FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224294196> ?p ?o ?g. }

• W4224294196 abstract "Existing leading methods for spectral reconstruction (SR) focus on designing deeper or wider convolutional neural networks (CNNs) to learn the end-to-end mapping from the RGB image to its hyperspectral image (HSI). These CNN-based methods achieve impressive restoration performance while showing limitations in capturing the long-range dependencies and self-similarity prior. To cope with this problem, we propose a novel Transformer-based method, Multi-stage Spectral-wise Transformer (MST++), for efficient spectral reconstruction. In particular, we employ Spectral-wise Multi-head Self-attention (S-MSA) that is based on the HSI spatially sparse while spectrally self-similar nature to compose the basic unit, Spectral-wise Attention Block (SAB). Then SABs build up Single-stage Spectral-wise Transformer (SST) that exploits a U-shaped structure to extract multi-resolution contextual information. Finally, our MST++, cascaded by several SSTs, progressively improves the reconstruction quality from coarse to fine. Comprehensive experiments show that our MST++ significantly outperforms other state-of-the-art methods. In the NTIRE 2022 Spectral Reconstruction Challenge, our approach won the First place. Code and pre-trained models are publicly available at https://github.com/caiyuanhao1998/MST-plus-plus." @default.
• W4224294196 created "2022-04-26" @default.
• W4224294196 creator A5001254143 @default.
• W4224294196 creator A5016580378 @default.
• W4224294196 creator A5022665877 @default.
• W4224294196 creator A5028229824 @default.
• W4224294196 creator A5038281038 @default.
• W4224294196 creator A5043151044 @default.
• W4224294196 creator A5052236177 @default.
• W4224294196 creator A5074865219 @default.
• W4224294196 date "2022-06-01" @default.
• W4224294196 modified "2023-10-04" @default.
• W4224294196 title "MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction" @default.
• W4224294196 cites W1487850528 @default.
• W4224294196 cites W1597864587 @default.
• W4224294196 cites W1986701690 @default.
• W4224294196 cites W1988386267 @default.
• W4224294196 cites W1992653101 @default.
• W4224294196 cites W2028349405 @default.
• W4224294196 cites W2052468738 @default.
• W4224294196 cites W2082590892 @default.
• W4224294196 cites W2084591647 @default.
• W4224294196 cites W2136251662 @default.
• W4224294196 cites W2144412886 @default.
• W4224294196 cites W2511401065 @default.
• W4224294196 cites W2520430674 @default.
• W4224294196 cites W2588000623 @default.
• W4224294196 cites W2766101120 @default.
• W4224294196 cites W2776639132 @default.
• W4224294196 cites W2884144629 @default.
• W4224294196 cites W2892288283 @default.
• W4224294196 cites W2893739000 @default.
• W4224294196 cites W2963372104 @default.
• W4224294196 cites W2963764784 @default.
• W4224294196 cites W2964984565 @default.
• W4224294196 cites W2983736948 @default.
• W4224294196 cites W2997797376 @default.
• W4224294196 cites W3035466729 @default.
• W4224294196 cites W3035556176 @default.
• W4224294196 cites W3035598238 @default.
• W4224294196 cites W3041490661 @default.
• W4224294196 cites W3096654432 @default.
• W4224294196 cites W3106758205 @default.
• W4224294196 cites W3113950706 @default.
• W4224294196 cites W3134510327 @default.
• W4224294196 cites W3136525061 @default.
• W4224294196 cites W3138516171 @default.
• W4224294196 cites W3151130473 @default.
• W4224294196 cites W3165924482 @default.
• W4224294196 cites W3170697543 @default.
• W4224294196 cites W3170841864 @default.
• W4224294196 cites W3171125843 @default.
• W4224294196 cites W3171613875 @default.
• W4224294196 cites W3173125503 @default.
• W4224294196 cites W3176096490 @default.
• W4224294196 cites W3176892444 @default.
• W4224294196 cites W3182390903 @default.
• W4224294196 cites W3191334516 @default.
• W4224294196 cites W3202550138 @default.
• W4224294196 cites W3203003533 @default.
• W4224294196 cites W3203925315 @default.
• W4224294196 cites W3207918547 @default.
• W4224294196 cites W4207070640 @default.
• W4224294196 cites W4214508443 @default.
• W4224294196 cites W4214612132 @default.
• W4224294196 cites W4214624153 @default.
• W4224294196 cites W4214893857 @default.
• W4224294196 cites W4221160948 @default.
• W4224294196 cites W4242943569 @default.
• W4224294196 doi "https://doi.org/10.1109/cvprw56347.2022.00090" @default.
• W4224294196 hasPublicationYear "2022" @default.
• W4224294196 type Work @default.
• W4224294196 citedByCount "23" @default.
• W4224294196 countsByYear W42242941962022 @default.
• W4224294196 countsByYear W42242941962023 @default.
• W4224294196 crossrefType "proceedings-article" @default.
• W4224294196 hasAuthorship W4224294196A5001254143 @default.
• W4224294196 hasAuthorship W4224294196A5016580378 @default.
• W4224294196 hasAuthorship W4224294196A5022665877 @default.
• W4224294196 hasAuthorship W4224294196A5028229824 @default.
• W4224294196 hasAuthorship W4224294196A5038281038 @default.
• W4224294196 hasAuthorship W4224294196A5043151044 @default.
• W4224294196 hasAuthorship W4224294196A5052236177 @default.
• W4224294196 hasAuthorship W4224294196A5074865219 @default.
• W4224294196 hasBestOaLocation W42242941962 @default.
• W4224294196 hasConcept C121332964 @default.
• W4224294196 hasConcept C141379421 @default.
• W4224294196 hasConcept C153180895 @default.
• W4224294196 hasConcept C154945302 @default.
• W4224294196 hasConcept C159078339 @default.
• W4224294196 hasConcept C165801399 @default.
• W4224294196 hasConcept C41008148 @default.
• W4224294196 hasConcept C62520636 @default.
• W4224294196 hasConcept C66322947 @default.
• W4224294196 hasConcept C81363708 @default.
• W4224294196 hasConceptScore W4224294196C121332964 @default.
• W4224294196 hasConceptScore W4224294196C141379421 @default.
• W4224294196 hasConceptScore W4224294196C153180895 @default.
• W4224294196 hasConceptScore W4224294196C154945302 @default.
• W4224294196 hasConceptScore W4224294196C159078339 @default.

• next