FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3109173618> ?p ?o ?g. }

• W3109173618 abstract "Thanks to large-scale labeled training data, deep neural networks (DNNs) have obtained remarkable success in many vision and multimedia tasks. However, because of the presence of domain shift, the learned knowledge of the well-trained DNNs cannot be well generalized to new domains or datasets that have few labels. Unsupervised domain adaptation (UDA) studies the problem of transferring models trained on one labeled source domain to another unlabeled target domain. In this paper, we focus on UDA in visual emotion analysis for both emotion distribution learning and dominant emotion classification. Specifically, we design a novel end-to-end cycle-consistent adversarial model, termed CycleEmotionGAN++. First, we generate an adapted domain to align the source and target domains on the pixel-level by improving CycleGAN with a multi-scale structured cycle-consistency loss. During the image translation, we propose a dynamic emotional semantic consistency loss to preserve the emotion labels of the source images. Second, we train a transferable task classifier on the adapted domain with feature-level alignment between the adapted and target domains. We conduct extensive UDA experiments on the Flickr-LDL & Twitter-LDL datasets for distribution learning and ArtPhoto & FI datasets for emotion classification. The results demonstrate the significant improvements yielded by the proposed CycleEmotionGAN++ as compared to state-of-the-art UDA approaches." @default.
• W3109173618 created "2020-12-07" @default.
• W3109173618 creator A5000680423 @default.
• W3109173618 creator A5018488422 @default.
• W3109173618 creator A5040673752 @default.
• W3109173618 creator A5047285420 @default.
• W3109173618 creator A5051149140 @default.
• W3109173618 creator A5057732142 @default.
• W3109173618 creator A5078143614 @default.
• W3109173618 creator A5078165161 @default.
• W3109173618 creator A5088660554 @default.
• W3109173618 creator A5089409678 @default.
• W3109173618 date "2020-11-24" @default.
• W3109173618 modified "2023-09-23" @default.
• W3109173618 title "Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation" @default.
• W3109173618 cites W1580389772 @default.
• W3109173618 cites W1722318740 @default.
• W3109173618 cites W1920280450 @default.
• W3109173618 cites W1920962657 @default.
• W3109173618 cites W1950412479 @default.
• W3109173618 cites W1981424477 @default.
• W3109173618 cites W1982696459 @default.
• W3109173618 cites W2003856922 @default.
• W3109173618 cites W2004236981 @default.
• W3109173618 cites W2031342017 @default.
• W3109173618 cites W2039940482 @default.
• W3109173618 cites W2046682605 @default.
• W3109173618 cites W2065632025 @default.
• W3109173618 cites W2074356411 @default.
• W3109173618 cites W2075456404 @default.
• W3109173618 cites W2085940040 @default.
• W3109173618 cites W2086399953 @default.
• W3109173618 cites W2099471712 @default.
• W3109173618 cites W2104068492 @default.
• W3109173618 cites W2112483442 @default.
• W3109173618 cites W2129112648 @default.
• W3109173618 cites W2149466042 @default.
• W3109173618 cites W2158815628 @default.
• W3109173618 cites W2159291411 @default.
• W3109173618 cites W2194775991 @default.
• W3109173618 cites W2339754110 @default.
• W3109173618 cites W2347880541 @default.
• W3109173618 cites W2478454054 @default.
• W3109173618 cites W2525668096 @default.
• W3109173618 cites W2531468424 @default.
• W3109173618 cites W2552066052 @default.
• W3109173618 cites W2552972371 @default.
• W3109173618 cites W2562637781 @default.
• W3109173618 cites W2584886900 @default.
• W3109173618 cites W2593414223 @default.
• W3109173618 cites W2593768305 @default.
• W3109173618 cites W2604737966 @default.
• W3109173618 cites W2604773025 @default.
• W3109173618 cites W2740046088 @default.
• W3109173618 cites W2741561025 @default.
• W3109173618 cites W2741630455 @default.
• W3109173618 cites W2765354427 @default.
• W3109173618 cites W2766251611 @default.
• W3109173618 cites W2767179670 @default.
• W3109173618 cites W2770912167 @default.
• W3109173618 cites W2790763247 @default.
• W3109173618 cites W2793784464 @default.
• W3109173618 cites W2795155917 @default.
• W3109173618 cites W2798503473 @default.
• W3109173618 cites W2805597187 @default.
• W3109173618 cites W2896591327 @default.
• W3109173618 cites W2904451048 @default.
• W3109173618 cites W2958360136 @default.
• W3109173618 cites W2962793481 @default.
• W3109173618 cites W2962808524 @default.
• W3109173618 cites W2963107255 @default.
• W3109173618 cites W2963120918 @default.
• W3109173618 cites W2963532621 @default.
• W3109173618 cites W2963709863 @default.
• W3109173618 cites W2963784072 @default.
• W3109173618 cites W2963992782 @default.
• W3109173618 cites W2964126011 @default.
• W3109173618 cites W2968557240 @default.
• W3109173618 cites W2974550657 @default.
• W3109173618 cites W2975758481 @default.
• W3109173618 cites W2981540341 @default.
• W3109173618 cites W2982259084 @default.
• W3109173618 cites W3012910746 @default.
• W3109173618 cites W3013868783 @default.
• W3109173618 cites W3034685081 @default.
• W3109173618 cites W3035231706 @default.
• W3109173618 cites W3094277917 @default.
• W3109173618 cites W3098061148 @default.
• W3109173618 cites W2097263426 @default.
• W3109173618 doi "https://doi.org/10.48550/arxiv.2011.12470" @default.
• W3109173618 hasPublicationYear "2020" @default.
• W3109173618 type Work @default.
• W3109173618 sameAs 3109173618 @default.
• W3109173618 citedByCount "0" @default.
• W3109173618 crossrefType "posted-content" @default.
• W3109173618 hasAuthorship W3109173618A5000680423 @default.
• W3109173618 hasAuthorship W3109173618A5018488422 @default.
• W3109173618 hasAuthorship W3109173618A5040673752 @default.
• W3109173618 hasAuthorship W3109173618A5047285420 @default.
• W3109173618 hasAuthorship W3109173618A5051149140 @default.

• next