Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379931083> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W4379931083 abstract "In this talk, I will first discuss approaches that reduce the GFLOPs during inference for 3D convolutional neural networks (CNN) and vision transformers. While state-of-the-art 3D CNNs and vision transformers achieve very good results on action recognition datasets, they are computationally very expensive and require many GFLOPs. While the GFLOPs of a 3D CNN or vision transformer can be decreased by reducing the temporal feature resolution or the number of tokens, there is no setting that is optimal for all input clips. I will therefore discuss two differentiable sampling approaches that can be plugged into any existing 3D CNN or vision transformer architecture. The sampling approaches adapt the computational resources to the input video such that as much resources as needed but not more than necessary are used to classify a video. The approaches substantially reduce the computational cost (GFLOPs) of state-of-the-art networks while preserving the accuracy. In the second part, I will discuss an approach that generates annotated training samples of very rare classes. It is based on a generative adversarial network (GAN) that jointly synthesizes images and the corresponding segmentation mask for each image. The generated data can then be used for one-shot video object segmentation." @default.
- W4379931083 created "2023-06-09" @default.
- W4379931083 creator A5025592506 @default.
- W4379931083 date "2023-06-12" @default.
- W4379931083 modified "2023-09-26" @default.
- W4379931083 title "Efficient CNNs and Transformers for Video Understanding and Image Synthesis" @default.
- W4379931083 doi "https://doi.org/10.1145/3591106.3592300" @default.
- W4379931083 hasPublicationYear "2023" @default.
- W4379931083 type Work @default.
- W4379931083 citedByCount "0" @default.
- W4379931083 crossrefType "proceedings-article" @default.
- W4379931083 hasAuthorship W4379931083A5025592506 @default.
- W4379931083 hasConcept C108583219 @default.
- W4379931083 hasConcept C121332964 @default.
- W4379931083 hasConcept C153180895 @default.
- W4379931083 hasConcept C154945302 @default.
- W4379931083 hasConcept C165801399 @default.
- W4379931083 hasConcept C173608175 @default.
- W4379931083 hasConcept C2776151529 @default.
- W4379931083 hasConcept C2776214188 @default.
- W4379931083 hasConcept C31972630 @default.
- W4379931083 hasConcept C3826847 @default.
- W4379931083 hasConcept C41008148 @default.
- W4379931083 hasConcept C62520636 @default.
- W4379931083 hasConcept C66322947 @default.
- W4379931083 hasConcept C81363708 @default.
- W4379931083 hasConcept C89600930 @default.
- W4379931083 hasConceptScore W4379931083C108583219 @default.
- W4379931083 hasConceptScore W4379931083C121332964 @default.
- W4379931083 hasConceptScore W4379931083C153180895 @default.
- W4379931083 hasConceptScore W4379931083C154945302 @default.
- W4379931083 hasConceptScore W4379931083C165801399 @default.
- W4379931083 hasConceptScore W4379931083C173608175 @default.
- W4379931083 hasConceptScore W4379931083C2776151529 @default.
- W4379931083 hasConceptScore W4379931083C2776214188 @default.
- W4379931083 hasConceptScore W4379931083C31972630 @default.
- W4379931083 hasConceptScore W4379931083C3826847 @default.
- W4379931083 hasConceptScore W4379931083C41008148 @default.
- W4379931083 hasConceptScore W4379931083C62520636 @default.
- W4379931083 hasConceptScore W4379931083C66322947 @default.
- W4379931083 hasConceptScore W4379931083C81363708 @default.
- W4379931083 hasConceptScore W4379931083C89600930 @default.
- W4379931083 hasLocation W43799310831 @default.
- W4379931083 hasOpenAccess W4379931083 @default.
- W4379931083 hasPrimaryLocation W43799310831 @default.
- W4379931083 hasRelatedWork W2004370856 @default.
- W4379931083 hasRelatedWork W2613186388 @default.
- W4379931083 hasRelatedWork W2738221750 @default.
- W4379931083 hasRelatedWork W3036934147 @default.
- W4379931083 hasRelatedWork W3102253946 @default.
- W4379931083 hasRelatedWork W3144574764 @default.
- W4379931083 hasRelatedWork W3156786002 @default.
- W4379931083 hasRelatedWork W4293211451 @default.
- W4379931083 hasRelatedWork W4308191152 @default.
- W4379931083 hasRelatedWork W4311401716 @default.
- W4379931083 isParatext "false" @default.
- W4379931083 isRetracted "false" @default.
- W4379931083 workType "article" @default.