Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048835936> ?p ?o ?g. }
- W3048835936 abstract "n recent years, text-guided image manipulation has gained increasing attention in the multimedia and computer vision community. The input to conditional image generation has evolved from image-only to multimodality. In this paper, we study a setting that allows users to edit an image with multiple objects using complex text instructions to add, remove, or change the objects. The inputs of the task are multimodal including (1) a reference image and (2) an instruction in natural language that describes desired modifications to the image. We propose a GAN-based method to tackle this problem. The key idea is to treat text as neural operators to locally modify the image feature. We show that the proposed model performs favorably against recent strong baselines on three public datasets. Specifically, it generates images of greater fidelity and semantic relevance, and when used as a image query, leads to better retrieval performance." @default.
- W3048835936 created "2020-08-18" @default.
- W3048835936 creator A5034291270 @default.
- W3048835936 creator A5044127793 @default.
- W3048835936 creator A5064419280 @default.
- W3048835936 creator A5070348998 @default.
- W3048835936 creator A5090586839 @default.
- W3048835936 creator A5090730336 @default.
- W3048835936 date "2021-10-17" @default.
- W3048835936 modified "2023-09-26" @default.
- W3048835936 title "Text as Neural Operator:Image Manipulation by Text Instruction" @default.
- W3048835936 cites W1996418862 @default.
- W3048835936 cites W2010223195 @default.
- W3048835936 cites W2194775991 @default.
- W3048835936 cites W2572730214 @default.
- W3048835936 cites W2593414223 @default.
- W3048835936 cites W2603777577 @default.
- W3048835936 cites W2612063021 @default.
- W3048835936 cites W2798600195 @default.
- W3048835936 cites W2894754680 @default.
- W3048835936 cites W2905544595 @default.
- W3048835936 cites W2952056941 @default.
- W3048835936 cites W2953016680 @default.
- W3048835936 cites W2962716332 @default.
- W3048835936 cites W2962793481 @default.
- W3048835936 cites W2962927829 @default.
- W3048835936 cites W2962974533 @default.
- W3048835936 cites W2963047368 @default.
- W3048835936 cites W2963163163 @default.
- W3048835936 cites W2963184176 @default.
- W3048835936 cites W2963402808 @default.
- W3048835936 cites W2963683323 @default.
- W3048835936 cites W2963800363 @default.
- W3048835936 cites W2963890275 @default.
- W3048835936 cites W2963966654 @default.
- W3048835936 cites W2964082983 @default.
- W3048835936 cites W2964138017 @default.
- W3048835936 cites W2964338366 @default.
- W3048835936 cites W2965289598 @default.
- W3048835936 cites W2966792645 @default.
- W3048835936 cites W2978052557 @default.
- W3048835936 cites W2981464166 @default.
- W3048835936 cites W2981824749 @default.
- W3048835936 cites W2982014123 @default.
- W3048835936 cites W2982260486 @default.
- W3048835936 cites W2984854289 @default.
- W3048835936 cites W3008653537 @default.
- W3048835936 cites W3026458074 @default.
- W3048835936 cites W3029165865 @default.
- W3048835936 cites W3092775865 @default.
- W3048835936 cites W3092906216 @default.
- W3048835936 cites W3093122931 @default.
- W3048835936 cites W3094715874 @default.
- W3048835936 cites W3095707326 @default.
- W3048835936 cites W3108984808 @default.
- W3048835936 cites W3115686843 @default.
- W3048835936 cites W3171615848 @default.
- W3048835936 cites W4238155858 @default.
- W3048835936 cites W4288079578 @default.
- W3048835936 doi "https://doi.org/10.1145/3474085.3475343" @default.
- W3048835936 hasPublicationYear "2021" @default.
- W3048835936 type Work @default.
- W3048835936 sameAs 3048835936 @default.
- W3048835936 citedByCount "9" @default.
- W3048835936 countsByYear W30488359362021 @default.
- W3048835936 countsByYear W30488359362022 @default.
- W3048835936 countsByYear W30488359362023 @default.
- W3048835936 crossrefType "proceedings-article" @default.
- W3048835936 hasAuthorship W3048835936A5034291270 @default.
- W3048835936 hasAuthorship W3048835936A5044127793 @default.
- W3048835936 hasAuthorship W3048835936A5064419280 @default.
- W3048835936 hasAuthorship W3048835936A5070348998 @default.
- W3048835936 hasAuthorship W3048835936A5090586839 @default.
- W3048835936 hasAuthorship W3048835936A5090730336 @default.
- W3048835936 hasBestOaLocation W30488359361 @default.
- W3048835936 hasConcept C104317684 @default.
- W3048835936 hasConcept C115961682 @default.
- W3048835936 hasConcept C138885662 @default.
- W3048835936 hasConcept C154945302 @default.
- W3048835936 hasConcept C158154518 @default.
- W3048835936 hasConcept C158448853 @default.
- W3048835936 hasConcept C162324750 @default.
- W3048835936 hasConcept C1667742 @default.
- W3048835936 hasConcept C17020691 @default.
- W3048835936 hasConcept C17744445 @default.
- W3048835936 hasConcept C184337299 @default.
- W3048835936 hasConcept C185592680 @default.
- W3048835936 hasConcept C187736073 @default.
- W3048835936 hasConcept C199360897 @default.
- W3048835936 hasConcept C199539241 @default.
- W3048835936 hasConcept C199579030 @default.
- W3048835936 hasConcept C23123220 @default.
- W3048835936 hasConcept C26517878 @default.
- W3048835936 hasConcept C2776401178 @default.
- W3048835936 hasConcept C2776459999 @default.
- W3048835936 hasConcept C2776674983 @default.
- W3048835936 hasConcept C2779532271 @default.
- W3048835936 hasConcept C2780451532 @default.
- W3048835936 hasConcept C31972630 @default.
- W3048835936 hasConcept C38652104 @default.