FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311165408> ?p ?o ?g. }

• W4311165408 endingPage "24354" @default.
• W4311165408 startingPage "24343" @default.
• W4311165408 abstract "Driver attention modeling is a crucial technique in building human-centric intelligent driving systems. Considering the human visual mechanism, this study leverages multi-level visual content, including low-level texture features, middle-level optical flows, and high-level semantic information, as the model input. Subsequently, a heterogeneous model is proposed to handle the multi-level input, which integrates the graph and convolutional neural networks. Distinguished from the existing studies that use semantic segmentation, our study directly leverages the objection detection information in an interpretable manner. To deal with the detected objects, in this work, a graph attention network is used to explicitly construct the semantic information, rather than handle the features extracted by convolutional modules for building the latent space features, which are used in existing studies. Further, a semantic attention module is proposed to integrate the non-Euclidean output of the graph network with the Euclidean feature maps of the convolutional neural networks. Finally, these integrated features are decoded to generate a driver attention map. Three typical datasets are used to validate the proposed method. A comprehensive comparison and analysis have proven the feasibility and validity of our proposed method, as well as its ability to achieve state-of-the-art performance." @default.
• W4311165408 created "2022-12-24" @default.
• W4311165408 creator A5026433926 @default.
• W4311165408 creator A5034663296 @default.
• W4311165408 creator A5038147203 @default.
• W4311165408 creator A5072073374 @default.
• W4311165408 date "2022-12-01" @default.
• W4311165408 modified "2023-10-16" @default.
• W4311165408 title "A Novel Heterogeneous Network for Modeling Driver Attention With Multi-Level Visual Content" @default.
• W4311165408 cites W1755205674 @default.
• W4311165408 cites W1934890906 @default.
• W4311165408 cites W2110019070 @default.
• W4311165408 cites W2116341502 @default.
• W4311165408 cites W2164084182 @default.
• W4311165408 cites W2605793178 @default.
• W4311165408 cites W2773064291 @default.
• W4311165408 cites W2793668851 @default.
• W4311165408 cites W2902418641 @default.
• W4311165408 cites W2903398871 @default.
• W4311165408 cites W2906722791 @default.
• W4311165408 cites W2909381593 @default.
• W4311165408 cites W2922458387 @default.
• W4311165408 cites W2934625602 @default.
• W4311165408 cites W2947918549 @default.
• W4311165408 cites W2955060956 @default.
• W4311165408 cites W2962608326 @default.
• W4311165408 cites W2963503775 @default.
• W4311165408 cites W2963513865 @default.
• W4311165408 cites W2963525576 @default.
• W4311165408 cites W2963828885 @default.
• W4311165408 cites W2969316698 @default.
• W4311165408 cites W2994984409 @default.
• W4311165408 cites W3000513982 @default.
• W4311165408 cites W3004380600 @default.
• W4311165408 cites W3007552921 @default.
• W4311165408 cites W3007724338 @default.
• W4311165408 cites W3009130550 @default.
• W4311165408 cites W3011872542 @default.
• W4311165408 cites W3016097197 @default.
• W4311165408 cites W3021656412 @default.
• W4311165408 cites W3025659338 @default.
• W4311165408 cites W3033681523 @default.
• W4311165408 cites W3034406258 @default.
• W4311165408 cites W3035564946 @default.
• W4311165408 cites W3040102868 @default.
• W4311165408 cites W3089943722 @default.
• W4311165408 cites W3100100339 @default.
• W4311165408 cites W3101840568 @default.
• W4311165408 cites W3107323529 @default.
• W4311165408 cites W3118519864 @default.
• W4311165408 cites W3122238731 @default.
• W4311165408 cites W3124849147 @default.
• W4311165408 cites W3126721752 @default.
• W4311165408 cites W3127334354 @default.
• W4311165408 cites W3128326875 @default.
• W4311165408 cites W3128389553 @default.
• W4311165408 cites W3151175129 @default.
• W4311165408 cites W3156346125 @default.
• W4311165408 cites W3157039246 @default.
• W4311165408 cites W3157914904 @default.
• W4311165408 cites W3165383086 @default.
• W4311165408 cites W3173398710 @default.
• W4311165408 cites W3184494646 @default.
• W4311165408 cites W3194349799 @default.
• W4311165408 cites W3208271024 @default.
• W4311165408 cites W3210240180 @default.
• W4311165408 cites W4210740016 @default.
• W4311165408 cites W4224115135 @default.
• W4311165408 cites W4225467065 @default.
• W4311165408 cites W4226379029 @default.
• W4311165408 cites W4285290430 @default.
• W4311165408 cites W4286253093 @default.
• W4311165408 cites W4286285578 @default.
• W4311165408 cites W4289823407 @default.
• W4311165408 cites W4292260879 @default.
• W4311165408 doi "https://doi.org/10.1109/tits.2022.3208004" @default.
• W4311165408 hasPublicationYear "2022" @default.
• W4311165408 type Work @default.
• W4311165408 citedByCount "3" @default.
• W4311165408 countsByYear W43111654082023 @default.
• W4311165408 crossrefType "journal-article" @default.
• W4311165408 hasAuthorship W4311165408A5026433926 @default.
• W4311165408 hasAuthorship W4311165408A5034663296 @default.
• W4311165408 hasAuthorship W4311165408A5038147203 @default.
• W4311165408 hasAuthorship W4311165408A5072073374 @default.
• W4311165408 hasConcept C119857082 @default.
• W4311165408 hasConcept C124101348 @default.
• W4311165408 hasConcept C132525143 @default.
• W4311165408 hasConcept C138885662 @default.
• W4311165408 hasConcept C153180895 @default.
• W4311165408 hasConcept C154945302 @default.
• W4311165408 hasConcept C170133592 @default.
• W4311165408 hasConcept C184337299 @default.
• W4311165408 hasConcept C199360897 @default.
• W4311165408 hasConcept C2776401178 @default.
• W4311165408 hasConcept C36464697 @default.
• W4311165408 hasConcept C41008148 @default.
• W4311165408 hasConcept C41895202 @default.

• next