Matches in SemOpenAlex for { <https://semopenalex.org/work/W2601686579> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2601686579 abstract "The ability to predict and therefore to anticipate the future is an important attribute of intelligence. It is also of utmost importance in real-time systems, e.g. in robotics or autonomous driving, which depend on visual scene understanding for decision making. While prediction of the raw RGB pixel values in future video frames has been studied in previous work, here we introduce the novel task of predicting semantic segmentations of future frames. Given a sequence of video frames, our goal is to predict segmentation maps of not yet observed video frames that lie up to a second or further in the future. We develop an autoregressive convolutional neural network that learns to iteratively generate multiple frames. Our results on the Cityscapes dataset show that directly predicting future segmentations is substantially better than predicting and then segmenting future RGB frames. Prediction results up to half a second in the future are visually convincing and are much more accurate than those of a baseline based on warping semantic segmentations using optical flow." @default.
- W2601686579 created "2017-04-07" @default.
- W2601686579 creator A5001226970 @default.
- W2601686579 creator A5004095177 @default.
- W2601686579 creator A5030447052 @default.
- W2601686579 creator A5036438597 @default.
- W2601686579 creator A5040312210 @default.
- W2601686579 date "2017-10-01" @default.
- W2601686579 modified "2023-10-13" @default.
- W2601686579 title "Predicting Deeper into the Future of Semantic Segmentation" @default.
- W2601686579 cites W1903029394 @default.
- W2601686579 cites W1971129545 @default.
- W2601686579 cites W1982185844 @default.
- W2601686579 cites W2016776918 @default.
- W2601686579 cites W2022508996 @default.
- W2601686579 cites W2045792079 @default.
- W2601686579 cites W2064675550 @default.
- W2601686579 cites W2133665775 @default.
- W2601686579 cites W2134944993 @default.
- W2601686579 cites W2340897893 @default.
- W2601686579 doi "https://doi.org/10.1109/iccv.2017.77" @default.
- W2601686579 hasPublicationYear "2017" @default.
- W2601686579 type Work @default.
- W2601686579 sameAs 2601686579 @default.
- W2601686579 citedByCount "180" @default.
- W2601686579 countsByYear W26016865792017 @default.
- W2601686579 countsByYear W26016865792018 @default.
- W2601686579 countsByYear W26016865792019 @default.
- W2601686579 countsByYear W26016865792020 @default.
- W2601686579 countsByYear W26016865792021 @default.
- W2601686579 countsByYear W26016865792022 @default.
- W2601686579 countsByYear W26016865792023 @default.
- W2601686579 crossrefType "proceedings-article" @default.
- W2601686579 hasAuthorship W2601686579A5001226970 @default.
- W2601686579 hasAuthorship W2601686579A5004095177 @default.
- W2601686579 hasAuthorship W2601686579A5030447052 @default.
- W2601686579 hasAuthorship W2601686579A5036438597 @default.
- W2601686579 hasAuthorship W2601686579A5040312210 @default.
- W2601686579 hasBestOaLocation W26016865792 @default.
- W2601686579 hasConcept C115961682 @default.
- W2601686579 hasConcept C119857082 @default.
- W2601686579 hasConcept C153180895 @default.
- W2601686579 hasConcept C154945302 @default.
- W2601686579 hasConcept C155542232 @default.
- W2601686579 hasConcept C157202957 @default.
- W2601686579 hasConcept C162324750 @default.
- W2601686579 hasConcept C187736073 @default.
- W2601686579 hasConcept C2780451532 @default.
- W2601686579 hasConcept C31972630 @default.
- W2601686579 hasConcept C41008148 @default.
- W2601686579 hasConcept C81363708 @default.
- W2601686579 hasConcept C82990744 @default.
- W2601686579 hasConcept C89600930 @default.
- W2601686579 hasConceptScore W2601686579C115961682 @default.
- W2601686579 hasConceptScore W2601686579C119857082 @default.
- W2601686579 hasConceptScore W2601686579C153180895 @default.
- W2601686579 hasConceptScore W2601686579C154945302 @default.
- W2601686579 hasConceptScore W2601686579C155542232 @default.
- W2601686579 hasConceptScore W2601686579C157202957 @default.
- W2601686579 hasConceptScore W2601686579C162324750 @default.
- W2601686579 hasConceptScore W2601686579C187736073 @default.
- W2601686579 hasConceptScore W2601686579C2780451532 @default.
- W2601686579 hasConceptScore W2601686579C31972630 @default.
- W2601686579 hasConceptScore W2601686579C41008148 @default.
- W2601686579 hasConceptScore W2601686579C81363708 @default.
- W2601686579 hasConceptScore W2601686579C82990744 @default.
- W2601686579 hasConceptScore W2601686579C89600930 @default.
- W2601686579 hasLocation W26016865791 @default.
- W2601686579 hasLocation W26016865792 @default.
- W2601686579 hasLocation W26016865793 @default.
- W2601686579 hasLocation W26016865794 @default.
- W2601686579 hasLocation W26016865795 @default.
- W2601686579 hasOpenAccess W2601686579 @default.
- W2601686579 hasPrimaryLocation W26016865791 @default.
- W2601686579 hasRelatedWork W1979149155 @default.
- W2601686579 hasRelatedWork W2056979260 @default.
- W2601686579 hasRelatedWork W2081419950 @default.
- W2601686579 hasRelatedWork W2116300362 @default.
- W2601686579 hasRelatedWork W2143630701 @default.
- W2601686579 hasRelatedWork W2621079708 @default.
- W2601686579 hasRelatedWork W2755343736 @default.
- W2601686579 hasRelatedWork W2901949253 @default.
- W2601686579 hasRelatedWork W3088596192 @default.
- W2601686579 hasRelatedWork W3172812035 @default.
- W2601686579 isParatext "false" @default.
- W2601686579 isRetracted "false" @default.
- W2601686579 magId "2601686579" @default.
- W2601686579 workType "article" @default.