Matches in SemOpenAlex for { <https://semopenalex.org/work/W2785243491> ?p ?o ?g. }
- W2785243491 abstract "Predicting attention is a popular topic at the intersection of human and computer vision, but video saliency prediction has only recently begun to benefit from deep learning-based approaches. Even though most of the available video-based saliency data sets and models claim to target human observers' fixations, they fail to differentiate them from smooth pursuit (SP), a major eye movement type that is unique to perception of dynamic scenes. In this work, we aim to make this distinction explicit, to which end we (i) use both algorithmic and manual annotations of SP traces and other eye movements for two well-established video saliency data sets, (ii) train Slicing Convolutional Neural Networks (S-CNN) for saliency prediction on either fixation- or SP-salient locations, and (iii) evaluate ours and over 20 popular published saliency models on the two annotated data sets for predicting both SP and fixations, as well as on another data set of human fixations. Our proposed model, trained on an independent set of videos, outperforms the state-of-the-art saliency models in the task of SP prediction on all considered data sets. Moreover, this model also demonstrates superior performance in the prediction of classical fixation-based saliency. Our results emphasize the importance of selectively approaching training set construction for attention modelling." @default.
- W2785243491 created "2018-02-02" @default.
- W2785243491 creator A5012216102 @default.
- W2785243491 creator A5041967088 @default.
- W2785243491 date "2018-01-26" @default.
- W2785243491 modified "2023-09-27" @default.
- W2785243491 title "Supersaliency: Predicting Smooth Pursuit-Based Attention with Slicing CNNs Improves Fixation Prediction for Naturalistic Videos" @default.
- W2785243491 cites W1497094965 @default.
- W2785243491 cites W1510835000 @default.
- W2785243491 cites W1517086206 @default.
- W2785243491 cites W1545595850 @default.
- W2785243491 cites W1686810756 @default.
- W2785243491 cites W1850164289 @default.
- W2785243491 cites W1959094031 @default.
- W2785243491 cites W1965301399 @default.
- W2785243491 cites W1967508848 @default.
- W2785243491 cites W1978479866 @default.
- W2785243491 cites W1983364832 @default.
- W2785243491 cites W1993254594 @default.
- W2785243491 cites W1995055145 @default.
- W2785243491 cites W2000617596 @default.
- W2785243491 cites W2013474298 @default.
- W2785243491 cites W2017245158 @default.
- W2785243491 cites W2020738756 @default.
- W2785243491 cites W2023592349 @default.
- W2785243491 cites W2032258487 @default.
- W2785243491 cites W2034436892 @default.
- W2785243491 cites W2040253108 @default.
- W2785243491 cites W2044176444 @default.
- W2785243491 cites W2055111849 @default.
- W2785243491 cites W2062197752 @default.
- W2785243491 cites W2071555787 @default.
- W2785243491 cites W2081239020 @default.
- W2785243491 cites W2095816583 @default.
- W2785243491 cites W2097295641 @default.
- W2785243491 cites W2098702446 @default.
- W2785243491 cites W2105370098 @default.
- W2785243491 cites W2105964837 @default.
- W2785243491 cites W2108007183 @default.
- W2785243491 cites W2113244983 @default.
- W2785243491 cites W2119577735 @default.
- W2785243491 cites W2120703069 @default.
- W2785243491 cites W2135571772 @default.
- W2785243491 cites W2135957164 @default.
- W2785243491 cites W2137197185 @default.
- W2785243491 cites W2150850720 @default.
- W2785243491 cites W2163292664 @default.
- W2785243491 cites W2164084182 @default.
- W2785243491 cites W2166206801 @default.
- W2785243491 cites W2176017127 @default.
- W2785243491 cites W2302130413 @default.
- W2785243491 cites W2313180542 @default.
- W2785243491 cites W2344129934 @default.
- W2785243491 cites W2345628569 @default.
- W2785243491 cites W2378845821 @default.
- W2785243491 cites W2436685139 @default.
- W2785243491 cites W2550617893 @default.
- W2785243491 cites W2566148191 @default.
- W2785243491 cites W2733081473 @default.
- W2785243491 cites W33363299 @default.
- W2785243491 cites W769398789 @default.
- W2785243491 hasPublicationYear "2018" @default.
- W2785243491 type Work @default.
- W2785243491 sameAs 2785243491 @default.
- W2785243491 citedByCount "0" @default.
- W2785243491 crossrefType "posted-content" @default.
- W2785243491 hasAuthorship W2785243491A5012216102 @default.
- W2785243491 hasAuthorship W2785243491A5041967088 @default.
- W2785243491 hasConcept C108583219 @default.
- W2785243491 hasConcept C119857082 @default.
- W2785243491 hasConcept C136764020 @default.
- W2785243491 hasConcept C144024400 @default.
- W2785243491 hasConcept C146249460 @default.
- W2785243491 hasConcept C149923435 @default.
- W2785243491 hasConcept C153050134 @default.
- W2785243491 hasConcept C153180895 @default.
- W2785243491 hasConcept C154945302 @default.
- W2785243491 hasConcept C169760540 @default.
- W2785243491 hasConcept C177264268 @default.
- W2785243491 hasConcept C199360897 @default.
- W2785243491 hasConcept C26760741 @default.
- W2785243491 hasConcept C2776190703 @default.
- W2785243491 hasConcept C2780719617 @default.
- W2785243491 hasConcept C2908647359 @default.
- W2785243491 hasConcept C2986089797 @default.
- W2785243491 hasConcept C41008148 @default.
- W2785243491 hasConcept C51632099 @default.
- W2785243491 hasConcept C66024118 @default.
- W2785243491 hasConcept C81363708 @default.
- W2785243491 hasConcept C86803240 @default.
- W2785243491 hasConceptScore W2785243491C108583219 @default.
- W2785243491 hasConceptScore W2785243491C119857082 @default.
- W2785243491 hasConceptScore W2785243491C136764020 @default.
- W2785243491 hasConceptScore W2785243491C144024400 @default.
- W2785243491 hasConceptScore W2785243491C146249460 @default.
- W2785243491 hasConceptScore W2785243491C149923435 @default.
- W2785243491 hasConceptScore W2785243491C153050134 @default.
- W2785243491 hasConceptScore W2785243491C153180895 @default.
- W2785243491 hasConceptScore W2785243491C154945302 @default.
- W2785243491 hasConceptScore W2785243491C169760540 @default.