FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2808707363> ?p ?o ?g. }

• W2808707363 abstract "Our goal is to predict future video frames given a sequence of input frames. Despite large amounts of video data, this remains a challenging task because of the high-dimensionality of video frames. We address this challenge by proposing the Decompositional Disentangled Predictive Auto-Encoder (DDPAE), a framework that combines structured probabilistic models and deep networks to automatically (i) decompose the high-dimensional video that we aim to predict into components, and (ii) disentangle each component to have low-dimensional temporal dynamics that are easier to predict. Crucially, with an appropriately specified generative model of video frames, our DDPAE is able to learn both the latent decomposition and disentanglement without explicit supervision. For the Moving MNIST dataset, we show that DDPAE is able to recover the underlying components (individual digits) and disentanglement (appearance and location) as we would intuitively do. We further demonstrate that DDPAE can be applied to the Bouncing Balls dataset involving complex interactions between multiple objects to predict the video frame directly from the pixels and recover physical states without explicit supervision." @default.
• W2808707363 created "2018-06-21" @default.
• W2808707363 creator A5007869267 @default.
• W2808707363 creator A5018518655 @default.
• W2808707363 creator A5042066976 @default.
• W2808707363 creator A5052829033 @default.
• W2808707363 creator A5082946919 @default.
• W2808707363 date "2018-06-11" @default.
• W2808707363 modified "2023-09-27" @default.
• W2808707363 title "Learning to Decompose and Disentangle Representations for Video Prediction" @default.
• W2808707363 cites W1568514080 @default.
• W2808707363 cites W1850742715 @default.
• W2808707363 cites W1959608418 @default.
• W2808707363 cites W2118688707 @default.
• W2808707363 cites W2157331557 @default.
• W2808707363 cites W2175030374 @default.
• W2808707363 cites W2185953016 @default.
• W2808707363 cites W2235735853 @default.
• W2808707363 cites W2327562811 @default.
• W2808707363 cites W2400532028 @default.
• W2808707363 cites W2401640538 @default.
• W2808707363 cites W2424778531 @default.
• W2808707363 cites W2470142083 @default.
• W2808707363 cites W2470475590 @default.
• W2808707363 cites W2524803249 @default.
• W2808707363 cites W2559857813 @default.
• W2808707363 cites W2583901669 @default.
• W2808707363 cites W2607738331 @default.
• W2808707363 cites W2611815546 @default.
• W2808707363 cites W2615413256 @default.
• W2808707363 cites W2619034550 @default.
• W2808707363 cites W2737548191 @default.
• W2808707363 cites W2738136547 @default.
• W2808707363 cites W2774160854 @default.
• W2808707363 cites W2786615588 @default.
• W2808707363 cites W2796152145 @default.
• W2808707363 cites W2911273949 @default.
• W2808707363 cites W2949099979 @default.
• W2808707363 cites W2949247522 @default.
• W2808707363 cites W2949888546 @default.
• W2808707363 cites W2950714698 @default.
• W2808707363 cites W2952453038 @default.
• W2808707363 cites W2952484912 @default.
• W2808707363 cites W2952915411 @default.
• W2808707363 cites W2953118818 @default.
• W2808707363 cites W2962839378 @default.
• W2808707363 cites W2962889261 @default.
• W2808707363 cites W2963125871 @default.
• W2808707363 cites W2963143598 @default.
• W2808707363 cites W2963629403 @default.
• W2808707363 cites W2963684088 @default.
• W2808707363 cites W2964121744 @default.
• W2808707363 cites W2964213104 @default.
• W2808707363 cites W3093010610 @default.
• W2808707363 cites W603908379 @default.
• W2808707363 hasPublicationYear "2018" @default.
• W2808707363 type Work @default.
• W2808707363 sameAs 2808707363 @default.
• W2808707363 citedByCount "9" @default.
• W2808707363 countsByYear W28087073632018 @default.
• W2808707363 countsByYear W28087073632019 @default.
• W2808707363 countsByYear W28087073632020 @default.
• W2808707363 countsByYear W28087073632021 @default.
• W2808707363 crossrefType "posted-content" @default.
• W2808707363 hasAuthorship W2808707363A5007869267 @default.
• W2808707363 hasAuthorship W2808707363A5018518655 @default.
• W2808707363 hasAuthorship W2808707363A5042066976 @default.
• W2808707363 hasAuthorship W2808707363A5052829033 @default.
• W2808707363 hasAuthorship W2808707363A5082946919 @default.
• W2808707363 hasConcept C101738243 @default.
• W2808707363 hasConcept C108583219 @default.
• W2808707363 hasConcept C111030470 @default.
• W2808707363 hasConcept C111919701 @default.
• W2808707363 hasConcept C118505674 @default.
• W2808707363 hasConcept C119857082 @default.
• W2808707363 hasConcept C121332964 @default.
• W2808707363 hasConcept C126042441 @default.
• W2808707363 hasConcept C153180895 @default.
• W2808707363 hasConcept C154945302 @default.
• W2808707363 hasConcept C162324750 @default.
• W2808707363 hasConcept C167966045 @default.
• W2808707363 hasConcept C168167062 @default.
• W2808707363 hasConcept C187736073 @default.
• W2808707363 hasConcept C190502265 @default.
• W2808707363 hasConcept C2778112365 @default.
• W2808707363 hasConcept C2780451532 @default.
• W2808707363 hasConcept C31972630 @default.
• W2808707363 hasConcept C39890363 @default.
• W2808707363 hasConcept C41008148 @default.
• W2808707363 hasConcept C49937458 @default.
• W2808707363 hasConcept C54355233 @default.
• W2808707363 hasConcept C76155785 @default.
• W2808707363 hasConcept C86803240 @default.
• W2808707363 hasConcept C97355855 @default.
• W2808707363 hasConceptScore W2808707363C101738243 @default.
• W2808707363 hasConceptScore W2808707363C108583219 @default.
• W2808707363 hasConceptScore W2808707363C111030470 @default.
• W2808707363 hasConceptScore W2808707363C111919701 @default.
• W2808707363 hasConceptScore W2808707363C118505674 @default.
• W2808707363 hasConceptScore W2808707363C119857082 @default.

• next