Matches in SemOpenAlex for { <https://semopenalex.org/work/W3021120485> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3021120485 endingPage "258" @default.
- W3021120485 startingPage "247" @default.
- W3021120485 abstract "Manual annotation of video segmentation datasets requires an immense amount of human effort, thus, reduction of human annotation costs is an active topic of research. While many papers deal with the propagation of masks through frames of a video, only a few results attempt to optimize annotation task selection. In this paper we present a deep learning based solution to the latter problem and train it using Reinforcement Learning. Our approach utilizes a modified version of the Dueling Deep Q-Network sharing weight parameters across the temporal axis of the video. This technique enables the trained agent to select annotation tasks from the whole video. We evaluate our annotation task selection method by means of a hierarchical supervoxel segmentation based mask propagation algorithm." @default.
- W3021120485 created "2020-05-13" @default.
- W3021120485 creator A5055832443 @default.
- W3021120485 creator A5066832439 @default.
- W3021120485 date "2020-09-01" @default.
- W3021120485 modified "2023-10-18" @default.
- W3021120485 title "Reducing human efforts in video segmentation annotation with reinforcement learning" @default.
- W3021120485 cites W2031489346 @default.
- W3021120485 cites W2062563118 @default.
- W3021120485 cites W2101309634 @default.
- W3021120485 cites W2108598243 @default.
- W3021120485 cites W2113137767 @default.
- W3021120485 cites W2124225542 @default.
- W3021120485 cites W2124351162 @default.
- W3021120485 cites W2143516773 @default.
- W3021120485 cites W2145339207 @default.
- W3021120485 cites W2585293115 @default.
- W3021120485 cites W2588240745 @default.
- W3021120485 cites W2804284560 @default.
- W3021120485 cites W2963732700 @default.
- W3021120485 cites W2964218467 @default.
- W3021120485 doi "https://doi.org/10.1016/j.neucom.2020.02.127" @default.
- W3021120485 hasPublicationYear "2020" @default.
- W3021120485 type Work @default.
- W3021120485 sameAs 3021120485 @default.
- W3021120485 citedByCount "8" @default.
- W3021120485 countsByYear W30211204852021 @default.
- W3021120485 countsByYear W30211204852022 @default.
- W3021120485 countsByYear W30211204852023 @default.
- W3021120485 crossrefType "journal-article" @default.
- W3021120485 hasAuthorship W3021120485A5055832443 @default.
- W3021120485 hasAuthorship W3021120485A5066832439 @default.
- W3021120485 hasBestOaLocation W30211204851 @default.
- W3021120485 hasConcept C119857082 @default.
- W3021120485 hasConcept C153180895 @default.
- W3021120485 hasConcept C154945302 @default.
- W3021120485 hasConcept C162324750 @default.
- W3021120485 hasConcept C187736073 @default.
- W3021120485 hasConcept C2776321320 @default.
- W3021120485 hasConcept C2780451532 @default.
- W3021120485 hasConcept C41008148 @default.
- W3021120485 hasConcept C81917197 @default.
- W3021120485 hasConcept C89600930 @default.
- W3021120485 hasConcept C97541855 @default.
- W3021120485 hasConceptScore W3021120485C119857082 @default.
- W3021120485 hasConceptScore W3021120485C153180895 @default.
- W3021120485 hasConceptScore W3021120485C154945302 @default.
- W3021120485 hasConceptScore W3021120485C162324750 @default.
- W3021120485 hasConceptScore W3021120485C187736073 @default.
- W3021120485 hasConceptScore W3021120485C2776321320 @default.
- W3021120485 hasConceptScore W3021120485C2780451532 @default.
- W3021120485 hasConceptScore W3021120485C41008148 @default.
- W3021120485 hasConceptScore W3021120485C81917197 @default.
- W3021120485 hasConceptScore W3021120485C89600930 @default.
- W3021120485 hasConceptScore W3021120485C97541855 @default.
- W3021120485 hasFunder F4320338080 @default.
- W3021120485 hasLocation W30211204851 @default.
- W3021120485 hasOpenAccess W3021120485 @default.
- W3021120485 hasPrimaryLocation W30211204851 @default.
- W3021120485 hasRelatedWork W1529400504 @default.
- W3021120485 hasRelatedWork W1892467659 @default.
- W3021120485 hasRelatedWork W260766989 @default.
- W3021120485 hasRelatedWork W2959276766 @default.
- W3021120485 hasRelatedWork W2961085424 @default.
- W3021120485 hasRelatedWork W3037422413 @default.
- W3021120485 hasRelatedWork W3139193008 @default.
- W3021120485 hasRelatedWork W4206669594 @default.
- W3021120485 hasRelatedWork W4295941380 @default.
- W3021120485 hasRelatedWork W4319083788 @default.
- W3021120485 hasVolume "405" @default.
- W3021120485 isParatext "false" @default.
- W3021120485 isRetracted "false" @default.
- W3021120485 magId "3021120485" @default.
- W3021120485 workType "article" @default.