{"id":"https://openalex.org/W4387969143","doi":"https://doi.org/10.1145/3581783.3612551","title":"Category-Specific Prompts for Animal Action Recognition with Pretrained Vision-Language Models","display_name":"Category-Specific Prompts for Animal Action Recognition with Pretrained Vision-Language Models","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969143","doi":"https://doi.org/10.1145/3581783.3612551"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612551","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5016189095","display_name":"Yinuo Jing","orcid":"https://orcid.org/0009-0004-0866-2305"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yinuo Jing","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0866-2305","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417808","display_name":"Chunyu Wang","orcid":"https://orcid.org/0000-0002-9400-9107"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyu Wang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9400-9107","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036310805","display_name":"Ruxu Zhang","orcid":"https://orcid.org/0009-0007-9635-7563"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruxu Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-9635-7563","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077313814","display_name":"Kongming Liang","orcid":"https://orcid.org/0000-0002-4726-093X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kongming Liang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4726-093X","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039812471","display_name":"Zhanyu Ma","orcid":"https://orcid.org/0000-0003-2950-2488"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanyu Ma","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2950-2488","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016189095"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.232,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53040633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5716","last_page":"5724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/computer-science","display_name":"Computer science","score":0.7976313233375549},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6920876502990723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6701104640960693},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.58258056640625},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5251134037971497},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36753472685813904},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33674269914627075},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3247207999229431},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32051217555999756},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.31041938066482544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976313233375549},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6920876502990723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6701104640960693},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.58258056640625},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5251134037971497},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36753472685813904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33674269914627075},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3247207999229431},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32051217555999756},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.31041938066482544},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612551","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1262852264","display_name":null,"funder_award_id":"2023QNTD02","funder_id":"https://openalex.org/F4320321470","funder_display_name":"Beijing University of Posts and Telecommunications"},{"id":"https://openalex.org/G172479822","display_name":null,"funder_award_id":"62225601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3848188706","display_name":null,"funder_award_id":"U19B2036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4767065429","display_name":null,"funder_award_id":"62106022, U19B2036, 62225601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5324240230","display_name":null,"funder_award_id":"62106022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1971733068","https://openalex.org/W2034920727","https://openalex.org/W2413850928","https://openalex.org/W2577784528","https://openalex.org/W2810685774","https://openalex.org/W2899609705","https://openalex.org/W2941352015","https://openalex.org/W2963300078","https://openalex.org/W2963524571","https://openalex.org/W2963745697","https://openalex.org/W2981385151","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W2990503944","https://openalex.org/W3009364469","https://openalex.org/W3034572008","https://openalex.org/W3035265375","https://openalex.org/W3037927687","https://openalex.org/W3044438666","https://openalex.org/W3104069527","https://openalex.org/W3130841421","https://openalex.org/W3137049560","https://openalex.org/W3198377975","https://openalex.org/W3216930742","https://openalex.org/W4206399095","https://openalex.org/W4214614183","https://openalex.org/W4224285690","https://openalex.org/W4312245820","https://openalex.org/W4312310776","https://openalex.org/W6600077625","https://openalex.org/W6600103761","https://openalex.org/W6601010567","https://openalex.org/W6601223237","https://openalex.org/W6601365666","https://openalex.org/W6602599378","https://openalex.org/W6602670149","https://openalex.org/W6602737616","https://openalex.org/W6607437068","https://openalex.org/W6628857929","https://openalex.org/W6634888948","https://openalex.org/W6637671230","https://openalex.org/W6701982200","https://openalex.org/W6725781397","https://openalex.org/W6761413974","https://openalex.org/W6818723395"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W1576128429","https://openalex.org/W2269464716"],"abstract_inverted_index":{"Animal":[0,198],"action":[1,23,48,78,89,141,193],"recognition":[2,49,90,194],"has":[3,66,73,202],"a":[4,54,86,104],"wide":[5],"range":[6],"of":[7,28,37,41,57,151,169,180],"applications.":[8],"However,":[9],"the":[10,17,42,82,94,100,120,149,157,162,170,174,178,197],"field":[11],"largely":[12],"remains":[13],"unexplored":[14],"due":[15],"to":[16,21,109,164],"greater":[18],"challenges":[19,102],"compared":[20],"human":[22,47,77],"recognition,":[24],"such":[25],"as":[26],"lack":[27],"annotated":[29,58],"training":[30],"data,":[31],"large":[32,55],"intra-class":[33],"variation,":[34],"and":[35,72,116,135,142,153,176,201],"interference":[36,179],"cluttered":[38],"background.":[39],"Most":[40],"existing":[43],"methods":[44,195],"directly":[45],"apply":[46],"techniques,":[50],"which":[51],"essentially":[52],"require":[53],"amount":[56],"data.":[59],"In":[60],"recent":[61],"years,":[62],"contrastive":[63],"vision-language":[64],"pretraining":[65],"demonstrated":[67],"strong":[68],"zero-shot":[69],"generalization":[70,205],"ability":[71,206],"been":[74],"used":[75],"for":[76,113,139],"recognition.":[79],"Inspired":[80],"by":[81],"success,":[83],"we":[84],"develop":[85],"highly":[87],"performant":[88],"framework":[91],"based":[92,118],"on":[93,119,166,196,207],"CLIP":[95],"model.":[96],"Our":[97],"model":[98,163],"addresses":[99],"above":[101],"via":[103],"novel":[105],"category-specific":[106],"prompting":[107],"module":[108],"generate":[110,132],"adaptive":[111],"prompts":[112],"both":[114],"text":[115],"video":[117,167,175,181],"animal":[121,143,172],"category":[122,144],"detected":[123],"in":[124,148,173],"input":[125],"videos.":[126],"On":[127,156],"one":[128],"hand,":[129,159],"it":[130,160],"can":[131],"more":[133],"precise":[134],"customized":[136],"textual":[137,152],"descriptions":[138],"each":[140],"pair,":[145],"being":[146],"helpful":[147],"alignment":[150],"visual":[154],"space.":[155],"other":[158],"allows":[161],"focus":[165],"features":[168],"target":[171],"reduce":[177],"background":[182],"noise.":[183],"Experimental":[184],"results":[185],"demonstrate":[186],"that":[187],"our":[188],"method":[189],"outperforms":[190],"five":[191],"previous":[192],"Kingdom":[199],"dataset":[200],"shown":[203],"best":[204],"unseen":[208],"animals.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}