Matches in SemOpenAlex for { <https://semopenalex.org/work/W3107295910> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3107295910 endingPage "979" @default.
- W3107295910 startingPage "969" @default.
- W3107295910 abstract "Temporal observations such as videos contain essential information about the dynamics of the underlying scene, but they are often interleaved with inessential, predictable details. One way of dealing with this problem is by focusing on the most informative moments in a sequence. We propose a model that learns to discover these important events and the times when they occur and uses them to represent the full sequence. We do so using a hierarchical Keyframe-Inpainter (KeyIn) model that first generates a video's keyframes and then inpaints the rest by generating the frames at the intervening times. We propose a fully differentiable formulation to efficiently learn this procedure. We show that KeyIn finds informative keyframes in several datasets with different dynamics and visual properties. KeyIn outperforms other recent hierarchical predictive models for planning. For more details, please see the project website at url{this https URL}." @default.
- W3107295910 created "2020-12-07" @default.
- W3107295910 creator A5010059469 @default.
- W3107295910 creator A5035555714 @default.
- W3107295910 creator A5050660826 @default.
- W3107295910 creator A5051121535 @default.
- W3107295910 creator A5052269532 @default.
- W3107295910 creator A5054155451 @default.
- W3107295910 creator A5060769258 @default.
- W3107295910 creator A5067594179 @default.
- W3107295910 date "2020-06-08" @default.
- W3107295910 modified "2023-09-23" @default.
- W3107295910 title "Keyframing the Future: Keyframe Discovery for Visual Prediction and Planning" @default.
- W3107295910 hasPublicationYear "2020" @default.
- W3107295910 type Work @default.
- W3107295910 sameAs 3107295910 @default.
- W3107295910 citedByCount "8" @default.
- W3107295910 countsByYear W31072959102020 @default.
- W3107295910 countsByYear W31072959102021 @default.
- W3107295910 crossrefType "journal-article" @default.
- W3107295910 hasAuthorship W3107295910A5010059469 @default.
- W3107295910 hasAuthorship W3107295910A5035555714 @default.
- W3107295910 hasAuthorship W3107295910A5050660826 @default.
- W3107295910 hasAuthorship W3107295910A5051121535 @default.
- W3107295910 hasAuthorship W3107295910A5052269532 @default.
- W3107295910 hasAuthorship W3107295910A5054155451 @default.
- W3107295910 hasAuthorship W3107295910A5060769258 @default.
- W3107295910 hasAuthorship W3107295910A5067594179 @default.
- W3107295910 hasConcept C119857082 @default.
- W3107295910 hasConcept C121332964 @default.
- W3107295910 hasConcept C124101348 @default.
- W3107295910 hasConcept C144986985 @default.
- W3107295910 hasConcept C145912823 @default.
- W3107295910 hasConcept C154945302 @default.
- W3107295910 hasConcept C24890656 @default.
- W3107295910 hasConcept C2778112365 @default.
- W3107295910 hasConcept C41008148 @default.
- W3107295910 hasConcept C54355233 @default.
- W3107295910 hasConcept C86803240 @default.
- W3107295910 hasConceptScore W3107295910C119857082 @default.
- W3107295910 hasConceptScore W3107295910C121332964 @default.
- W3107295910 hasConceptScore W3107295910C124101348 @default.
- W3107295910 hasConceptScore W3107295910C144986985 @default.
- W3107295910 hasConceptScore W3107295910C145912823 @default.
- W3107295910 hasConceptScore W3107295910C154945302 @default.
- W3107295910 hasConceptScore W3107295910C24890656 @default.
- W3107295910 hasConceptScore W3107295910C2778112365 @default.
- W3107295910 hasConceptScore W3107295910C41008148 @default.
- W3107295910 hasConceptScore W3107295910C54355233 @default.
- W3107295910 hasConceptScore W3107295910C86803240 @default.
- W3107295910 hasLocation W31072959101 @default.
- W3107295910 hasOpenAccess W3107295910 @default.
- W3107295910 hasPrimaryLocation W31072959101 @default.
- W3107295910 hasRelatedWork W192235773 @default.
- W3107295910 hasRelatedWork W2009788881 @default.
- W3107295910 hasRelatedWork W2251353663 @default.
- W3107295910 hasRelatedWork W2296744054 @default.
- W3107295910 hasRelatedWork W2547401708 @default.
- W3107295910 hasRelatedWork W2548993058 @default.
- W3107295910 hasRelatedWork W2576295345 @default.
- W3107295910 hasRelatedWork W2964121744 @default.
- W3107295910 hasRelatedWork W2965433310 @default.
- W3107295910 hasRelatedWork W2978660225 @default.
- W3107295910 hasRelatedWork W2982209458 @default.
- W3107295910 hasRelatedWork W2991024531 @default.
- W3107295910 hasRelatedWork W3021329436 @default.
- W3107295910 hasRelatedWork W3024690827 @default.
- W3107295910 hasRelatedWork W3103577395 @default.
- W3107295910 hasRelatedWork W3104180728 @default.
- W3107295910 hasRelatedWork W3122720668 @default.
- W3107295910 hasRelatedWork W3136275882 @default.
- W3107295910 hasRelatedWork W3170972077 @default.
- W3107295910 hasRelatedWork W3193627206 @default.
- W3107295910 isParatext "false" @default.
- W3107295910 isRetracted "false" @default.
- W3107295910 magId "3107295910" @default.
- W3107295910 workType "article" @default.