{"id":"https://openalex.org/W4379931083","doi":"https://doi.org/10.1145/3591106.3592300","title":"Efficient CNNs and Transformers for Video Understanding and Image Synthesis","display_name":"Efficient CNNs and Transformers for Video Understanding and Image Synthesis","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379931083","doi":"https://doi.org/10.1145/3591106.3592300"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592300","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","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/A5108351560","display_name":"J\u00fcrgen Gall","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"J\u00fcrgen Gall","raw_affiliation_strings":["Department of Information Systems and Artificial Intelligence, University of Bonn, Germany and \rLamarr Institute for Machine Learning and Artificial Intelligence, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems and Artificial Intelligence, University of Bonn, Germany and \rLamarr Institute for Machine Learning and Artificial Intelligence, Germany","institution_ids":["https://openalex.org/I135140700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108351560"],"corresponding_institution_ids":["https://openalex.org/I135140700"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05226185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"670","last_page":"670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9907000064849854,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9907000064849854,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9776999950408936,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9717000126838684,"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/flops","display_name":"FLOPS","score":0.8998715877532959},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.839085578918457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6875019073486328},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6232789754867554},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5757750868797302},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5743297338485718},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.571506917476654},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4885028600692749},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.471581369638443},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4266647398471832},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.338359534740448}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.8998715877532959},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.839085578918457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6875019073486328},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6232789754867554},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5757750868797302},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5743297338485718},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.571506917476654},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4885028600692749},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.471581369638443},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4266647398471832},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.338359534740448},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592300","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W3102845713","https://openalex.org/W2971502891","https://openalex.org/W3005814217","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093","https://openalex.org/W2969228573","https://openalex.org/W2963690996"],"abstract_inverted_index":{"In":[0,147],"this":[1],"talk,":[2],"I":[3,82,151],"will":[4,83,152],"first":[5],"discuss":[6,85,153],"approaches":[7,89,105,133],"that":[8,75,90,115,156,174],"reduce":[9,135],"the":[10,48,62,67,107,111,136,145,148,179],"GFLOPs":[11,49],"during":[12],"inference":[13],"for":[14,78,183,193],"3D":[15,25,52,97],"convolutional":[16],"neural":[17],"networks":[18,142],"(CNN)":[19],"and":[20,27,43,178],"vision":[21,28,55,100],"transformers.":[22],"While":[23,47],"state-of-the-art":[24,141],"CNNs":[26],"transformers":[29],"achieve":[30],"very":[31,41,162],"good":[32],"results":[33],"on":[34,168],"action":[35],"recognition":[36],"datasets,":[37],"they":[38],"are":[39,126],"computationally":[40],"expensive":[42],"require":[44],"many":[45],"GFLOPs.":[46],"of":[50,69,140,161],"a":[51,130,169],"CNN":[53,98],"or":[54,66,99],"transformer":[56,101],"can":[57,91,189],"be":[58,92,191],"decreased":[59],"by":[60],"reducing":[61],"temporal":[63],"feature":[64],"resolution":[65],"number":[68],"tokens,":[70],"there":[71],"is":[72,76,166],"no":[73],"setting":[74],"optimal":[77],"all":[79],"input":[80,112],"clips.":[81],"therefore":[84],"two":[86],"differentiable":[87],"sampling":[88,104],"plugged":[93],"into":[94],"any":[95],"existing":[96],"architecture.":[102],"The":[103,132,186],"adapt":[106],"computational":[108,137],"resources":[109,118],"to":[110,128],"video":[113,195],"such":[114],"as":[116,119],"much":[117],"needed":[120],"but":[121],"not":[122],"more":[123],"than":[124],"necessary":[125],"used":[127,192],"classify":[129],"video.":[131],"substantially":[134],"cost":[138],"(GFLOPs)":[139],"while":[143],"preserving":[144],"accuracy.":[146],"second":[149],"part,":[150],"an":[154],"approach":[155],"generates":[157],"annotated":[158],"training":[159],"samples":[160],"rare":[163],"classes.":[164],"It":[165],"based":[167],"generative":[170],"adversarial":[171],"network":[172],"(GAN)":[173],"jointly":[175],"synthesizes":[176],"images":[177],"corresponding":[180],"segmentation":[181],"mask":[182],"each":[184],"image.":[185],"generated":[187],"data":[188],"then":[190],"one-shot":[194],"object":[196],"segmentation.":[197]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}