{"id":"https://openalex.org/W7134985824","doi":"https://doi.org/10.1109/icdmw69685.2025.00054","title":"OTTER: Open-Tagging via Text-Image Representation for Multi-Modal Understanding","display_name":"OTTER: Open-Tagging via Text-Image Representation for Multi-Modal Understanding","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7134985824","doi":"https://doi.org/10.1109/icdmw69685.2025.00054"},"language":null,"primary_location":{"id":"doi:10.1109/icdmw69685.2025.00054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","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/A5104315319","display_name":"Jieer Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210166625","display_name":"Huawei German Research Center","ror":"https://ror.org/00z59w514","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353","https://openalex.org/I4210166625"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Jieer Ouyang","raw_affiliation_strings":["Huawei Singapore Research Center,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center,Singapore","institution_ids":["https://openalex.org/I4210166625","https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128734283","display_name":"Xiaoneng Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210166625","display_name":"Huawei German Research Center","ror":"https://ror.org/00z59w514","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353","https://openalex.org/I4210166625"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Xiaoneng Xiang","raw_affiliation_strings":["Huawei Singapore Research Center,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center,Singapore","institution_ids":["https://openalex.org/I4210166625","https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401111","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0002-7064-6267"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210166625","display_name":"Huawei German Research Center","ror":"https://ror.org/00z59w514","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353","https://openalex.org/I4210166625"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["Huawei Singapore Research Center,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center,Singapore","institution_ids":["https://openalex.org/I4210166625","https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004003995","display_name":"Yuting Ding","orcid":"https://orcid.org/0009-0000-5038-8195"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210166625","display_name":"Huawei German Research Center","ror":"https://ror.org/00z59w514","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353","https://openalex.org/I4210166625"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Yangkai Ding","raw_affiliation_strings":["Huawei Singapore Research Center,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center,Singapore","institution_ids":["https://openalex.org/I4210166625","https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67292598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"421","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4309999942779541,"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":0.4309999942779541,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.1331000030040741,"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/T10028","display_name":"Topic Modeling","score":0.04899999871850014,"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/representation","display_name":"Representation (politics)","score":0.4675000011920929},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.27489998936653137},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2728999853134155},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27129998803138733},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.263700008392334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5616999864578247},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4675000011920929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43220001459121704},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28279998898506165},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27079999446868896},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdmw69685.2025.00054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","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":21,"referenced_works":["https://openalex.org/W2125204570","https://openalex.org/W2171061940","https://openalex.org/W2410641892","https://openalex.org/W2413850928","https://openalex.org/W2963300078","https://openalex.org/W2965373594","https://openalex.org/W2982112268","https://openalex.org/W2997136715","https://openalex.org/W3035333188","https://openalex.org/W3099518117","https://openalex.org/W3109067582","https://openalex.org/W3204334464","https://openalex.org/W3216083537","https://openalex.org/W4226509270","https://openalex.org/W4313175608","https://openalex.org/W4316810125","https://openalex.org/W4390190073","https://openalex.org/W4396220005","https://openalex.org/W4402727922","https://openalex.org/W4404628297","https://openalex.org/W4409494162"],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"OTTER,":[2],"a":[3,14,30,44,56],"unified":[4],"open-set":[5,71,119],"multi-label":[6],"tagging":[7,152],"framework":[8],"that":[9],"harmonizes":[10],"the":[11,20,104],"stability":[12],"of":[13,22,95,109,123],"curated,":[15],"predefined":[16,136],"category":[17],"set":[18],"with":[19,51,67,121,147],"adaptability":[21],"user-driven":[23],"open":[24],"tags.":[25],"OTTER":[26,60,80,114],"is":[27],"built":[28],"upon":[29],"large-scale,":[31],"hierarchically":[32],"organized":[33],"multi-modal":[34,151],"dataset,":[35],"collected":[36],"from":[37],"diverse":[38],"online":[39],"repositories":[40],"and":[41,64,70,76,99,111,127],"annotated":[42],"through":[43],"hybrid":[45],"pipeline":[46],"combining":[47],"automated":[48],"vision-language":[49],"labeling":[50],"human":[52],"refinement.":[53],"By":[54],"leveraging":[55],"multi-head":[57],"attention":[58],"architecture,":[59],"jointly":[61],"aligns":[62],"visual":[63],"textual":[65],"representations":[66],"both":[68],"fixed":[69],"label":[72],"embeddings,":[73],"enabling":[74],"dynamic":[75],"semantically":[77],"consistent":[78],"tagging.":[79],"consistently":[81],"outperforms":[82],"competitive":[83,133],"baselines":[84],"on":[85,97,101,118,125,129,135],"two":[86],"benchmark":[87],"datasets:":[88],"it":[89],"achieves":[90],"an":[91],"overall":[92],"F1":[93,122],"score":[94],"0.81":[96],"Otter":[98,126],"0.75":[100],"Favorite,":[102,130],"surpassing":[103],"nextbest":[105],"results":[106,139],"by":[107],"margins":[108],"0.10":[110],"0.02,":[112],"respectively.":[113],"attains":[115],"near-perfect":[116],"performance":[117],"labels,":[120],"0.99":[124],"0.97":[128],"while":[131],"maintaining":[132],"accuracy":[134],"labels.":[137],"These":[138],"demonstrate":[140],"OTTER's":[141],"effectiveness":[142],"in":[143],"bridging":[144],"closed-set":[145],"consistency":[146],"open-vocabulary":[148],"flexibility":[149],"for":[150],"applications.":[153]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-12T00:00:00"}