{"id":"https://openalex.org/W4392207693","doi":"https://doi.org/10.1109/tnnls.2024.3359716","title":"GSSTU: Generative Spatial Self-Attention Transformer Unit for Enhanced Video Prediction","display_name":"GSSTU: Generative Spatial Self-Attention Transformer Unit for Enhanced Video Prediction","publication_year":2024,"publication_date":"2024-02-27","ids":{"openalex":"https://openalex.org/W4392207693","doi":"https://doi.org/10.1109/tnnls.2024.3359716","pmid":"https://pubmed.ncbi.nlm.nih.gov/38412087"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3359716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3359716","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5025729615","display_name":"Binit Kumar Singh","orcid":"https://orcid.org/0000-0001-9065-999X"},"institutions":[{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Binit Singh","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT (Banaras Hindu University) Varanasi, Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT (Banaras Hindu University) Varanasi, Varanasi, India","institution_ids":["https://openalex.org/I91357014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027769079","display_name":"Divij Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Divij Singh","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT (Banaras Hindu University) Varanasi, Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT (Banaras Hindu University) Varanasi, Varanasi, India","institution_ids":["https://openalex.org/I91357014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108904248","display_name":"R. P. Kaushal","orcid":null},"institutions":[{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rohan Kaushal","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT (Banaras Hindu University) Varanasi, Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT (Banaras Hindu University) Varanasi, Varanasi, India","institution_ids":["https://openalex.org/I91357014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009986045","display_name":"Agrya Halder","orcid":"https://orcid.org/0000-0001-9675-8104"},"institutions":[{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Agrya Halder","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT (Banaras Hindu University) Varanasi, Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT (Banaras Hindu University) Varanasi, Varanasi, India","institution_ids":["https://openalex.org/I91357014"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010819780","display_name":"Pratik Chattopadhyay","orcid":"https://orcid.org/0000-0002-5805-6563"},"institutions":[{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pratik Chattopadhyay","raw_affiliation_strings":["Department of Computer Science and Engineering, IIT (Banaras Hindu University) Varanasi, Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIT (Banaras Hindu University) Varanasi, Varanasi, India","institution_ids":["https://openalex.org/I91357014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025729615"],"corresponding_institution_ids":["https://openalex.org/I91357014"],"apc_list":null,"apc_paid":null,"fwci":1.0526,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75728059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"36","issue":"3","first_page":"4625","last_page":"4638"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","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/T10531","display_name":"Advanced Vision and Imaging","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9983999729156494,"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":0.9983999729156494,"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":0.8115766048431396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7055663466453552},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5396866798400879},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4906829595565796},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4746468663215637},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4400763213634491},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4342002868652344},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4152148962020874},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.41483891010284424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115766048431396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7055663466453552},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5396866798400879},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4906829595565796},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4746468663215637},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4400763213634491},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4342002868652344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4152148962020874},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.41483891010284424},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3359716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3359716","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:38412087","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38412087","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W2038176251","https://openalex.org/W2064675550","https://openalex.org/W2098699644","https://openalex.org/W2187089797","https://openalex.org/W2798017603","https://openalex.org/W2808493349","https://openalex.org/W2950635152","https://openalex.org/W2964199361","https://openalex.org/W2966687987","https://openalex.org/W2991019415","https://openalex.org/W2996936831","https://openalex.org/W3034426027","https://openalex.org/W3120048558","https://openalex.org/W3138340468","https://openalex.org/W3152733922","https://openalex.org/W3181942264","https://openalex.org/W4214562059","https://openalex.org/W4249279051","https://openalex.org/W4285216227","https://openalex.org/W4294306266","https://openalex.org/W4298157202","https://openalex.org/W4309368547","https://openalex.org/W4312305807","https://openalex.org/W4313009682","https://openalex.org/W4319452844","https://openalex.org/W4323897056","https://openalex.org/W4385245566","https://openalex.org/W6628877408","https://openalex.org/W6634221342","https://openalex.org/W6677326919","https://openalex.org/W6680241920","https://openalex.org/W6691096134","https://openalex.org/W6735992252","https://openalex.org/W6739112683","https://openalex.org/W6745420753","https://openalex.org/W6745829810","https://openalex.org/W6748392304","https://openalex.org/W6750366247","https://openalex.org/W6750642828","https://openalex.org/W6757613341","https://openalex.org/W6764529735","https://openalex.org/W6766861245","https://openalex.org/W6770086194","https://openalex.org/W6771200186","https://openalex.org/W6771703261","https://openalex.org/W6789948695","https://openalex.org/W6793801364","https://openalex.org/W6804010475","https://openalex.org/W6849846199"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W3135697610","https://openalex.org/W4391621807","https://openalex.org/W2085033728","https://openalex.org/W4285411112","https://openalex.org/W2171299904","https://openalex.org/W1647606319","https://openalex.org/W2922442631","https://openalex.org/W4390494008","https://openalex.org/W4324290231"],"abstract_inverted_index":{"Future":[0],"frame":[1,79],"prediction":[2,80],"is":[3],"a":[4,74,99,104],"challenging":[5],"task":[6],"in":[7,13,30,47,123,182],"computer":[8],"vision":[9],"with":[10,42,89],"practical":[11],"applications":[12],"areas":[14],"such":[15],"as":[16],"video":[17],"generation,":[18],"autonomous":[19],"driving,":[20],"and":[21,36,63,103,114,133,156,161],"robotics.":[22],"Traditional":[23],"recurrent":[24,43],"neural":[25,39],"networks":[26,40,44,53],"have":[27,54],"limited":[28],"effectiveness":[29,177],"capturing":[31],"long-range":[32],"dependencies":[33],"between":[34],"frames,":[35],"combining":[37],"convolutional":[38],"(CNNs)":[41],"has":[45],"limitations":[46],"modeling":[48,92],"complex":[49],"dependencies.":[50],"Generative":[51],"adversarial":[52],"shown":[55],"promising":[56],"results,":[57],"but":[58],"they":[59],"are":[60],"computationally":[61],"expensive":[62],"suffer":[64],"from":[65],"instability":[66],"during":[67],"training.":[68],"In":[69],"this":[70],"article,":[71],"we":[72],"propose":[73,98],"novel":[75,105],"approach":[76,119],"for":[77,163],"future":[78,187],"that":[81],"combines":[82],"the":[83,90,164,176],"encoding":[84],"capabilities":[85,93],"of":[86,94,125,153,178,186],"3-D":[87],"CNNs":[88],"sequence":[91],"Transformers.":[95],"We":[96],"also":[97],"spatial":[100],"self-attention":[101],"mechanism":[102],"neighborhood":[106],"pixel":[107],"intensity":[108],"loss":[109],"to":[110],"preserve":[111],"structural":[112,126],"information":[113],"local":[115],"intensity,":[116],"respectively.":[117],"Our":[118],"outperforms":[120],"existing":[121],"methods":[122],"terms":[124],"similarity":[127,138],"(SSIM),":[128],"peak":[129],"signal-to-noise":[130],"ratio":[131],"(PSNR),":[132],"learned":[134],"perceptual":[135],"image":[136],"patch":[137],"(LPIPS)":[139],"scores":[140],"on":[141],"five":[142],"public":[143],"datasets.":[144,172],"More":[145],"precisely,":[146],"our":[147,179],"model":[148],"exhibited":[149],"an":[150],"average":[151],"improvement":[152],"4.64%,":[154],"18.5%,":[155],"42%":[157],"concerning":[158],"SSIM,":[159],"PSNR,":[160],"LPIPS":[162],"second":[165],"most":[166],"proficient":[167],"method":[168,181],"correspondingly,":[169],"across":[170],"all":[171],"The":[173],"results":[174],"demonstrate":[175],"proposed":[180],"generating":[183],"high-quality":[184],"predictions":[185],"frames.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}