Matches in SemOpenAlex for { <https://semopenalex.org/work/W2998322014> ?p ?o ?g. }
- W2998322014 abstract "This paper tackles the problem of real-time semantic segmentation of high definition videos using a hybrid GPU / CPU approach. We propose an Efficient Video Segmentation(EVS) pipeline that combines: (i) On the CPU, a very fast optical flow method, that is used to exploit the temporal aspect of the video and propagate semantic information from one frame to the next. It runs in parallel with the GPU. (ii) On the GPU, two Convolutional Neural Networks: A main segmentation network that is used to predict dense semantic labels from scratch, and a Refiner that is designed to improve predictions from previous frames with the help of a fast Inconsistencies Attention Module (IAM). The latter can identify regions that cannot be propagated accurately. We suggest several operating points depending on the desired frame rate and accuracy. Our pipeline achieves accuracy levels competitive to the existing real-time methods for semantic image segmentation(mIoU above 60%), while achieving much higher frame rates. On the popular Cityscapes dataset with high resolution frames (2048 x 1024), the proposed operating points range from 80 to 1000 Hz on a single GPU and CPU." @default.
- W2998322014 created "2020-01-10" @default.
- W2998322014 creator A5001254143 @default.
- W2998322014 creator A5032479945 @default.
- W2998322014 creator A5052236177 @default.
- W2998322014 creator A5071526929 @default.
- W2998322014 date "2019-12-26" @default.
- W2998322014 modified "2023-09-23" @default.
- W2998322014 title "Efficient Video Semantic Segmentation with Labels Propagation and Refinement" @default.
- W2998322014 cites W148565212 @default.
- W2998322014 cites W1513100184 @default.
- W2998322014 cites W1755205674 @default.
- W2998322014 cites W1903029394 @default.
- W2998322014 cites W1913356549 @default.
- W2998322014 cites W1971618559 @default.
- W2998322014 cites W2047639605 @default.
- W2998322014 cites W2068994826 @default.
- W2998322014 cites W2076756823 @default.
- W2998322014 cites W2115579991 @default.
- W2998322014 cites W2121947440 @default.
- W2998322014 cites W2163605009 @default.
- W2998322014 cites W2171943915 @default.
- W2998322014 cites W2295628903 @default.
- W2998322014 cites W2340897893 @default.
- W2998322014 cites W2412782625 @default.
- W2998322014 cites W2419448466 @default.
- W2998322014 cites W2470139095 @default.
- W2998322014 cites W2487365028 @default.
- W2998322014 cites W2552900565 @default.
- W2998322014 cites W2560023338 @default.
- W2998322014 cites W2561585794 @default.
- W2998322014 cites W2566030665 @default.
- W2998322014 cites W2606492274 @default.
- W2998322014 cites W2610147486 @default.
- W2998322014 cites W2738569017 @default.
- W2998322014 cites W2762439315 @default.
- W2998322014 cites W2907965334 @default.
- W2998322014 cites W2952147788 @default.
- W2998322014 cites W2954469458 @default.
- W2998322014 cites W2962815021 @default.
- W2998322014 cites W2963108253 @default.
- W2998322014 cites W2963418739 @default.
- W2998322014 cites W2963445119 @default.
- W2998322014 cites W2963548592 @default.
- W2998322014 cites W2963866581 @default.
- W2998322014 cites W2963881378 @default.
- W2998322014 cites W2963917006 @default.
- W2998322014 cites W2964217532 @default.
- W2998322014 cites W2964309882 @default.
- W2998322014 cites W801273237 @default.
- W2998322014 hasPublicationYear "2019" @default.
- W2998322014 type Work @default.
- W2998322014 sameAs 2998322014 @default.
- W2998322014 citedByCount "0" @default.
- W2998322014 crossrefType "posted-content" @default.
- W2998322014 hasAuthorship W2998322014A5001254143 @default.
- W2998322014 hasAuthorship W2998322014A5032479945 @default.
- W2998322014 hasAuthorship W2998322014A5052236177 @default.
- W2998322014 hasAuthorship W2998322014A5071526929 @default.
- W2998322014 hasConcept C115961682 @default.
- W2998322014 hasConcept C126042441 @default.
- W2998322014 hasConcept C154945302 @default.
- W2998322014 hasConcept C155542232 @default.
- W2998322014 hasConcept C165696696 @default.
- W2998322014 hasConcept C199360897 @default.
- W2998322014 hasConcept C31972630 @default.
- W2998322014 hasConcept C3261483 @default.
- W2998322014 hasConcept C38652104 @default.
- W2998322014 hasConcept C41008148 @default.
- W2998322014 hasConcept C43521106 @default.
- W2998322014 hasConcept C76155785 @default.
- W2998322014 hasConcept C81363708 @default.
- W2998322014 hasConcept C89600930 @default.
- W2998322014 hasConceptScore W2998322014C115961682 @default.
- W2998322014 hasConceptScore W2998322014C126042441 @default.
- W2998322014 hasConceptScore W2998322014C154945302 @default.
- W2998322014 hasConceptScore W2998322014C155542232 @default.
- W2998322014 hasConceptScore W2998322014C165696696 @default.
- W2998322014 hasConceptScore W2998322014C199360897 @default.
- W2998322014 hasConceptScore W2998322014C31972630 @default.
- W2998322014 hasConceptScore W2998322014C3261483 @default.
- W2998322014 hasConceptScore W2998322014C38652104 @default.
- W2998322014 hasConceptScore W2998322014C41008148 @default.
- W2998322014 hasConceptScore W2998322014C43521106 @default.
- W2998322014 hasConceptScore W2998322014C76155785 @default.
- W2998322014 hasConceptScore W2998322014C81363708 @default.
- W2998322014 hasConceptScore W2998322014C89600930 @default.
- W2998322014 hasOpenAccess W2998322014 @default.
- W2998322014 hasRelatedWork W2467614162 @default.
- W2998322014 hasRelatedWork W2790933182 @default.
- W2998322014 hasRelatedWork W2997806675 @default.
- W2998322014 hasRelatedWork W3021040258 @default.
- W2998322014 hasRelatedWork W3025847014 @default.
- W2998322014 hasRelatedWork W3034162943 @default.
- W2998322014 hasRelatedWork W3041819070 @default.
- W2998322014 hasRelatedWork W3099754550 @default.
- W2998322014 hasRelatedWork W3105625199 @default.
- W2998322014 hasRelatedWork W3111025150 @default.
- W2998322014 hasRelatedWork W3111273966 @default.
- W2998322014 hasRelatedWork W3128892380 @default.