Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319300191> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4319300191 abstract "Pedestrian trajectory prediction is an essential component of autonomous systems and robot navigation. Recent research has shown promising predictive performance by designing prediction networks to model a variety of motion-related features. Different from existing works, our focus is on designing a novel online adaptation framework (OAT-Mem) to exploit the temporal similarities among trajectory samples encountered during testing to improve the prediction accuracy of any such models (i.e., predictors) without knowing the details of these predictors. Our framework consists of two novel modules: an augmented temporal observation-target memory network (ATM) and a certainty-based selector (CS). Inspired by the concept of key-value memory networks [16], ATM is proposed to learn the temporal information from short-term past frames by encoding the trajectory samples of past pedestrians in form of observation-target (i.e., key-value) during testing. In addition, we propose a certainty-based selector (CS) to enhance the predictive ability of our framework under scenarios where there are large temporal dissimilarities between current pedestrians’ movements and those stored in memory. In dynamic scenes, these scenarios commonly occur due to abrupt changes in contexts, such as camera motions, scene contexts, and pedestrians’ behaviors. We extensively evaluate our framework in commonly-used datasets: JAAD [12] and PIE [19] and show that our framework significantly improves the prediction accuracy of state-of-the-art models. Finally, in-depth studies are conducted to show the importance of each proposed component." @default.
- W4319300191 created "2023-02-07" @default.
- W4319300191 creator A5070579032 @default.
- W4319300191 creator A5005161142 @default.
- W4319300191 date "2023-01-01" @default.
- W4319300191 modified "2023-09-23" @default.
- W4319300191 title "Online Adaptive Temporal Memory with Certainty Estimation for Human Trajectory Prediction" @default.
- W4319300191 cites W2096727211 @default.
- W4319300191 cites W2116341502 @default.
- W4319300191 cites W2150839555 @default.
- W4319300191 cites W2163502413 @default.
- W4319300191 cites W2424778531 @default.
- W4319300191 cites W2520761760 @default.
- W4319300191 cites W2769735038 @default.
- W4319300191 cites W2773583505 @default.
- W4319300191 cites W2963001155 @default.
- W4319300191 cites W2964199361 @default.
- W4319300191 cites W2968393007 @default.
- W4319300191 cites W2981207549 @default.
- W4319300191 cites W2991484432 @default.
- W4319300191 cites W3025086266 @default.
- W4319300191 cites W3035096461 @default.
- W4319300191 cites W3035339264 @default.
- W4319300191 cites W3127710918 @default.
- W4319300191 cites W3154724615 @default.
- W4319300191 cites W3160582233 @default.
- W4319300191 cites W3184430082 @default.
- W4319300191 cites W3190699669 @default.
- W4319300191 cites W3196215298 @default.
- W4319300191 cites W4200247997 @default.
- W4319300191 cites W4206531697 @default.
- W4319300191 cites W4210457203 @default.
- W4319300191 cites W4214913711 @default.
- W4319300191 cites W4312265233 @default.
- W4319300191 doi "https://doi.org/10.1109/wacv56688.2023.00100" @default.
- W4319300191 hasPublicationYear "2023" @default.
- W4319300191 type Work @default.
- W4319300191 citedByCount "0" @default.
- W4319300191 crossrefType "proceedings-article" @default.
- W4319300191 hasAuthorship W4319300191A5005161142 @default.
- W4319300191 hasAuthorship W4319300191A5070579032 @default.
- W4319300191 hasConcept C104114177 @default.
- W4319300191 hasConcept C119857082 @default.
- W4319300191 hasConcept C121332964 @default.
- W4319300191 hasConcept C125411270 @default.
- W4319300191 hasConcept C1276947 @default.
- W4319300191 hasConcept C13662910 @default.
- W4319300191 hasConcept C154945302 @default.
- W4319300191 hasConcept C168167062 @default.
- W4319300191 hasConcept C26517878 @default.
- W4319300191 hasConcept C31972630 @default.
- W4319300191 hasConcept C38652104 @default.
- W4319300191 hasConcept C41008148 @default.
- W4319300191 hasConcept C90509273 @default.
- W4319300191 hasConcept C97355855 @default.
- W4319300191 hasConceptScore W4319300191C104114177 @default.
- W4319300191 hasConceptScore W4319300191C119857082 @default.
- W4319300191 hasConceptScore W4319300191C121332964 @default.
- W4319300191 hasConceptScore W4319300191C125411270 @default.
- W4319300191 hasConceptScore W4319300191C1276947 @default.
- W4319300191 hasConceptScore W4319300191C13662910 @default.
- W4319300191 hasConceptScore W4319300191C154945302 @default.
- W4319300191 hasConceptScore W4319300191C168167062 @default.
- W4319300191 hasConceptScore W4319300191C26517878 @default.
- W4319300191 hasConceptScore W4319300191C31972630 @default.
- W4319300191 hasConceptScore W4319300191C38652104 @default.
- W4319300191 hasConceptScore W4319300191C41008148 @default.
- W4319300191 hasConceptScore W4319300191C90509273 @default.
- W4319300191 hasConceptScore W4319300191C97355855 @default.
- W4319300191 hasLocation W43193001911 @default.
- W4319300191 hasOpenAccess W4319300191 @default.
- W4319300191 hasPrimaryLocation W43193001911 @default.
- W4319300191 hasRelatedWork W1562288862 @default.
- W4319300191 hasRelatedWork W2000407620 @default.
- W4319300191 hasRelatedWork W2029249305 @default.
- W4319300191 hasRelatedWork W2061090284 @default.
- W4319300191 hasRelatedWork W2125579716 @default.
- W4319300191 hasRelatedWork W2144043954 @default.
- W4319300191 hasRelatedWork W2511137960 @default.
- W4319300191 hasRelatedWork W2687972263 @default.
- W4319300191 hasRelatedWork W3214088465 @default.
- W4319300191 hasRelatedWork W4246474087 @default.
- W4319300191 isParatext "false" @default.
- W4319300191 isRetracted "false" @default.
- W4319300191 workType "article" @default.