Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385688009> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4385688009 abstract "Referring image segmentation aims to segment the target region from an image according to the query language description. One of the main challenges behind this fundamental task is to find a qualitative query representation to index the referred object or stuff. In this study, we introduced a query-based framework with Transformer architecture for referring image segmentation, dubbed SQFormer. It treats the sentence and word embeddings as components of two types of semantic queries: (i) mask queries conditioned on the sentence embeddings and (ii) word queries induced from text inputs, to directly attends to the most relevant areas in the image. The semantic queries are input-specific to diverse language expressions while maintaining the prior knowledge of intrinsic image patterns. Concretely, word queries enable flexible and adaptive interactions between vision-language modalities. Mask queries are obligated to generate a set of prototype masks. Then in Prototype Mask Balance (PMB) module, the prototype masks are weighted sum according to the holistic understanding of language expression to get the final mask prediction. Besides, to better fuse linguistic and visual features, we propose a language-aware feature pyramid network (LA-FPN) to enhance the cross-modal alignment. Extensive experiments show our method surpasses the previous state-of-the-art approaches on RefCOCO, RefCOCO+, and G-Ref datasets." @default.
- W4385688009 created "2023-08-10" @default.
- W4385688009 creator A5078710220 @default.
- W4385688009 date "2023-06-16" @default.
- W4385688009 modified "2023-09-27" @default.
- W4385688009 title "Semantic Queries with Transformer for Referring Image Segmentation" @default.
- W4385688009 cites W1903029394 @default.
- W4385688009 cites W2565639579 @default.
- W4385688009 cites W2963109634 @default.
- W4385688009 cites W2963145877 @default.
- W4385688009 cites W2980088508 @default.
- W4385688009 cites W2993182889 @default.
- W4385688009 cites W3138516171 @default.
- W4385688009 doi "https://doi.org/10.1145/3605801.3605832" @default.
- W4385688009 hasPublicationYear "2023" @default.
- W4385688009 type Work @default.
- W4385688009 citedByCount "0" @default.
- W4385688009 crossrefType "proceedings-article" @default.
- W4385688009 hasAuthorship W4385688009A5078710220 @default.
- W4385688009 hasConcept C121332964 @default.
- W4385688009 hasConcept C154945302 @default.
- W4385688009 hasConcept C165801399 @default.
- W4385688009 hasConcept C204321447 @default.
- W4385688009 hasConcept C23123220 @default.
- W4385688009 hasConcept C2777530160 @default.
- W4385688009 hasConcept C41008148 @default.
- W4385688009 hasConcept C62520636 @default.
- W4385688009 hasConcept C66322947 @default.
- W4385688009 hasConcept C89600930 @default.
- W4385688009 hasConceptScore W4385688009C121332964 @default.
- W4385688009 hasConceptScore W4385688009C154945302 @default.
- W4385688009 hasConceptScore W4385688009C165801399 @default.
- W4385688009 hasConceptScore W4385688009C204321447 @default.
- W4385688009 hasConceptScore W4385688009C23123220 @default.
- W4385688009 hasConceptScore W4385688009C2777530160 @default.
- W4385688009 hasConceptScore W4385688009C41008148 @default.
- W4385688009 hasConceptScore W4385688009C62520636 @default.
- W4385688009 hasConceptScore W4385688009C66322947 @default.
- W4385688009 hasConceptScore W4385688009C89600930 @default.
- W4385688009 hasLocation W43856880091 @default.
- W4385688009 hasOpenAccess W4385688009 @default.
- W4385688009 hasPrimaryLocation W43856880091 @default.
- W4385688009 hasRelatedWork W159132833 @default.
- W4385688009 hasRelatedWork W2035950535 @default.
- W4385688009 hasRelatedWork W2086064646 @default.
- W4385688009 hasRelatedWork W2351555819 @default.
- W4385688009 hasRelatedWork W2357241418 @default.
- W4385688009 hasRelatedWork W2789919619 @default.
- W4385688009 hasRelatedWork W4283585122 @default.
- W4385688009 hasRelatedWork W4318978824 @default.
- W4385688009 hasRelatedWork W4385873483 @default.
- W4385688009 hasRelatedWork W4385877744 @default.
- W4385688009 isParatext "false" @default.
- W4385688009 isRetracted "false" @default.
- W4385688009 workType "article" @default.