Matches in SemOpenAlex for { <https://semopenalex.org/work/W2883451034> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2883451034 endingPage "814" @default.
- W2883451034 startingPage "797" @default.
- W2883451034 abstract "Self-supervised learning of convolutional neural networks can harness large amounts of cheap unlabeled data to train powerful feature representations. As surrogate task, we jointly address ordering of visual data in the spatial and temporal domain. The permutations of training samples, which are at the core of self-supervision by ordering, have so far been sampled randomly from a fixed preselected set. Based on deep reinforcement learning we propose a sampling policy that adapts to the state of the network, which is being trained. Therefore, new permutations are sampled according to their expected utility for updating the convolutional feature representation. Experimental evaluation on unsupervised and transfer learning tasks demonstrates competitive performance on standard benchmarks for image and video classification and nearest neighbor retrieval." @default.
- W2883451034 created "2018-08-03" @default.
- W2883451034 creator A5011964759 @default.
- W2883451034 creator A5074576698 @default.
- W2883451034 creator A5084415727 @default.
- W2883451034 date "2018-01-01" @default.
- W2883451034 modified "2023-10-14" @default.
- W2883451034 title "Improving Spatiotemporal Self-supervision by Deep Reinforcement Learning" @default.
- W2883451034 cites W1903029394 @default.
- W2883451034 cites W1993411524 @default.
- W2883451034 cites W2064675550 @default.
- W2883451034 cites W2117539524 @default.
- W2883451034 cites W2126579184 @default.
- W2883451034 cites W2145339207 @default.
- W2883451034 cites W2155893237 @default.
- W2883451034 cites W219040644 @default.
- W2883451034 cites W2257979135 @default.
- W2883451034 cites W2296073425 @default.
- W2883451034 cites W2321533354 @default.
- W2883451034 cites W2326925005 @default.
- W2883451034 cites W2507009361 @default.
- W2883451034 cites W2511428026 @default.
- W2883451034 cites W2550462002 @default.
- W2883451034 cites W2558661413 @default.
- W2883451034 cites W2575671312 @default.
- W2883451034 cites W2578257192 @default.
- W2883451034 cites W2599837529 @default.
- W2883451034 cites W2606014079 @default.
- W2883451034 cites W2745436507 @default.
- W2883451034 cites W2750549109 @default.
- W2883451034 cites W2788970402 @default.
- W2883451034 cites W2962824366 @default.
- W2883451034 cites W2962843838 @default.
- W2883451034 cites W2963420272 @default.
- W2883451034 cites W2963437997 @default.
- W2883451034 cites W2963465221 @default.
- W2883451034 cites W2963749571 @default.
- W2883451034 cites W2963785020 @default.
- W2883451034 cites W2964037671 @default.
- W2883451034 cites W2964178561 @default.
- W2883451034 cites W343636949 @default.
- W2883451034 doi "https://doi.org/10.1007/978-3-030-01267-0_47" @default.
- W2883451034 hasPublicationYear "2018" @default.
- W2883451034 type Work @default.
- W2883451034 sameAs 2883451034 @default.
- W2883451034 citedByCount "92" @default.
- W2883451034 countsByYear W28834510342018 @default.
- W2883451034 countsByYear W28834510342019 @default.
- W2883451034 countsByYear W28834510342020 @default.
- W2883451034 countsByYear W28834510342021 @default.
- W2883451034 countsByYear W28834510342022 @default.
- W2883451034 countsByYear W28834510342023 @default.
- W2883451034 crossrefType "book-chapter" @default.
- W2883451034 hasAuthorship W2883451034A5011964759 @default.
- W2883451034 hasAuthorship W2883451034A5074576698 @default.
- W2883451034 hasAuthorship W2883451034A5084415727 @default.
- W2883451034 hasBestOaLocation W28834510342 @default.
- W2883451034 hasConcept C154945302 @default.
- W2883451034 hasConcept C15744967 @default.
- W2883451034 hasConcept C41008148 @default.
- W2883451034 hasConcept C67203356 @default.
- W2883451034 hasConcept C77805123 @default.
- W2883451034 hasConcept C97541855 @default.
- W2883451034 hasConceptScore W2883451034C154945302 @default.
- W2883451034 hasConceptScore W2883451034C15744967 @default.
- W2883451034 hasConceptScore W2883451034C41008148 @default.
- W2883451034 hasConceptScore W2883451034C67203356 @default.
- W2883451034 hasConceptScore W2883451034C77805123 @default.
- W2883451034 hasConceptScore W2883451034C97541855 @default.
- W2883451034 hasLocation W28834510341 @default.
- W2883451034 hasLocation W28834510342 @default.
- W2883451034 hasOpenAccess W2883451034 @default.
- W2883451034 hasPrimaryLocation W28834510341 @default.
- W2883451034 hasRelatedWork W1562959674 @default.
- W2883451034 hasRelatedWork W2022498796 @default.
- W2883451034 hasRelatedWork W2062574812 @default.
- W2883451034 hasRelatedWork W2076575706 @default.
- W2883451034 hasRelatedWork W2748952813 @default.
- W2883451034 hasRelatedWork W2899084033 @default.
- W2883451034 hasRelatedWork W2923653485 @default.
- W2883451034 hasRelatedWork W2952472710 @default.
- W2883451034 hasRelatedWork W4210912933 @default.
- W2883451034 hasRelatedWork W4224287422 @default.
- W2883451034 isParatext "false" @default.
- W2883451034 isRetracted "false" @default.
- W2883451034 magId "2883451034" @default.
- W2883451034 workType "book-chapter" @default.