Matches in SemOpenAlex for { <https://semopenalex.org/work/W3126683704> ?p ?o ?g. }
- W3126683704 abstract "Saliency detection based on the complementary information from RGB images and depth maps has recently gained great popularity. In this paper, we propose Complementary Attention and Adaptive Integration Network (CAAI-Net), a novel RGB-D saliency detection model that integrates complementary attention based feature concentration and adaptive cross-modal feature fusion into a unified framework for accurate saliency detection. Specifically, we propose a context-aware complementary attention (CCA) module, which consists of a feature interaction component, a complementary attention component, and a global-context component. The CCA module first utilizes the feature interaction component to extract rich local context features. The resulting features are then fed into the complementary attention component, which employs the complementary attention generated from adjacent levels to guide the attention at the current layer so that the mutual background disturbances are suppressed and the network focuses more on the areas with salient objects. Finally, we utilize a specially-designed adaptive feature integration (AFI) module, which sufficiently considers the low-quality issue of depth maps, to aggregate the RGB and depth features in an adaptive manner. Extensive experiments on six challenging benchmark datasets demonstrate that CAAI-Net is an effective saliency detection model and outperforms nine state-of-the-art models in terms of four widely-used metrics. In addition, extensive ablation studies confirm the effectiveness of the proposed CCA and AFI modules." @default.
- W3126683704 created "2021-02-15" @default.
- W3126683704 creator A5013301642 @default.
- W3126683704 creator A5018404473 @default.
- W3126683704 creator A5039679140 @default.
- W3126683704 creator A5047423420 @default.
- W3126683704 creator A5056500637 @default.
- W3126683704 creator A5081513423 @default.
- W3126683704 date "2021-02-08" @default.
- W3126683704 modified "2023-09-25" @default.
- W3126683704 title "Towards Accurate RGB-D Saliency Detection with Complementary Attention and Adaptive Integration" @default.
- W3126683704 cites W1849277567 @default.
- W3126683704 cites W1894057436 @default.
- W3126683704 cites W1966025376 @default.
- W3126683704 cites W1976409045 @default.
- W3126683704 cites W1993713494 @default.
- W3126683704 cites W2037954058 @default.
- W3126683704 cites W2038913936 @default.
- W3126683704 cites W2039313011 @default.
- W3126683704 cites W2057220024 @default.
- W3126683704 cites W2068078373 @default.
- W3126683704 cites W20683899 @default.
- W3126683704 cites W2110019070 @default.
- W3126683704 cites W2110158442 @default.
- W3126683704 cites W2161185676 @default.
- W3126683704 cites W2514658199 @default.
- W3126683704 cites W2528092473 @default.
- W3126683704 cites W2567978322 @default.
- W3126683704 cites W2585592883 @default.
- W3126683704 cites W2588503511 @default.
- W3126683704 cites W2741745116 @default.
- W3126683704 cites W2757028014 @default.
- W3126683704 cites W2768270796 @default.
- W3126683704 cites W2884555738 @default.
- W3126683704 cites W2887522866 @default.
- W3126683704 cites W2907643346 @default.
- W3126683704 cites W2909381593 @default.
- W3126683704 cites W2921653116 @default.
- W3126683704 cites W2938260698 @default.
- W3126683704 cites W2944209449 @default.
- W3126683704 cites W2944241532 @default.
- W3126683704 cites W2948300571 @default.
- W3126683704 cites W2948500402 @default.
- W3126683704 cites W2955058313 @default.
- W3126683704 cites W2957408986 @default.
- W3126683704 cites W2962159375 @default.
- W3126683704 cites W2962965915 @default.
- W3126683704 cites W2963032190 @default.
- W3126683704 cites W2963529609 @default.
- W3126683704 cites W2963706010 @default.
- W3126683704 cites W2963868681 @default.
- W3126683704 cites W2969626490 @default.
- W3126683704 cites W2975589893 @default.
- W3126683704 cites W2986825110 @default.
- W3126683704 cites W2996699350 @default.
- W3126683704 cites W2997316506 @default.
- W3126683704 cites W2999281281 @default.
- W3126683704 cites W3002301267 @default.
- W3126683704 cites W3003251337 @default.
- W3126683704 cites W3003376220 @default.
- W3126683704 cites W3004661479 @default.
- W3126683704 cites W3005084867 @default.
- W3126683704 cites W3006465601 @default.
- W3126683704 cites W3010616503 @default.
- W3126683704 cites W3016719260 @default.
- W3126683704 cites W3019728440 @default.
- W3126683704 cites W3021941048 @default.
- W3126683704 cites W3027763298 @default.
- W3126683704 cites W3034609900 @default.
- W3126683704 cites W3034692043 @default.
- W3126683704 cites W3035284915 @default.
- W3126683704 cites W3035584216 @default.
- W3126683704 cites W3035633116 @default.
- W3126683704 cites W3080122069 @default.
- W3126683704 cites W3080684679 @default.
- W3126683704 cites W3098389804 @default.
- W3126683704 cites W3104979525 @default.
- W3126683704 cites W3118710621 @default.
- W3126683704 cites W3120113457 @default.
- W3126683704 cites W3122238731 @default.
- W3126683704 cites W2167363007 @default.
- W3126683704 doi "https://doi.org/10.48550/arxiv.2102.04046" @default.
- W3126683704 hasPublicationYear "2021" @default.
- W3126683704 type Work @default.
- W3126683704 sameAs 3126683704 @default.
- W3126683704 citedByCount "0" @default.
- W3126683704 crossrefType "posted-content" @default.
- W3126683704 hasAuthorship W3126683704A5013301642 @default.
- W3126683704 hasAuthorship W3126683704A5018404473 @default.
- W3126683704 hasAuthorship W3126683704A5039679140 @default.
- W3126683704 hasAuthorship W3126683704A5047423420 @default.
- W3126683704 hasAuthorship W3126683704A5056500637 @default.
- W3126683704 hasAuthorship W3126683704A5081513423 @default.
- W3126683704 hasBestOaLocation W31266837041 @default.
- W3126683704 hasConcept C121332964 @default.
- W3126683704 hasConcept C13280743 @default.
- W3126683704 hasConcept C138885662 @default.
- W3126683704 hasConcept C151730666 @default.
- W3126683704 hasConcept C153180895 @default.
- W3126683704 hasConcept C154945302 @default.