{"id":"https://openalex.org/W4375869254","doi":"https://doi.org/10.1109/icassp49357.2023.10096573","title":"Multi-Scale Compositional Constraints for Representation Learning on Videos","display_name":"Multi-Scale Compositional Constraints for Representation Learning on Videos","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869254","doi":"https://doi.org/10.1109/icassp49357.2023.10096573"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096573","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5026032406","display_name":"Georgios Paraskevopoulos","orcid":"https://orcid.org/0000-0003-4067-6294"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Georgios Paraskevopoulos","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058760668","display_name":"Chandrashekhar Lavania","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chandrashekhar Lavania","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005748335","display_name":"Lovish Chum","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lovish Chum","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113697636","display_name":"Shiva Sundaram","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiva Sundaram","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026032406"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04050585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"5"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9991000294685364,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8729583024978638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7956678867340088},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6736654043197632},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5828521251678467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5214687585830688},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.49520865082740784},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4722908139228821},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.46150898933410645},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.4467311203479767},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4238203763961792},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.419051855802536},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3494902551174164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.347428560256958}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8729583024978638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956678867340088},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6736654043197632},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5828521251678467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5214687585830688},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.49520865082740784},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4722908139228821},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.46150898933410645},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4467311203479767},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4238203763961792},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.419051855802536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3494902551174164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.347428560256958},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096573","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W2112328181","https://openalex.org/W2529272619","https://openalex.org/W2593116425","https://openalex.org/W2781922022","https://openalex.org/W2798991696","https://openalex.org/W2899274165","https://openalex.org/W2948242301","https://openalex.org/W2963155035","https://openalex.org/W2964222561","https://openalex.org/W2972778456","https://openalex.org/W2981851019","https://openalex.org/W3010094231","https://openalex.org/W3017374003","https://openalex.org/W3035299099","https://openalex.org/W3093051361","https://openalex.org/W3107828565","https://openalex.org/W3145385912","https://openalex.org/W3175300676","https://openalex.org/W3198659451","https://openalex.org/W3199148273","https://openalex.org/W3209059054","https://openalex.org/W3209483675","https://openalex.org/W3214261769","https://openalex.org/W4210276931","https://openalex.org/W4214507759","https://openalex.org/W4214614183","https://openalex.org/W4224920427","https://openalex.org/W4297808394","https://openalex.org/W4300618906","https://openalex.org/W4312699666","https://openalex.org/W4388392666","https://openalex.org/W6600983433","https://openalex.org/W6682948231","https://openalex.org/W6751805184","https://openalex.org/W6755207826","https://openalex.org/W6770805772","https://openalex.org/W6775244068","https://openalex.org/W6779879114","https://openalex.org/W6784660784","https://openalex.org/W6804411763","https://openalex.org/W6810271288","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W1517524280","https://openalex.org/W4323520239"],"abstract_inverted_index":{"Combining":[0],"simple":[1,61],"concepts":[2,10],"to":[3],"form":[4],"structured":[5],"thoughts":[6],"and":[7,85,102,118,124],"decomposing":[8],"complex":[9],"into":[11],"their":[12],"constituents":[13],"is":[14],"one":[15],"key":[16],"characteristic":[17],"of":[18,56,81,97,130],"human":[19],"cognition.":[20],"In":[21,74],"this":[22],"work":[23],"we":[24,36,77],"extract":[25],"video":[26,49,58,103,132],"representations":[27],"by":[28,42],"combining":[29],"multi-scale":[30],"processing":[31],"with":[32],"compositional":[33,83,131],"constraints,":[34],"i.e.,":[35,116],"constrain":[37],"the":[38,43,65,82,90,94,106,114,128],"latent":[39],"space":[40],"created":[41],"network":[44],"so":[45],"that":[46],"coarse":[47],"grained":[48],"features":[50,59],"are":[51],"composed":[52],"from":[53],"a":[54,69],"set":[55],"fine-grained":[57],"using":[60],"functions.":[62,87],"We":[63,88,109],"integrate":[64],"proposed":[66,91],"constraints":[67,84],"in":[68,100,105],"state-of-the-art":[70],"contrastive":[71],"learning":[72],"frame-work.":[73],"our":[75],"ablations,":[76],"evaluate":[78,89],"different":[79],"formulations":[80],"composition":[86],"approach":[92],"for":[93,122],"downstream":[95],"tasks":[96],"action":[98],"detection":[99],"UCF-101,":[101],"summarization":[104],"SumMe":[107,125],"dataset.":[108],"achieve":[110],"significant":[111],"improvements":[112,121],"over":[113],"baseline,":[115],"3.9%":[117],"6.3%":[119],"relative":[120],"UCF-101":[123],"respectively,":[126],"showcasing":[127],"importance":[129],"representations.":[133]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}