Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206651063> ?p ?o ?g. }
- W3206651063 abstract "Nowadays, scene text recognition has attracted more and more attention due to its various applications. Most state-of-the-art methods adopt an encoder-decoder framework with attention mechanism, which generates text autoregressively from left to right. Despite the convincing performance, the speed is limited because of the one-by-one decoding strategy. As opposed to autoregressive models, non-autoregressive models predict the results in parallel with a much shorter inference time, but the accuracy falls behind the autoregressive counterpart considerably. In this paper, we propose a Parallel, Iterative and Mimicking Network (PIMNet) to balance accuracy and efficiency. Specifically, PIMNet adopts a parallel attention mechanism to predict the text faster and an iterative generation mechanism to make the predictions more accurate. In each iteration, the context information is fully explored. To improve learning of the hidden layer, we exploit the mimicking learning in the training phase, where an additional autoregressive decoder is adopted and the parallel decoder mimics the autoregressive decoder with fitting outputs of the hidden layer. With the shared backbone between the two decoders, the proposed PIMNet can be trained end-to-end without pre-training. During inference, the branch of the autoregressive decoder is removed for a faster speed. Extensive experiments on public benchmarks demonstrate the effectiveness and efficiency of PIMNet. Our code is available in the supplementary material." @default.
- W3206651063 created "2021-10-25" @default.
- W3206651063 creator A5009994877 @default.
- W3206651063 creator A5016175345 @default.
- W3206651063 creator A5026666926 @default.
- W3206651063 creator A5031767581 @default.
- W3206651063 creator A5046597133 @default.
- W3206651063 creator A5047382378 @default.
- W3206651063 creator A5052756710 @default.
- W3206651063 creator A5077114895 @default.
- W3206651063 date "2021-10-17" @default.
- W3206651063 modified "2023-10-16" @default.
- W3206651063 title "PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition" @default.
- W3206651063 cites W1569614731 @default.
- W3206651063 cites W1922126009 @default.
- W3206651063 cites W1971822075 @default.
- W3206651063 cites W1978729128 @default.
- W3206651063 cites W1981283549 @default.
- W3206651063 cites W1998042868 @default.
- W3206651063 cites W2008806374 @default.
- W3206651063 cites W2144554289 @default.
- W3206651063 cites W2146835493 @default.
- W3206651063 cites W2194187530 @default.
- W3206651063 cites W2272681403 @default.
- W3206651063 cites W2532759528 @default.
- W3206651063 cites W2896034938 @default.
- W3206651063 cites W2963233387 @default.
- W3206651063 cites W2963536265 @default.
- W3206651063 cites W2965066169 @default.
- W3206651063 cites W2988975212 @default.
- W3206651063 cites W2997749585 @default.
- W3206651063 cites W2997907976 @default.
- W3206651063 cites W2998382406 @default.
- W3206651063 cites W3034381931 @default.
- W3206651063 cites W3092863018 @default.
- W3206651063 cites W3092894544 @default.
- W3206651063 cites W3097874139 @default.
- W3206651063 cites W3105966348 @default.
- W3206651063 cites W3109576564 @default.
- W3206651063 cites W3160053372 @default.
- W3206651063 cites W3169714379 @default.
- W3206651063 cites W3178292378 @default.
- W3206651063 cites W3178307467 @default.
- W3206651063 doi "https://doi.org/10.1145/3474085.3475238" @default.
- W3206651063 hasPublicationYear "2021" @default.
- W3206651063 type Work @default.
- W3206651063 sameAs 3206651063 @default.
- W3206651063 citedByCount "20" @default.
- W3206651063 countsByYear W32066510632021 @default.
- W3206651063 countsByYear W32066510632022 @default.
- W3206651063 countsByYear W32066510632023 @default.
- W3206651063 crossrefType "proceedings-article" @default.
- W3206651063 hasAuthorship W3206651063A5009994877 @default.
- W3206651063 hasAuthorship W3206651063A5016175345 @default.
- W3206651063 hasAuthorship W3206651063A5026666926 @default.
- W3206651063 hasAuthorship W3206651063A5031767581 @default.
- W3206651063 hasAuthorship W3206651063A5046597133 @default.
- W3206651063 hasAuthorship W3206651063A5047382378 @default.
- W3206651063 hasAuthorship W3206651063A5052756710 @default.
- W3206651063 hasAuthorship W3206651063A5077114895 @default.
- W3206651063 hasBestOaLocation W32066510632 @default.
- W3206651063 hasConcept C111919701 @default.
- W3206651063 hasConcept C11413529 @default.
- W3206651063 hasConcept C118505674 @default.
- W3206651063 hasConcept C119857082 @default.
- W3206651063 hasConcept C149782125 @default.
- W3206651063 hasConcept C151730666 @default.
- W3206651063 hasConcept C153180895 @default.
- W3206651063 hasConcept C154945302 @default.
- W3206651063 hasConcept C159877910 @default.
- W3206651063 hasConcept C2776214188 @default.
- W3206651063 hasConcept C2779343474 @default.
- W3206651063 hasConcept C2779982483 @default.
- W3206651063 hasConcept C33923547 @default.
- W3206651063 hasConcept C41008148 @default.
- W3206651063 hasConcept C57273362 @default.
- W3206651063 hasConcept C86803240 @default.
- W3206651063 hasConceptScore W3206651063C111919701 @default.
- W3206651063 hasConceptScore W3206651063C11413529 @default.
- W3206651063 hasConceptScore W3206651063C118505674 @default.
- W3206651063 hasConceptScore W3206651063C119857082 @default.
- W3206651063 hasConceptScore W3206651063C149782125 @default.
- W3206651063 hasConceptScore W3206651063C151730666 @default.
- W3206651063 hasConceptScore W3206651063C153180895 @default.
- W3206651063 hasConceptScore W3206651063C154945302 @default.
- W3206651063 hasConceptScore W3206651063C159877910 @default.
- W3206651063 hasConceptScore W3206651063C2776214188 @default.
- W3206651063 hasConceptScore W3206651063C2779343474 @default.
- W3206651063 hasConceptScore W3206651063C2779982483 @default.
- W3206651063 hasConceptScore W3206651063C33923547 @default.
- W3206651063 hasConceptScore W3206651063C41008148 @default.
- W3206651063 hasConceptScore W3206651063C57273362 @default.
- W3206651063 hasConceptScore W3206651063C86803240 @default.
- W3206651063 hasLocation W32066510631 @default.
- W3206651063 hasLocation W32066510632 @default.
- W3206651063 hasOpenAccess W3206651063 @default.
- W3206651063 hasPrimaryLocation W32066510631 @default.
- W3206651063 hasRelatedWork W1520183331 @default.
- W3206651063 hasRelatedWork W1972271943 @default.
- W3206651063 hasRelatedWork W2099889858 @default.