Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308235904> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4308235904 abstract "Predicting multiple future frames from a given video is a challenging problem due to several factors such as changing camera, dynamically moving objects, occlusions, etc. While recent deep learning methods have made significant progress on the video prediction problem, most methods predict the immediate or a fixed number of future frames. To obtain longer-term frame predictions, existing techniques usually process the predicted frames iteratively, resulting in blurry or inconsistent predictions. In this work, we present a new approach that can predict an arbitrary number of future video frames with a single forward pass through the network. Instead of directly predicting a fixed number of future optical flows or frames, we learn temporal motion encodings, i.e., temporal motion basis vectors and a network to predict the coefficients. The learned motion basis can be easily extended to arbitrary length at inference time, enabling us to predict an arbitrary number of future frames. Experiments on benchmark datasets show that our approach performs favorably against several competitive techniques even for the next frame prediction setting. When evaluated under 5-frame or 10-frame prediction settings, the proposed method achieves higher performance gains over the state-of-the-art techniques that iteratively process the predictions." @default.
- W4308235904 created "2022-11-09" @default.
- W4308235904 creator A5006447679 @default.
- W4308235904 creator A5012164804 @default.
- W4308235904 creator A5063179713 @default.
- W4308235904 creator A5085870393 @default.
- W4308235904 date "2022-10-16" @default.
- W4308235904 modified "2023-09-30" @default.
- W4308235904 title "Multi-Frame Video Prediction with Learnable Motion Encodings" @default.
- W4308235904 cites W1677182931 @default.
- W4308235904 cites W1951289974 @default.
- W4308235904 cites W2016776918 @default.
- W4308235904 cites W2031454541 @default.
- W4308235904 cites W2133665775 @default.
- W4308235904 cites W2395611524 @default.
- W4308235904 cites W2535388113 @default.
- W4308235904 cites W2560474170 @default.
- W4308235904 cites W2575671312 @default.
- W4308235904 cites W2891942975 @default.
- W4308235904 cites W2911273949 @default.
- W4308235904 cites W2962914239 @default.
- W4308235904 cites W2963302737 @default.
- W4308235904 cites W2963782415 @default.
- W4308235904 cites W2964254867 @default.
- W4308235904 cites W2989708447 @default.
- W4308235904 cites W3094891242 @default.
- W4308235904 cites W764651262 @default.
- W4308235904 doi "https://doi.org/10.1109/icip46576.2022.9897483" @default.
- W4308235904 hasPublicationYear "2022" @default.
- W4308235904 type Work @default.
- W4308235904 citedByCount "0" @default.
- W4308235904 crossrefType "proceedings-article" @default.
- W4308235904 hasAuthorship W4308235904A5006447679 @default.
- W4308235904 hasAuthorship W4308235904A5012164804 @default.
- W4308235904 hasAuthorship W4308235904A5063179713 @default.
- W4308235904 hasAuthorship W4308235904A5085870393 @default.
- W4308235904 hasConcept C10161872 @default.
- W4308235904 hasConcept C104114177 @default.
- W4308235904 hasConcept C111919701 @default.
- W4308235904 hasConcept C12426560 @default.
- W4308235904 hasConcept C126042441 @default.
- W4308235904 hasConcept C13280743 @default.
- W4308235904 hasConcept C154945302 @default.
- W4308235904 hasConcept C172849965 @default.
- W4308235904 hasConcept C185798385 @default.
- W4308235904 hasConcept C205649164 @default.
- W4308235904 hasConcept C2524010 @default.
- W4308235904 hasConcept C2776214188 @default.
- W4308235904 hasConcept C31972630 @default.
- W4308235904 hasConcept C33923547 @default.
- W4308235904 hasConcept C39394851 @default.
- W4308235904 hasConcept C41008148 @default.
- W4308235904 hasConcept C76155785 @default.
- W4308235904 hasConcept C98045186 @default.
- W4308235904 hasConceptScore W4308235904C10161872 @default.
- W4308235904 hasConceptScore W4308235904C104114177 @default.
- W4308235904 hasConceptScore W4308235904C111919701 @default.
- W4308235904 hasConceptScore W4308235904C12426560 @default.
- W4308235904 hasConceptScore W4308235904C126042441 @default.
- W4308235904 hasConceptScore W4308235904C13280743 @default.
- W4308235904 hasConceptScore W4308235904C154945302 @default.
- W4308235904 hasConceptScore W4308235904C172849965 @default.
- W4308235904 hasConceptScore W4308235904C185798385 @default.
- W4308235904 hasConceptScore W4308235904C205649164 @default.
- W4308235904 hasConceptScore W4308235904C2524010 @default.
- W4308235904 hasConceptScore W4308235904C2776214188 @default.
- W4308235904 hasConceptScore W4308235904C31972630 @default.
- W4308235904 hasConceptScore W4308235904C33923547 @default.
- W4308235904 hasConceptScore W4308235904C39394851 @default.
- W4308235904 hasConceptScore W4308235904C41008148 @default.
- W4308235904 hasConceptScore W4308235904C76155785 @default.
- W4308235904 hasConceptScore W4308235904C98045186 @default.
- W4308235904 hasLocation W43082359041 @default.
- W4308235904 hasOpenAccess W4308235904 @default.
- W4308235904 hasPrimaryLocation W43082359041 @default.
- W4308235904 hasRelatedWork W135098264 @default.
- W4308235904 hasRelatedWork W2029249305 @default.
- W4308235904 hasRelatedWork W2122456626 @default.
- W4308235904 hasRelatedWork W2140468889 @default.
- W4308235904 hasRelatedWork W2395873996 @default.
- W4308235904 hasRelatedWork W2511137960 @default.
- W4308235904 hasRelatedWork W2610014769 @default.
- W4308235904 hasRelatedWork W2687972263 @default.
- W4308235904 hasRelatedWork W3114588369 @default.
- W4308235904 hasRelatedWork W4321142835 @default.
- W4308235904 isParatext "false" @default.
- W4308235904 isRetracted "false" @default.
- W4308235904 workType "article" @default.