{"id":"https://openalex.org/W4399418535","doi":"https://doi.org/10.1145/3652583.3657617","title":"Directly Locating Actions in Video with Single Frame Annotation","display_name":"Directly Locating Actions in Video with Single Frame Annotation","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418535","doi":"https://doi.org/10.1145/3652583.3657617"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3657617","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657617","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657617","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/10.1145/3652583.3657617","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025658431","display_name":"Haoran Tong","orcid":"https://orcid.org/0009-0006-4975-194X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoran Tong","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439402","display_name":"Xinyan Liu","orcid":"https://orcid.org/0000-0003-2638-4324"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyan Liu","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775216","display_name":"Guorong Li","orcid":"https://orcid.org/0000-0003-3954-2387"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guorong Li","raw_affiliation_strings":["University of Chinese Academy of Sciences, Bejing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Bejing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010557705","display_name":"Laiyun Qing","orcid":"https://orcid.org/0000-0001-9923-5034"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Laiyun Qing","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025658431"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.2493,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48725476,"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":"1135","last_page":"1139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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/T11439","display_name":"Video Analysis and Summarization","score":0.9948999881744385,"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":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.8060389161109924},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.66729336977005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6157661080360413},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.5630403757095337},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5308103561401367},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5199395418167114},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5136341452598572},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5097805857658386},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4974103271961212},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.496232807636261},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4939888119697571},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4477861821651459},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38660287857055664},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13162511587142944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060389161109924},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.66729336977005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6157661080360413},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.5630403757095337},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5308103561401367},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5199395418167114},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5136341452598572},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5097805857658386},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4974103271961212},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.496232807636261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4939888119697571},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4477861821651459},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38660287857055664},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13162511587142944},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3657617","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657617","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657617","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:10.1145/3652583.3657617","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657617","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657617","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418535.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2336403884","https://openalex.org/W2604113307","https://openalex.org/W2799262584","https://openalex.org/W2962709777","https://openalex.org/W2962876901","https://openalex.org/W2963247196","https://openalex.org/W2963524571","https://openalex.org/W2964214371","https://openalex.org/W2964216549","https://openalex.org/W2975310793","https://openalex.org/W2986407524","https://openalex.org/W3189379416","https://openalex.org/W3202825210","https://openalex.org/W3203848195","https://openalex.org/W3207172562","https://openalex.org/W4230270698","https://openalex.org/W4288020064","https://openalex.org/W4304945116","https://openalex.org/W4312421085","https://openalex.org/W4312508181"],"related_works":["https://openalex.org/W2417253731","https://openalex.org/W2350469024","https://openalex.org/W2491583298","https://openalex.org/W2036154621","https://openalex.org/W2327827625","https://openalex.org/W2395860100","https://openalex.org/W2938698191","https://openalex.org/W3087274204","https://openalex.org/W3004505825","https://openalex.org/W4283332100"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,37,59],"novel":[3],"method":[4,23],"for":[5,77],"point-supervised":[6,31],"action":[7,32,42,78,99],"localization.Differs":[8],"from":[9],"the":[10,48,62,68,71,90,92,95,108],"common":[11],"practice":[12],"of":[13,39,67,97,110],"locating":[14],"actions":[15],"by":[16,36],"first":[17],"categorizing":[18],"each":[19,46,86,98],"video":[20,50],"frame,":[21],"our":[22,111],"directly":[24],"predicts":[25],"actions'":[26],"positions":[27],"and":[28,56,70,94],"length.":[29],"Specifically,":[30],"localization":[33],"is":[34],"achieved":[35],"series":[38],"fully":[40],"supervised":[41],"location":[43],"iteratively.":[44],"In":[45],"iteration,":[47],"input":[49,54],"are":[51,83],"used":[52],"as":[53],"tokens":[55],"fed":[57],"into":[58],"transformer,":[60],"where":[61],"encoder":[63],"extracts":[64],"global":[65],"context":[66],"clips,":[69],"decoder":[72],"generates":[73],"queries":[74],"containing":[75],"information":[76],"localization.":[79],"Three":[80],"MLP":[81],"heads":[82],"built":[84],"on":[85,103],"query":[87],"to":[88],"obtain":[89],"probability,":[91],"center,":[93],"length":[96],"instance":[100],"respectively.":[101],"Experiments":[102],"three":[104],"popular":[105],"datasets":[106],"prove":[107],"potential":[109],"method.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}