Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312305807> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4312305807 abstract "In this paper, we propose a new Transformer block for video future frames prediction based on an efficient local spatial-temporal separation attention mechanism. Based on this new Transformer block, a fully autoregressive video future frames prediction Transformer is proposed. In addition, a non-autoregressive video prediction Transformer is also proposed to increase the inference speed and reduce the accumulated inference errors of its autoregressive counterpart. In order to avoid the prediction of very similar future frames, a contrastive feature loss is applied to maximize the mutual information between predicted and ground-truth future frame features. This work is the first that makes a formal comparison of the two types of attention-based video future frames prediction models over different scenarios. The proposed models reach a performance competitive with more complex state-of-the-art models. The source code is available at https://github.com/XiYe20/VPTR." @default.
- W4312305807 created "2023-01-04" @default.
- W4312305807 creator A5023333652 @default.
- W4312305807 creator A5069984230 @default.
- W4312305807 date "2022-08-21" @default.
- W4312305807 modified "2023-09-30" @default.
- W4312305807 title "VPTR: Efficient Transformers for Video Prediction" @default.
- W4312305807 cites W2163922914 @default.
- W4312305807 cites W219040644 @default.
- W4312305807 cites W2626530627 @default.
- W4312305807 cites W2962785568 @default.
- W4312305807 cites W2963073614 @default.
- W4312305807 cites W2963536265 @default.
- W4312305807 cites W2963610939 @default.
- W4312305807 cites W2963925437 @default.
- W4312305807 cites W2970752013 @default.
- W4312305807 cites W2981689412 @default.
- W4312305807 cites W2991019415 @default.
- W4312305807 cites W2991506670 @default.
- W4312305807 cites W3010309798 @default.
- W4312305807 cites W3035005073 @default.
- W4312305807 cites W3035265644 @default.
- W4312305807 cites W3035540643 @default.
- W4312305807 cites W3097065222 @default.
- W4312305807 cites W3131500599 @default.
- W4312305807 cites W3138516171 @default.
- W4312305807 cites W3139633126 @default.
- W4312305807 cites W3180355996 @default.
- W4312305807 cites W3181942264 @default.
- W4312305807 cites W3206493939 @default.
- W4312305807 cites W4214612132 @default.
- W4312305807 cites W4214614183 @default.
- W4312305807 cites W4249279051 @default.
- W4312305807 doi "https://doi.org/10.1109/icpr56361.2022.9956707" @default.
- W4312305807 hasPublicationYear "2022" @default.
- W4312305807 type Work @default.
- W4312305807 citedByCount "1" @default.
- W4312305807 countsByYear W43123058072023 @default.
- W4312305807 crossrefType "proceedings-article" @default.
- W4312305807 hasAuthorship W4312305807A5023333652 @default.
- W4312305807 hasAuthorship W4312305807A5069984230 @default.
- W4312305807 hasBestOaLocation W43123058072 @default.
- W4312305807 hasConcept C119599485 @default.
- W4312305807 hasConcept C119857082 @default.
- W4312305807 hasConcept C127413603 @default.
- W4312305807 hasConcept C146849305 @default.
- W4312305807 hasConcept C149782125 @default.
- W4312305807 hasConcept C153180895 @default.
- W4312305807 hasConcept C154945302 @default.
- W4312305807 hasConcept C159877910 @default.
- W4312305807 hasConcept C162324750 @default.
- W4312305807 hasConcept C165801399 @default.
- W4312305807 hasConcept C2776214188 @default.
- W4312305807 hasConcept C41008148 @default.
- W4312305807 hasConcept C66322947 @default.
- W4312305807 hasConceptScore W4312305807C119599485 @default.
- W4312305807 hasConceptScore W4312305807C119857082 @default.
- W4312305807 hasConceptScore W4312305807C127413603 @default.
- W4312305807 hasConceptScore W4312305807C146849305 @default.
- W4312305807 hasConceptScore W4312305807C149782125 @default.
- W4312305807 hasConceptScore W4312305807C153180895 @default.
- W4312305807 hasConceptScore W4312305807C154945302 @default.
- W4312305807 hasConceptScore W4312305807C159877910 @default.
- W4312305807 hasConceptScore W4312305807C162324750 @default.
- W4312305807 hasConceptScore W4312305807C165801399 @default.
- W4312305807 hasConceptScore W4312305807C2776214188 @default.
- W4312305807 hasConceptScore W4312305807C41008148 @default.
- W4312305807 hasConceptScore W4312305807C66322947 @default.
- W4312305807 hasLocation W43123058071 @default.
- W4312305807 hasLocation W43123058072 @default.
- W4312305807 hasOpenAccess W4312305807 @default.
- W4312305807 hasPrimaryLocation W43123058071 @default.
- W4312305807 hasRelatedWork W2372328424 @default.
- W4312305807 hasRelatedWork W2511279186 @default.
- W4312305807 hasRelatedWork W2963058055 @default.
- W4312305807 hasRelatedWork W2989134874 @default.
- W4312305807 hasRelatedWork W3014413043 @default.
- W4312305807 hasRelatedWork W3206689743 @default.
- W4312305807 hasRelatedWork W4225344190 @default.
- W4312305807 hasRelatedWork W4283644197 @default.
- W4312305807 hasRelatedWork W4303874710 @default.
- W4312305807 hasRelatedWork W4310915510 @default.
- W4312305807 isParatext "false" @default.
- W4312305807 isRetracted "false" @default.
- W4312305807 workType "article" @default.