{"id":"https://openalex.org/W7125075094","doi":"https://doi.org/10.1109/cbmi66578.2025.11339325","title":"MI-Cap: A Multi-Modal Interpretable Model for Video Captioning","display_name":"MI-Cap: A Multi-Modal Interpretable Model for Video Captioning","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7125075094","doi":"https://doi.org/10.1109/cbmi66578.2025.11339325"},"language":"en","primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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/A5114657298","display_name":"Antoine Hanna-Asaad","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118719","display_name":"\u00c9cole Sup\u00e9rieure des Techniques A\u00e9ronautiques et de Construction Automobile","ror":"https://ror.org/02az5b805","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210118719"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Antoine Hanna-Asaad","raw_affiliation_strings":["ESTACA Paris-Saclay,ESTACA'Lab,Montigny-le-Bretonneux,France"],"affiliations":[{"raw_affiliation_string":"ESTACA Paris-Saclay,ESTACA'Lab,Montigny-le-Bretonneux,France","institution_ids":["https://openalex.org/I4210118719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074947842","display_name":"Decky Aspandi-Latif","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Decky Aspandi-Latif","raw_affiliation_strings":["SAMOVAR, Télécom SudParis, Institute Polytechnique de Paris,Palaiseau,France,91120"],"affiliations":[{"raw_affiliation_string":"SAMOVAR, Télécom SudParis, Institute Polytechnique de Paris,Palaiseau,France,91120","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123398463","display_name":"Titus Zaharia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Titus Zaharia","raw_affiliation_strings":["SAMOVAR, Télécom SudParis, Institute Polytechnique de Paris,Palaiseau,France,91120"],"affiliations":[{"raw_affiliation_string":"SAMOVAR, Télécom SudParis, Institute Polytechnique de Paris,Palaiseau,France,91120","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114657298"],"corresponding_institution_ids":["https://openalex.org/I4210118719"],"apc_list":null,"apc_paid":null,"fwci":1.3104,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8693737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9926999807357788,"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":0.9926999807357788,"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/T11439","display_name":"Video Analysis and Summarization","score":0.0010999999940395355,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0006000000284984708,"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":0.9830999970436096},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.9416000247001648},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5235999822616577},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5029000043869019},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49380001425743103},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4230000078678131},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3986999988555908}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9830999970436096},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9416000247001648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943000197410583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6460999846458435},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5752999782562256},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49380001425743103},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3894999921321869},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3325999975204468},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2696000039577484}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05332291v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05332291","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Content-Based Multimedia Indexing (CBMI), Oct 2025, Dublin, Ireland. ⟨10.1109/CBMI66578.2025.11339325⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W15592790","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2139501017","https://openalex.org/W2289988710","https://openalex.org/W2425121537","https://openalex.org/W2558834163","https://openalex.org/W2575842049","https://openalex.org/W2598003564","https://openalex.org/W2616247523","https://openalex.org/W2961881472","https://openalex.org/W2970231061","https://openalex.org/W2984862483","https://openalex.org/W2989322838","https://openalex.org/W2997591391","https://openalex.org/W3034221024","https://openalex.org/W3035265375","https://openalex.org/W3035635319","https://openalex.org/W3176989556","https://openalex.org/W3203711169","https://openalex.org/W3216659302","https://openalex.org/W3217340782","https://openalex.org/W4214814722","https://openalex.org/W4312560592","https://openalex.org/W4323244431","https://openalex.org/W4372266552","https://openalex.org/W4385245566","https://openalex.org/W4386072365","https://openalex.org/W4405812114"],"related_works":[],"abstract_inverted_index":{"Video":[0],"captioning":[1,61],"aims":[2],"to":[3,81,110],"describing":[4],"video":[5,60],"content":[6],"in":[7,23,91],"natural":[8],"language,":[9],"which":[10],"implies":[11],"understanding":[12],"and":[13,18,75,94,130],"interpreting":[14],"scenes,":[15],"objects,":[16],"actions":[17],"events":[19],"that":[20,70,133],"are":[21],"present":[22],"the":[24,36,46,83,87,98,106,114,134],"video.":[25],"Current":[26],"approaches":[27],"have":[28],"mostly":[29],"concentrated":[30],"on":[31,122],"visual":[32],"cues,":[33],"often":[34],"neglecting":[35],"rich":[37,84],"information":[38],"available":[39],"from":[40],"other":[41],"important":[42],"modalities,":[43,89],"such":[44,127],"as":[45,128],"audio":[47],"or":[48],"textual":[49],"(e.g.":[50],"subtitles)":[51],"channels.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"introduce":[57],"a":[58,65],"novel":[59],"method":[62,136],"trained":[63],"with":[64],"multi-modal":[66,73],"contrastive":[67],"loss":[68],"function":[69],"emphasizes":[71],"both":[72],"integration":[74],"interpretability.":[76],"Our":[77],"approach":[78],"is":[79,108],"designed":[80],"capture":[82],"dependencies":[85],"between":[86],"different":[88],"resulting":[90],"more":[92],"accurate":[93],"pertinent":[95],"captions.":[96],"Concerning":[97],"interpretability":[99],"issues,":[100],"by":[101],"exploiting":[102],"multiple":[103],"attention":[104],"mechanisms,":[105],"model":[107],"able":[109],"provide":[111],"explanations":[112],"of":[113],"results":[115],"proposed.":[116],"The":[117],"experimental":[118],"evaluation,":[119],"caried":[120],"out":[121],"widely":[123],"used":[124],"benchmark":[125],"datasets":[126],"MSR-VTT":[129],"VATEX,":[131],"demonstrate":[132],"proposed":[135],"performs":[137],"favorably":[138],"against":[139],"state-of":[140],"the-art":[141],"models.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2026-01-21T00:00:00"}