FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377000496> ?p ?o ?g. }

• W4377000496 endingPage "6490" @default.
• W4377000496 startingPage "6477" @default.
• W4377000496 abstract "To make intelligent decisions in an autonomous vehicle, the system must predict the future reactions of surrounding vehicles for any given action plan of the ego vehicle. However, learning reactive trajectories is challenging due to scant action-reaction pair data. That is, building a dataset with multiple action-reaction pairs for an identical scene history is impossible in reality. Here, we propose a semi-supervised learning framework with auxiliary structures to handle this problem. The proposed training framework has two modules: Action Reconstructor and Identifier modules with corresponding loss functions referred to as the Reconstruction Loss and Association Loss. In addition to the conventional supervised approach pertaining to readily available data, the Action Reconstructor module is employed to learn the dependencies on the ego vehicle in an unsupervised manner. Furthermore, reaction trajectory data corresponding to the augmented future trajectories of the ego vehicle are not available, meaning that the model must be trained in an unsupervised manner as well. The main idea of the proposed unsupervised learning method is to find the identity feature vector from both history and future trajectories and associate these features for each vehicle. This idea is realized by introducing the Identifier network and the Association Loss, which are used only during the training process. Interestingly, experimental results show that plausible reaction can be predicted for the augmented future trajectory of the ego vehicle, which indicates that the network can generalize the interactive behavior of vehicles from a partially labelled dataset." @default.
• W4377000496 created "2023-05-19" @default.
• W4377000496 creator A5007261581 @default.
• W4377000496 creator A5019576420 @default.
• W4377000496 creator A5026762568 @default.
• W4377000496 creator A5053369243 @default.
• W4377000496 creator A5059976423 @default.
• W4377000496 creator A5091555350 @default.
• W4377000496 date "2023-06-01" @default.
• W4377000496 modified "2023-09-24" @default.
• W4377000496 title "Are Reactions to Ego Vehicles Predictable Without Data?: A Semi-Supervised Approach" @default.
• W4377000496 cites W2116341502 @default.
• W4377000496 cites W2321533354 @default.
• W4377000496 cites W2326925005 @default.
• W4377000496 cites W2424778531 @default.
• W4377000496 cites W2565639579 @default.
• W4377000496 cites W2607296803 @default.
• W4377000496 cites W2801667201 @default.
• W4377000496 cites W2883725317 @default.
• W4377000496 cites W2903709398 @default.
• W4377000496 cites W2940129212 @default.
• W4377000496 cites W2955189650 @default.
• W4377000496 cites W2962687116 @default.
• W4377000496 cites W2963001155 @default.
• W4377000496 cites W2963906196 @default.
• W4377000496 cites W2967177252 @default.
• W4377000496 cites W2997985526 @default.
• W4377000496 cites W3035671534 @default.
• W4377000496 cites W3081613680 @default.
• W4377000496 cites W3107209377 @default.
• W4377000496 cites W3108486966 @default.
• W4377000496 cites W3116263883 @default.
• W4377000496 cites W3116636888 @default.
• W4377000496 cites W3117590843 @default.
• W4377000496 cites W3120182457 @default.
• W4377000496 cites W3129932917 @default.
• W4377000496 cites W3132231991 @default.
• W4377000496 cites W3132718927 @default.
• W4377000496 cites W3139491754 @default.
• W4377000496 cites W3169575318 @default.
• W4377000496 cites W3180491419 @default.
• W4377000496 cites W3205301818 @default.
• W4377000496 cites W3208105962 @default.
• W4377000496 cites W3209373652 @default.
• W4377000496 cites W343636949 @default.
• W4377000496 cites W4300962625 @default.
• W4377000496 doi "https://doi.org/10.1109/tits.2022.3221275" @default.
• W4377000496 hasPublicationYear "2023" @default.
• W4377000496 type Work @default.
• W4377000496 citedByCount "0" @default.
• W4377000496 crossrefType "journal-article" @default.
• W4377000496 hasAuthorship W4377000496A5007261581 @default.
• W4377000496 hasAuthorship W4377000496A5019576420 @default.
• W4377000496 hasAuthorship W4377000496A5026762568 @default.
• W4377000496 hasAuthorship W4377000496A5053369243 @default.
• W4377000496 hasAuthorship W4377000496A5059976423 @default.
• W4377000496 hasAuthorship W4377000496A5091555350 @default.
• W4377000496 hasConcept C11171543 @default.
• W4377000496 hasConcept C119857082 @default.
• W4377000496 hasConcept C121332964 @default.
• W4377000496 hasConcept C1276947 @default.
• W4377000496 hasConcept C136389625 @default.
• W4377000496 hasConcept C13662910 @default.
• W4377000496 hasConcept C138885662 @default.
• W4377000496 hasConcept C142853389 @default.
• W4377000496 hasConcept C154504017 @default.
• W4377000496 hasConcept C154945302 @default.
• W4377000496 hasConcept C15744967 @default.
• W4377000496 hasConcept C199360897 @default.
• W4377000496 hasConcept C24890656 @default.
• W4377000496 hasConcept C2776401178 @default.
• W4377000496 hasConcept C2778355321 @default.
• W4377000496 hasConcept C2780791683 @default.
• W4377000496 hasConcept C41008148 @default.
• W4377000496 hasConcept C41895202 @default.
• W4377000496 hasConcept C50644808 @default.
• W4377000496 hasConcept C542102704 @default.
• W4377000496 hasConcept C62520636 @default.
• W4377000496 hasConcept C8038995 @default.
• W4377000496 hasConcept C9180747 @default.
• W4377000496 hasConceptScore W4377000496C11171543 @default.
• W4377000496 hasConceptScore W4377000496C119857082 @default.
• W4377000496 hasConceptScore W4377000496C121332964 @default.
• W4377000496 hasConceptScore W4377000496C1276947 @default.
• W4377000496 hasConceptScore W4377000496C136389625 @default.
• W4377000496 hasConceptScore W4377000496C13662910 @default.
• W4377000496 hasConceptScore W4377000496C138885662 @default.
• W4377000496 hasConceptScore W4377000496C142853389 @default.
• W4377000496 hasConceptScore W4377000496C154504017 @default.
• W4377000496 hasConceptScore W4377000496C154945302 @default.
• W4377000496 hasConceptScore W4377000496C15744967 @default.
• W4377000496 hasConceptScore W4377000496C199360897 @default.
• W4377000496 hasConceptScore W4377000496C24890656 @default.
• W4377000496 hasConceptScore W4377000496C2776401178 @default.
• W4377000496 hasConceptScore W4377000496C2778355321 @default.
• W4377000496 hasConceptScore W4377000496C2780791683 @default.
• W4377000496 hasConceptScore W4377000496C41008148 @default.
• W4377000496 hasConceptScore W4377000496C41895202 @default.

• next