Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288283931> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4288283931 abstract "Predicting distant future trajectories of agents in a dynamic scene is not an easy problem because the future trajectory of an agent is affected by not only his/her past trajectory but also the scene contexts. To tackle this problem, we propose a model based on recurrent neural networks (RNNs) and a novel method for training the model. The proposed model is based on an encoder-decoder architecture where the encoder encodes inputs (past trajectories and scene context information) while the decoder produces a trajectory from the context vector given by the encoder. We train the networks of the proposed model to produce a future trajectory, which is the closest to the true trajectory, while maximizing a reward from a reward function. The reward function is also trained at the same time to maximize the margin between the rewards from the ground-truth trajectory and its estimate. The reward function plays the role of a regularizer for the proposed model so the trained networks are able to better utilize the scene context information for the prediction task. We evaluated the proposed model on several public datasets. Experimental results show that the prediction performance of the proposed model is much improved by the regularization, which outperforms the-state-of-the-arts in terms of accuracy. The implementation codes are available at https://github.com/d1024choi/traj-pred-irl/." @default.
- W4288283931 created "2022-07-28" @default.
- W4288283931 creator A5029382046 @default.
- W4288283931 creator A5038807650 @default.
- W4288283931 creator A5049775169 @default.
- W4288283931 date "2019-07-10" @default.
- W4288283931 modified "2023-09-26" @default.
- W4288283931 title "Regularizing Neural Networks for Future Trajectory Prediction via Inverse Reinforcement Learning Framework" @default.
- W4288283931 doi "https://doi.org/10.48550/arxiv.1907.04525" @default.
- W4288283931 hasPublicationYear "2019" @default.
- W4288283931 type Work @default.
- W4288283931 citedByCount "0" @default.
- W4288283931 crossrefType "posted-content" @default.
- W4288283931 hasAuthorship W4288283931A5029382046 @default.
- W4288283931 hasAuthorship W4288283931A5038807650 @default.
- W4288283931 hasAuthorship W4288283931A5049775169 @default.
- W4288283931 hasBestOaLocation W42882839311 @default.
- W4288283931 hasConcept C111919701 @default.
- W4288283931 hasConcept C118505674 @default.
- W4288283931 hasConcept C119857082 @default.
- W4288283931 hasConcept C121332964 @default.
- W4288283931 hasConcept C1276947 @default.
- W4288283931 hasConcept C13662910 @default.
- W4288283931 hasConcept C14036430 @default.
- W4288283931 hasConcept C147168706 @default.
- W4288283931 hasConcept C151730666 @default.
- W4288283931 hasConcept C154945302 @default.
- W4288283931 hasConcept C2776135515 @default.
- W4288283931 hasConcept C2779343474 @default.
- W4288283931 hasConcept C41008148 @default.
- W4288283931 hasConcept C50644808 @default.
- W4288283931 hasConcept C774472 @default.
- W4288283931 hasConcept C78458016 @default.
- W4288283931 hasConcept C86803240 @default.
- W4288283931 hasConcept C97541855 @default.
- W4288283931 hasConceptScore W4288283931C111919701 @default.
- W4288283931 hasConceptScore W4288283931C118505674 @default.
- W4288283931 hasConceptScore W4288283931C119857082 @default.
- W4288283931 hasConceptScore W4288283931C121332964 @default.
- W4288283931 hasConceptScore W4288283931C1276947 @default.
- W4288283931 hasConceptScore W4288283931C13662910 @default.
- W4288283931 hasConceptScore W4288283931C14036430 @default.
- W4288283931 hasConceptScore W4288283931C147168706 @default.
- W4288283931 hasConceptScore W4288283931C151730666 @default.
- W4288283931 hasConceptScore W4288283931C154945302 @default.
- W4288283931 hasConceptScore W4288283931C2776135515 @default.
- W4288283931 hasConceptScore W4288283931C2779343474 @default.
- W4288283931 hasConceptScore W4288283931C41008148 @default.
- W4288283931 hasConceptScore W4288283931C50644808 @default.
- W4288283931 hasConceptScore W4288283931C774472 @default.
- W4288283931 hasConceptScore W4288283931C78458016 @default.
- W4288283931 hasConceptScore W4288283931C86803240 @default.
- W4288283931 hasConceptScore W4288283931C97541855 @default.
- W4288283931 hasLocation W42882839311 @default.
- W4288283931 hasOpenAccess W4288283931 @default.
- W4288283931 hasPrimaryLocation W42882839311 @default.
- W4288283931 hasRelatedWork W1572419878 @default.
- W4288283931 hasRelatedWork W2809005670 @default.
- W4288283931 hasRelatedWork W2963561234 @default.
- W4288283931 hasRelatedWork W2965519056 @default.
- W4288283931 hasRelatedWork W3015280164 @default.
- W4288283931 hasRelatedWork W3022038857 @default.
- W4288283931 hasRelatedWork W3162151154 @default.
- W4288283931 hasRelatedWork W3170828825 @default.
- W4288283931 hasRelatedWork W4319083788 @default.
- W4288283931 hasRelatedWork W1629725936 @default.
- W4288283931 isParatext "false" @default.
- W4288283931 isRetracted "false" @default.
- W4288283931 workType "article" @default.