Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312468404> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4312468404 abstract "Despite the great success of attention mechanisms on object recognition, scene recognition remains a challenging problem. The reason is that discriminative regions are not evident in a scene image. For example, a tree in an image can be a cue to recognize a scene, but the tree cannot be the only cue for recognizing the scene. That means several scene categories (e.g. mountain, marsh, and river) can contain a tree. Thus sometimes, overall regions, rather than specific regions, need to be considered for scene recognition. To solve the problem, we propose Spatial-Channel Transformer (SC-Transformer). The SC-Transformer is a simple yet effective module that uses a new attention mechanism by incorporating the importance between the spatial and the channel domain for a given scene image. If the given scene image should be considered only within some specific regions, SC-Transformer turns off the channel attention, and vice versa. Furthermore, the attention mechanism used in our proposed method is advanced from previous approaches. Previous spatial and channel attention mechanisms were designed in a sequential or parallel manner. These mechanisms eventually combine spatial and channel attention together, so spatial and channel attention may often interfere with each other. In contrast to the previous works, we present a new mechanism that simultaneously considers spatial and channel attentions. We validate our approach on a large-scale scene recognition dataset and outperform the previous state-of-the-art spatial-channel attention mechanism. Experimental results demonstrate the efficacy of our attention mechanism for scene recognition." @default.
- W4312468404 created "2023-01-04" @default.
- W4312468404 creator A5014132188 @default.
- W4312468404 creator A5028558267 @default.
- W4312468404 creator A5065415014 @default.
- W4312468404 creator A5076340349 @default.
- W4312468404 date "2022-07-18" @default.
- W4312468404 modified "2023-09-23" @default.
- W4312468404 title "Spatial-Channel Transformer for Scene Recognition" @default.
- W4312468404 cites W2070792803 @default.
- W4312468404 cites W2099528205 @default.
- W4312468404 cites W2194775991 @default.
- W4312468404 cites W2752782242 @default.
- W4312468404 cites W2755125693 @default.
- W4312468404 cites W2809273606 @default.
- W4312468404 cites W2903082930 @default.
- W4312468404 cites W2974118232 @default.
- W4312468404 cites W2978803196 @default.
- W4312468404 cites W2992734365 @default.
- W4312468404 cites W3005999698 @default.
- W4312468404 cites W3019917704 @default.
- W4312468404 cites W3101522362 @default.
- W4312468404 cites W3104752576 @default.
- W4312468404 cites W315880484 @default.
- W4312468404 cites W4289388289 @default.
- W4312468404 doi "https://doi.org/10.1109/ijcnn55064.2022.9891998" @default.
- W4312468404 hasPublicationYear "2022" @default.
- W4312468404 type Work @default.
- W4312468404 citedByCount "1" @default.
- W4312468404 countsByYear W43124684042023 @default.
- W4312468404 crossrefType "proceedings-article" @default.
- W4312468404 hasAuthorship W4312468404A5014132188 @default.
- W4312468404 hasAuthorship W4312468404A5028558267 @default.
- W4312468404 hasAuthorship W4312468404A5065415014 @default.
- W4312468404 hasAuthorship W4312468404A5076340349 @default.
- W4312468404 hasConcept C119599485 @default.
- W4312468404 hasConcept C127162648 @default.
- W4312468404 hasConcept C127413603 @default.
- W4312468404 hasConcept C153180895 @default.
- W4312468404 hasConcept C154945302 @default.
- W4312468404 hasConcept C165801399 @default.
- W4312468404 hasConcept C31258907 @default.
- W4312468404 hasConcept C31972630 @default.
- W4312468404 hasConcept C41008148 @default.
- W4312468404 hasConcept C66322947 @default.
- W4312468404 hasConcept C97931131 @default.
- W4312468404 hasConceptScore W4312468404C119599485 @default.
- W4312468404 hasConceptScore W4312468404C127162648 @default.
- W4312468404 hasConceptScore W4312468404C127413603 @default.
- W4312468404 hasConceptScore W4312468404C153180895 @default.
- W4312468404 hasConceptScore W4312468404C154945302 @default.
- W4312468404 hasConceptScore W4312468404C165801399 @default.
- W4312468404 hasConceptScore W4312468404C31258907 @default.
- W4312468404 hasConceptScore W4312468404C31972630 @default.
- W4312468404 hasConceptScore W4312468404C41008148 @default.
- W4312468404 hasConceptScore W4312468404C66322947 @default.
- W4312468404 hasConceptScore W4312468404C97931131 @default.
- W4312468404 hasFunder F4320322091 @default.
- W4312468404 hasLocation W43124684041 @default.
- W4312468404 hasOpenAccess W4312468404 @default.
- W4312468404 hasPrimaryLocation W43124684041 @default.
- W4312468404 hasRelatedWork W1652783584 @default.
- W4312468404 hasRelatedWork W1990254706 @default.
- W4312468404 hasRelatedWork W2024160000 @default.
- W4312468404 hasRelatedWork W2285052147 @default.
- W4312468404 hasRelatedWork W2404514746 @default.
- W4312468404 hasRelatedWork W2729514902 @default.
- W4312468404 hasRelatedWork W2743258233 @default.
- W4312468404 hasRelatedWork W2773500201 @default.
- W4312468404 hasRelatedWork W4287995534 @default.
- W4312468404 hasRelatedWork W2073139667 @default.
- W4312468404 isParatext "false" @default.
- W4312468404 isRetracted "false" @default.
- W4312468404 workType "article" @default.