Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890636441> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W2890636441 abstract "Standard video encoders developed for conventional narrow field-of-view video are widely applied to 360° video as well, with reasonable results. However, while this approach commits arbitrarily to a projection of the spherical frames, we observe that some orientations of a 360° video, once projected, are more compressible than others. We introduce an approach to predict the sphere rotation that will yield the maximal compression rate. Given video clips in their original encoding, a convolutional neural network learns the association between a clip's visual content and its compressibility at different rotations of a cubemap projection. Given a novel video, our learning-based approach efficiently infers the most compressible direction in one shot, without repeated rendering and compression of the source video. We validate our idea on thousands of video clips and multiple popular video codecs. The results show that this untapped dimension of 360° compression has substantial potential-good rotations are typically 8-10% more compressible than bad ones, and our learning approach can predict them reliably 82% of the time." @default.
- W2890636441 created "2018-09-27" @default.
- W2890636441 creator A5012765543 @default.
- W2890636441 creator A5053331595 @default.
- W2890636441 date "2018-06-01" @default.
- W2890636441 modified "2023-10-18" @default.
- W2890636441 title "Learning Compressible 360° Video Isomers" @default.
- W2890636441 cites W1903029394 @default.
- W2890636441 cites W2045556253 @default.
- W2890636441 cites W2103189262 @default.
- W2890636441 cites W2117947052 @default.
- W2890636441 cites W2118246710 @default.
- W2890636441 cites W2121169511 @default.
- W2890636441 cites W2295499828 @default.
- W2890636441 cites W2556362500 @default.
- W2890636441 cites W2579692724 @default.
- W2890636441 cites W2593745480 @default.
- W2890636441 cites W2963149687 @default.
- W2890636441 cites W2963339238 @default.
- W2890636441 cites W2964244417 @default.
- W2890636441 doi "https://doi.org/10.1109/cvpr.2018.00816" @default.
- W2890636441 hasPublicationYear "2018" @default.
- W2890636441 type Work @default.
- W2890636441 sameAs 2890636441 @default.
- W2890636441 citedByCount "12" @default.
- W2890636441 countsByYear W28906364412018 @default.
- W2890636441 countsByYear W28906364412019 @default.
- W2890636441 countsByYear W28906364412020 @default.
- W2890636441 countsByYear W28906364412021 @default.
- W2890636441 countsByYear W28906364412022 @default.
- W2890636441 crossrefType "proceedings-article" @default.
- W2890636441 hasAuthorship W2890636441A5012765543 @default.
- W2890636441 hasAuthorship W2890636441A5053331595 @default.
- W2890636441 hasBestOaLocation W28906364412 @default.
- W2890636441 hasConcept C121684516 @default.
- W2890636441 hasConcept C41008148 @default.
- W2890636441 hasConcept C49774154 @default.
- W2890636441 hasConceptScore W2890636441C121684516 @default.
- W2890636441 hasConceptScore W2890636441C41008148 @default.
- W2890636441 hasConceptScore W2890636441C49774154 @default.
- W2890636441 hasLocation W28906364411 @default.
- W2890636441 hasLocation W28906364412 @default.
- W2890636441 hasOpenAccess W2890636441 @default.
- W2890636441 hasPrimaryLocation W28906364411 @default.
- W2890636441 hasRelatedWork W1522515376 @default.
- W2890636441 hasRelatedWork W2347883734 @default.
- W2890636441 hasRelatedWork W2355862304 @default.
- W2890636441 hasRelatedWork W2356108042 @default.
- W2890636441 hasRelatedWork W2376796979 @default.
- W2890636441 hasRelatedWork W2379285345 @default.
- W2890636441 hasRelatedWork W2379418341 @default.
- W2890636441 hasRelatedWork W2380054981 @default.
- W2890636441 hasRelatedWork W2393110101 @default.
- W2890636441 hasRelatedWork W4239328682 @default.
- W2890636441 isParatext "false" @default.
- W2890636441 isRetracted "false" @default.
- W2890636441 magId "2890636441" @default.
- W2890636441 workType "article" @default.