FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3178384248> ?p ?o ?g. }

• W3178384248 endingPage "9204" @default.
• W3178384248 startingPage "9190" @default.
• W3178384248 abstract "Modeling interactions among vehicles is critical in improving the efficiency and safety of autonomous driving since complex interactions are ubiquitous in many traffic scenarios. To model interactions under different traffic scenarios, most existing works consider interaction information implicitly in their specific tasks with hand-crafted features and predefined maneuvers. Extracting interaction representation, which can be commonly used among different downstream tasks, is not explored. In this article, we propose a general and novel graph self-attention network (GSAN) to learn the spatial–temporal interaction representation among vehicles by a framework consisting of pretraining and fine-tuning. Specifically, in the pretraining step, we construct the GSAN module based on a graph self-attention layer and a gated recurrent unit layer, and use trajectory autoregression to learn the interaction information among vehicles. In the fine-tuning step, we propose two different adaptation schemes to utilize the learned interaction information in various downstream tasks and fine-tune the entire model with only a few steps. To illustrate the effectiveness and generality of our spatial–temporal interaction model, we conduct extensive experiments on two typical interaction-related tasks, namely, lane-changing classification and trajectory prediction. The experiment results demonstrate that our approach significantly outperforms the state-of-the-art solutions of these two tasks. We also visualize the impact of surrounding vehicles on the ego vehicle in different interaction scenes. The visualization offers an intuitive explanation on how our model captures the dynamic changing interactions among vehicles and makes good predictions in various interaction-related tasks." @default.
• W3178384248 created "2021-07-19" @default.
• W3178384248 creator A5020715652 @default.
• W3178384248 creator A5023664336 @default.
• W3178384248 creator A5036344741 @default.
• W3178384248 creator A5066981817 @default.
• W3178384248 creator A5071933192 @default.
• W3178384248 creator A5072450889 @default.
• W3178384248 date "2022-06-15" @default.
• W3178384248 modified "2023-09-29" @default.
• W3178384248 title "GSAN: Graph Self-Attention Network for Learning Spatial–Temporal Interaction Representation in Autonomous Driving" @default.
• W3178384248 cites W100367037 @default.
• W3178384248 cites W1502485165 @default.
• W3178384248 cites W1919962963 @default.
• W3178384248 cites W1952987468 @default.
• W3178384248 cites W2016407611 @default.
• W3178384248 cites W2048093873 @default.
• W3178384248 cites W2054469884 @default.
• W3178384248 cites W2055556996 @default.
• W3178384248 cites W2058083416 @default.
• W3178384248 cites W2060135607 @default.
• W3178384248 cites W2097545165 @default.
• W3178384248 cites W2101545882 @default.
• W3178384248 cites W2105242877 @default.
• W3178384248 cites W2117144307 @default.
• W3178384248 cites W2120581524 @default.
• W3178384248 cites W2144082602 @default.
• W3178384248 cites W2145989380 @default.
• W3178384248 cites W2149372643 @default.
• W3178384248 cites W2149822156 @default.
• W3178384248 cites W2151491931 @default.
• W3178384248 cites W2151992080 @default.
• W3178384248 cites W2157331557 @default.
• W3178384248 cites W2194775991 @default.
• W3178384248 cites W2343381408 @default.
• W3178384248 cites W2343781317 @default.
• W3178384248 cites W2344985987 @default.
• W3178384248 cites W2406067508 @default.
• W3178384248 cites W2525884872 @default.
• W3178384248 cites W2567297805 @default.
• W3178384248 cites W2570298958 @default.
• W3178384248 cites W2580495915 @default.
• W3178384248 cites W2587460705 @default.
• W3178384248 cites W2607296803 @default.
• W3178384248 cites W2739770424 @default.
• W3178384248 cites W2741086815 @default.
• W3178384248 cites W2758107681 @default.
• W3178384248 cites W2784715585 @default.
• W3178384248 cites W2887177098 @default.
• W3178384248 cites W2896053418 @default.
• W3178384248 cites W2896642734 @default.
• W3178384248 cites W2940129212 @default.
• W3178384248 cites W2963898834 @default.
• W3178384248 cites W2963906196 @default.
• W3178384248 cites W2963945905 @default.
• W3178384248 cites W2969239003 @default.
• W3178384248 cites W2989851631 @default.
• W3178384248 cites W2990116160 @default.
• W3178384248 cites W3011630888 @default.
• W3178384248 cites W3105115779 @default.
• W3178384248 cites W3114753236 @default.
• W3178384248 cites W3130205781 @default.
• W3178384248 cites W2735347723 @default.
• W3178384248 doi "https://doi.org/10.1109/jiot.2021.3093523" @default.
• W3178384248 hasPublicationYear "2022" @default.
• W3178384248 type Work @default.
• W3178384248 sameAs 3178384248 @default.
• W3178384248 citedByCount "5" @default.
• W3178384248 countsByYear W31783842482022 @default.
• W3178384248 countsByYear W31783842482023 @default.
• W3178384248 crossrefType "journal-article" @default.
• W3178384248 hasAuthorship W3178384248A5020715652 @default.
• W3178384248 hasAuthorship W3178384248A5023664336 @default.
• W3178384248 hasAuthorship W3178384248A5036344741 @default.
• W3178384248 hasAuthorship W3178384248A5066981817 @default.
• W3178384248 hasAuthorship W3178384248A5071933192 @default.
• W3178384248 hasAuthorship W3178384248A5072450889 @default.
• W3178384248 hasConcept C105795698 @default.
• W3178384248 hasConcept C107457646 @default.
• W3178384248 hasConcept C119857082 @default.
• W3178384248 hasConcept C121332964 @default.
• W3178384248 hasConcept C1276947 @default.
• W3178384248 hasConcept C132525143 @default.
• W3178384248 hasConcept C13662910 @default.
• W3178384248 hasConcept C154945302 @default.
• W3178384248 hasConcept C15744967 @default.
• W3178384248 hasConcept C17744445 @default.
• W3178384248 hasConcept C199539241 @default.
• W3178384248 hasConcept C2776359362 @default.
• W3178384248 hasConcept C2780767217 @default.
• W3178384248 hasConcept C2993807640 @default.
• W3178384248 hasConcept C33923547 @default.
• W3178384248 hasConcept C36464697 @default.
• W3178384248 hasConcept C38764148 @default.
• W3178384248 hasConcept C41008148 @default.
• W3178384248 hasConcept C542102704 @default.
• W3178384248 hasConcept C80444323 @default.
• W3178384248 hasConcept C94625758 @default.

• next