FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328008203> ?p ?o ?g. }

• W4328008203 endingPage "5801" @default.
• W4328008203 startingPage "5790" @default.
• W4328008203 abstract "Over the past few years, gaze prediction technology has rapidly developed in human visual attention mechanism research. However, there is still a large gap between the prediction models and the human visual system (HVS). This work makes four contributions to video egocentric gaze prediction research. First, we introduce a new benchmark named ECVG (egocentric video gaze), which consists of 3K high-quality, elaborately selected video sequences spanning a large range of scenes. Existing eye-tracking datasets limit human activities. In contrast, ECVG achieves the collection of eye movement data under real human activity. Second, we establish a visual attention-selection and gaze-tracking model, which summarizes the human visual attention process. Third, we propose a novel feature pyramid interactive attention 3D network (FPIANet) for egocentric gaze prediction, which directly captures the long-term relationship between spatiotemporal features at different time steps and achieves feature nonlocal interactions across temporal, spatial, and scales. In addition, we propose a multiscale interactive attention (MSIA) module, which first explicitly integrates the human top-down and bottom-up visual attention mechanisms to transform any spatiotemporal feature into another feature of the same size but with richer contexts. Furthermore, we propose a new gaze transfer path consistency evaluation and thoroughly examine the performance of our model on two large datasets (ECVG and LEDOV). The experimental results show that our model outperforms the existing state-of-the-art methods." @default.
• W4328008203 created "2023-03-22" @default.
• W4328008203 creator A5017450107 @default.
• W4328008203 creator A5086765632 @default.
• W4328008203 date "2023-10-01" @default.
• W4328008203 modified "2023-10-06" @default.
• W4328008203 title "Spatio-Temporal Feature Pyramid Interactive Attention Network for Egocentric Gaze Prediction" @default.
• W4328008203 cites W1510835000 @default.
• W4328008203 cites W1934890906 @default.
• W4328008203 cites W1971022913 @default.
• W4328008203 cites W2037328649 @default.
• W4328008203 cites W2071555787 @default.
• W4328008203 cites W2078903912 @default.
• W4328008203 cites W2098702446 @default.
• W4328008203 cites W2102148524 @default.
• W4328008203 cites W2112845172 @default.
• W4328008203 cites W2114873786 @default.
• W4328008203 cites W2119577735 @default.
• W4328008203 cites W2128272608 @default.
• W4328008203 cites W2133589685 @default.
• W4328008203 cites W2136668269 @default.
• W4328008203 cites W2145725161 @default.
• W4328008203 cites W2146103513 @default.
• W4328008203 cites W2148383759 @default.
• W4328008203 cites W2160754664 @default.
• W4328008203 cites W2162216530 @default.
• W4328008203 cites W2163292664 @default.
• W4328008203 cites W2163588226 @default.
• W4328008203 cites W2164084182 @default.
• W4328008203 cites W2212216676 @default.
• W4328008203 cites W2212494831 @default.
• W4328008203 cites W2288514685 @default.
• W4328008203 cites W2550553598 @default.
• W4328008203 cites W2585592883 @default.
• W4328008203 cites W2791303549 @default.
• W4328008203 cites W2792312609 @default.
• W4328008203 cites W2793668851 @default.
• W4328008203 cites W2795307598 @default.
• W4328008203 cites W2804743778 @default.
• W4328008203 cites W2807663718 @default.
• W4328008203 cites W2883429621 @default.
• W4328008203 cites W2891726870 @default.
• W4328008203 cites W2921653116 @default.
• W4328008203 cites W2962762462 @default.
• W4328008203 cites W2962965915 @default.
• W4328008203 cites W2963091558 @default.
• W4328008203 cites W2963503775 @default.
• W4328008203 cites W2963524571 @default.
• W4328008203 cites W2963581854 @default.
• W4328008203 cites W2964114039 @default.
• W4328008203 cites W2965638232 @default.
• W4328008203 cites W2969741484 @default.
• W4328008203 cites W2980565715 @default.
• W4328008203 cites W2981165461 @default.
• W4328008203 cites W2986131415 @default.
• W4328008203 cites W2997304642 @default.
• W4328008203 cites W2999458807 @default.
• W4328008203 cites W3022565501 @default.
• W4328008203 cites W3043142510 @default.
• W4328008203 cites W3082940248 @default.
• W4328008203 cites W3099561715 @default.
• W4328008203 cites W3101840568 @default.
• W4328008203 cites W3102582269 @default.
• W4328008203 cites W3122238731 @default.
• W4328008203 cites W3125703990 @default.
• W4328008203 cites W3138095408 @default.
• W4328008203 cites W3190399926 @default.
• W4328008203 cites W3202477427 @default.
• W4328008203 cites W4214612132 @default.
• W4328008203 cites W4221078550 @default.
• W4328008203 cites W4226051135 @default.
• W4328008203 cites W4226056010 @default.
• W4328008203 cites W4285176798 @default.
• W4328008203 doi "https://doi.org/10.1109/tcsvt.2023.3258962" @default.
• W4328008203 hasPublicationYear "2023" @default.
• W4328008203 type Work @default.
• W4328008203 citedByCount "0" @default.
• W4328008203 crossrefType "journal-article" @default.
• W4328008203 hasAuthorship W4328008203A5017450107 @default.
• W4328008203 hasAuthorship W4328008203A5086765632 @default.
• W4328008203 hasConcept C111919701 @default.
• W4328008203 hasConcept C115961682 @default.
• W4328008203 hasConcept C120665830 @default.
• W4328008203 hasConcept C121332964 @default.
• W4328008203 hasConcept C13280743 @default.
• W4328008203 hasConcept C138885662 @default.
• W4328008203 hasConcept C142575187 @default.
• W4328008203 hasConcept C154945302 @default.
• W4328008203 hasConcept C160086991 @default.
• W4328008203 hasConcept C185798385 @default.
• W4328008203 hasConcept C205649164 @default.
• W4328008203 hasConcept C2776401178 @default.
• W4328008203 hasConcept C2779916870 @default.
• W4328008203 hasConcept C31972630 @default.
• W4328008203 hasConcept C36464697 @default.
• W4328008203 hasConcept C41008148 @default.
• W4328008203 hasConcept C41895202 @default.
• W4328008203 hasConcept C56461940 @default.

• next