906967163},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3420654833316803},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32763153314590454},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1021747887134552},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08734586834907532}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.955907940864563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512485980987549},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6189459562301636},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6159080266952515},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5786488652229309},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5693867206573486},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5642766952514648},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5450801849365234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5230860710144043},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43559786677360535},{"id":"https://openalex.org/C3018134525","wikidata":"https://www.wikidata.org/wiki/Q2501541","display_name":"Control signal","level":3,"score":0.4279961884021759},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41211026906967163},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3420654833316803},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32763153314590454},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1021747887134552},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08734586834907532},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658112","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658112","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658112","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658112","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658112","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658112","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399423183.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2185175083","https://openalex.org/W2242818861","https://openalex.org/W2542898981","https://openalex.org/W2559655401","https://openalex.org/W2612690371","https://openalex.org/W2625940279","https://openalex.org/W2896457183","https://openalex.org/W2901988662","https://openalex.org/W2908056713","https://openalex.org/W2955956881","https://openalex.org/W2963062932","https://openalex.org/W2972897806","https://openalex.org/W2982260276","https://openalex.org/W2982553922","https://openalex.org/W2997248215","https://openalex.org/W3009270862","https://openalex.org/W3034984754","https://openalex.org/W3170494780","https://openalex.org/W4212774754","https://openalex.org/W4312922092","https://openalex.org/W4312938727","https://openalex.org/W4313131769","https://openalex.org/W4324312108","https://openalex.org/W4382459038","https://openalex.org/W4386075661","https://openalex.org/W4387373893"],"related_works":["https://openalex.org/W2291845389","https://openalex.org/W2356888604","https://openalex.org/W2380639163","https://openalex.org/W4281926873","https://openalex.org/W4388502705","https://openalex.org/W3007307084","https://openalex.org/W2103416677","https://openalex.org/W1765460115","https://openalex.org/W1575229193","https://openalex.org/W2105913963"],"abstract_inverted_index":{"Despite":[0],"remarkable":[1],"advances":[2],"in":[3,176],"image":[4,22,34,100,116,147],"captioning,":[5,101],"existing":[6,146],"models":[7,166],"still":[8],"lack":[9,62],"the":[10,30,38,41,63,111,115,128,160],"ability":[11,64],"to":[12,65],"generate":[13,124],"controllable":[14,21,99],"and":[15,61,138],"diverse":[16],"captions.":[17],"As":[18],"a":[19,136],"solution,":[20,140],"captioning":[23],"(CIC)":[24],"has":[25],"recently":[26],"gained":[27],"attention,":[28],"with":[29,85,110,144],"goal":[31],"of":[32,40,68,114,162,179],"generating":[33],"captions":[35,125],"that":[36,126,141,155],"satisfy":[37,127],"constraints":[39,130],"given":[42],"control":[43,59,70,169,181],"signals.":[44,71,182],"Current":[45],"CIC":[46,165],"methods":[47],"have":[48],"two":[49],"main":[50],"limitations:":[51],"(1)":[52],"They":[53,73],"can":[54,123,142],"only":[55,158],"handle":[56,66],"one":[57],"specific":[58],"signal":[60],"combinations":[67,178],"multiple":[69,180],"(2)":[72],"depend":[74],"on":[75],"costly":[76],"supervised":[77],"learning":[78],"from":[79],"task-specific":[80,150],"data,":[81],"which":[82],"becomes":[83],"impractical":[84],"increasing":[86],"model":[87],"size.":[88],"To":[89],"this":[90],"end,":[91],"we":[92,122],"propose":[93],"an":[94,119],"energy-based":[95],"sampling":[96],"method":[97],"for":[98,167],"named":[102],"SamCap.":[103],"Specifically,":[104],"by":[105],"combining":[106],"various":[107],"constraint":[108],"functions":[109],"log":[112],"likelihood":[113],"captioner":[117,148],"into":[118],"energy":[120],"function,":[121],"specified":[129],"through":[131],"gradient-based":[132],"sampling.":[133],"SamCap":[134,156],"provides":[135],"learning-free":[137],"plug-and-play":[139],"integrate":[143],"any":[145],"without":[149],"fine-tuning.":[151],"Extensive":[152],"results":[153],"demonstrate":[154],"not":[157],"matches":[159],"performance":[161],"SOTA":[163],"signal-specific":[164],"single":[168],"signals,":[170],"but":[171],"also":[172],"shows":[173],"significant":[174],"advantages":[175],"handling":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
