{"id":"https://openalex.org/W7133200465","doi":"https://doi.org/10.52202/075280-2504","title":"On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes","display_name":"On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W7133200465","doi":"https://doi.org/10.52202/075280-2504"},"language":"en","primary_location":{"id":"doi:10.52202/075280-2504","doi":"https://doi.org/10.52202/075280-2504","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-2504","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.19553","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109587990","display_name":"Rajat Modi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajat Modi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045147286","display_name":"Vibhav Vineet","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vibhav Vineet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127819613","display_name":"Yogesh Rawat","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yogesh Rawat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.54,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77624985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"57306","last_page":"57335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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":0.9990000128746033,"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":0.00019999999494757503,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/occlusion","display_name":"occlusion","score":0.7260000109672546},{"id":"https://openalex.org/keywords/video-action-detection","display_name":"video action detection","score":0.9860000014305115},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.875},{"id":"https://openalex.org/keywords/object-occlusion","display_name":"object occlusion","score":0.527999997138977},{"id":"https://openalex.org/keywords/human-action-recognition","display_name":"human action recognition","score":0.35100001096725464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7020000219345093},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985000133514404},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5659999847412109},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3666999936103821},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35249999165534973},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2597000002861023}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/075280-2504","doi":"https://doi.org/10.52202/075280-2504","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-2504","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.19553","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2410.19553","pdf_url":"https://arxiv.org/pdf/2410.19553","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.19553","doi":"https://doi.org/10.48550/arxiv.2410.19553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.19553","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.19553","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2410.19553","pdf_url":"https://arxiv.org/pdf/2410.19553","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3959072361","display_name":null,"funder_award_id":"2022-21102100001","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G5609518939","display_name":null,"funder_award_id":"2022-21102100001","funder_id":"https://openalex.org/F4320312530","funder_display_name":"Office of the Director of National Intelligence"}],"funders":[{"id":"https://openalex.org/F4320310161","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12"},{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133200465.pdf","grobid_xml":"https://content.openalex.org/works/W7133200465.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1821462560","https://openalex.org/W2903100412","https://openalex.org/W2985693775","https://openalex.org/W3113055895","https://openalex.org/W3132401450","https://openalex.org/W3177828909","https://openalex.org/W3185289325","https://openalex.org/W4221146106","https://openalex.org/W4288043070","https://openalex.org/W4297990624","https://openalex.org/W4306890139","https://openalex.org/W4312122317","https://openalex.org/W4313304716","https://openalex.org/W4324128075","https://openalex.org/W4366208220","https://openalex.org/W4390873752","https://openalex.org/W4390874575"],"related_works":["https://openalex.org/W7133196659","https://openalex.org/W4404986715","https://openalex.org/W4402044247","https://openalex.org/W3136367208","https://openalex.org/W7154283013","https://openalex.org/W3212555189","https://openalex.org/W3200671706","https://openalex.org/W7220718166","https://openalex.org/W7096044614","https://openalex.org/W3175250097"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,164,169,197],"impact":[4],"of":[5,26,35,101,128,168,196],"occlusions":[6,36,43],"in":[7,44,82,132,194],"video":[8,179],"action":[9],"detection.":[10],"We":[11,47,76],"facilitate":[12],"this":[13,203],"study":[14],"by":[15,183],"introducing":[16],"five":[17],"new":[18],"benchmark":[19],"datasets":[20],"namely":[21],"O-UCF":[22],"and":[23,32,40,63,125],"O-JHMDB":[24,189],"consisting":[25,34],"synthetically":[27],"controlled":[28],"static/dynamic":[29],"occlusions,":[30],"OVIS-UCF":[31],"OVIS-JHMDB":[33],"with":[37],"realistic":[38,133],"motions":[39],"Real-OUCF":[41,193],"for":[42,202],"realistic-world":[45],"scenarios.":[46],"formally":[48],"confirm":[49],"an":[50],"intuitive":[51],"expectation:":[52],"existing":[53,178],"models":[54,91,161],"suffer":[55],"a":[56,99],"lot":[57],"as":[58,98],"occlusion":[59,97,160,182],"severity":[60],"is":[61],"increased":[62],"exhibit":[64],"different":[65],"behaviours":[66],"when":[67,72],"occluders":[68,119],"are":[69,74],"static":[70],"vs":[71],"they":[73],"moving.":[75],"discover":[77],"several":[78],"intriguing":[79],"phenomenon":[80],"emerging":[81],"neural":[83],"nets:":[84],"1)":[85],"transformers":[86],"can":[87,130],"naturally":[88],"outperform":[89,177],"CNN":[90],"which":[92,156],"might":[93],"have":[94],"even":[95,121],"used":[96],"form":[100],"data":[102],"augmentation":[103],"during":[104,123],"training":[105,124,154],"2)":[106],"incorporating":[107],"symbolic-components":[108],"like":[109],"capsules":[110],"to":[111,116,118,149,158],"such":[112],"backbones":[113],"allows":[114],"them":[115],"bind":[117],"never":[120],"seen":[122],"3)":[126],"Islands":[127],"agreement":[129],"emerge":[131],"images/videos":[134],"without":[135],"instance-level":[136],"supervision,":[137],"distillation":[138],"or":[139],"contrastive-based":[140],"objectives2(eg.":[141],"video-textual":[142],"training).":[143],"Such":[144],"emergent":[145],"properties":[146],"allow":[147],"us":[148],"derive":[150],"simple":[151],"yet":[152],"effective":[153],"recipes":[155,176],"lead":[157],"robust":[159],"inductively":[162],"satisfying":[163],"first":[165],"two":[166],"stages":[167],"binding":[170],"mechanism":[171],"(grouping/segregation).":[172],"Models":[173],"leveraging":[174],"these":[175],"action-detectors":[180],"under":[181],"32.3%":[184],"on":[185,188,192],"O-UCF,":[186],"32.7%":[187],"&":[190],"2.6%":[191],"terms":[195],"vMAP":[198],"metric.":[199],"The":[200],"code":[201],"work":[204],"has":[205],"been":[206],"released":[207],"at":[208],"https://github.com/rajatmodi62/OccludedActionBenchmark.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-03-03T00:00:00"}