FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4322731710> ?p ?o ?g. }

• W4322731710 abstract "Efficiently encoding high definition maps is of great importance for autonomous navigation, thus they are widely used for tasks such as predicting the future behaviour of traffic participants and planning a safe trajectory. Previous methods tackled this problem either by rasterizing the road into a multichannel image, or by sampling the vectorial representation in fixed sized sub-segments (often called lanelets). The latter has become the go-to method due to its efficiency and expressiveness. However, its main limitation is the fact that the points creating a geometrical shape have to be sampled at a fixed spatial dimension, hence not taking full advantage of this representation’s potential. In this work, we address this problem by making 2 additions to the classical architectures used for encoding such a heterogeneous structure. Rather than using a single network to encode a map element, we propose the decomposition of the map attributes such as road lines, traffic signs, road edges, etc. into structure and style features, an approach inspired by the recent progresses in the photo-realistic style transfer domain. The structural features will be encoded by a shared message passing network that treats the most essential positional data without the need of resampling at a fixed resolution, being able to adapt during inference the spatial dimension of the representation based on the initial length and complexity. The style attributes will be encoded separately and will allow for an easier addition of a new type of map element, without the retraining of the whole system. Evaluating the method on various edge prediction and node classification tasks proves that our method has better results than the previously mentioned approaches in both tasks, while having a 53% smaller memory footprint on average when representing a scenario." @default.
• W4322731710 created "2023-03-03" @default.
• W4322731710 creator A5047954457 @default.
• W4322731710 creator A5078001972 @default.
• W4322731710 date "2022-09-22" @default.
• W4322731710 modified "2023-09-27" @default.
• W4322731710 title "Efficient HD Map encoding via disentangled style-structure representation using graph neural networks" @default.
• W4322731710 cites W1490632837 @default.
• W4322731710 cites W1901129140 @default.
• W4322731710 cites W1999360130 @default.
• W4322731710 cites W2032924574 @default.
• W4322731710 cites W2045531847 @default.
• W4322731710 cites W2194775991 @default.
• W4322731710 cites W2476752140 @default.
• W4322731710 cites W2603777577 @default.
• W4322731710 cites W2604314403 @default.
• W4322731710 cites W2796795797 @default.
• W4322731710 cites W2911286998 @default.
• W4322731710 cites W2962974533 @default.
• W4322731710 cites W2963890275 @default.
• W4322731710 cites W2971092880 @default.
• W4322731710 cites W3034722190 @default.
• W4322731710 cites W3035172746 @default.
• W4322731710 cites W3035574324 @default.
• W4322731710 cites W3090789587 @default.
• W4322731710 cites W3108486966 @default.
• W4322731710 cites W3169575318 @default.
• W4322731710 cites W3172477795 @default.
• W4322731710 cites W3194259208 @default.
• W4322731710 cites W3214950490 @default.
• W4322731710 cites W4312731878 @default.
• W4322731710 doi "https://doi.org/10.1109/iccp56966.2022.10053938" @default.
• W4322731710 hasPublicationYear "2022" @default.
• W4322731710 type Work @default.
• W4322731710 citedByCount "0" @default.
• W4322731710 crossrefType "proceedings-article" @default.
• W4322731710 hasAuthorship W4322731710A5047954457 @default.
• W4322731710 hasAuthorship W4322731710A5078001972 @default.
• W4322731710 hasConcept C104317684 @default.
• W4322731710 hasConcept C125411270 @default.
• W4322731710 hasConcept C132525143 @default.
• W4322731710 hasConcept C153180895 @default.
• W4322731710 hasConcept C154945302 @default.
• W4322731710 hasConcept C17744445 @default.
• W4322731710 hasConcept C185592680 @default.
• W4322731710 hasConcept C199539241 @default.
• W4322731710 hasConcept C202444582 @default.
• W4322731710 hasConcept C2776214188 @default.
• W4322731710 hasConcept C2776359362 @default.
• W4322731710 hasConcept C2780297707 @default.
• W4322731710 hasConcept C31972630 @default.
• W4322731710 hasConcept C33676613 @default.
• W4322731710 hasConcept C33923547 @default.
• W4322731710 hasConcept C41008148 @default.
• W4322731710 hasConcept C55493867 @default.
• W4322731710 hasConcept C66746571 @default.
• W4322731710 hasConcept C80444323 @default.
• W4322731710 hasConcept C94625758 @default.
• W4322731710 hasConceptScore W4322731710C104317684 @default.
• W4322731710 hasConceptScore W4322731710C125411270 @default.
• W4322731710 hasConceptScore W4322731710C132525143 @default.
• W4322731710 hasConceptScore W4322731710C153180895 @default.
• W4322731710 hasConceptScore W4322731710C154945302 @default.
• W4322731710 hasConceptScore W4322731710C17744445 @default.
• W4322731710 hasConceptScore W4322731710C185592680 @default.
• W4322731710 hasConceptScore W4322731710C199539241 @default.
• W4322731710 hasConceptScore W4322731710C202444582 @default.
• W4322731710 hasConceptScore W4322731710C2776214188 @default.
• W4322731710 hasConceptScore W4322731710C2776359362 @default.
• W4322731710 hasConceptScore W4322731710C2780297707 @default.
• W4322731710 hasConceptScore W4322731710C31972630 @default.
• W4322731710 hasConceptScore W4322731710C33676613 @default.
• W4322731710 hasConceptScore W4322731710C33923547 @default.
• W4322731710 hasConceptScore W4322731710C41008148 @default.
• W4322731710 hasConceptScore W4322731710C55493867 @default.
• W4322731710 hasConceptScore W4322731710C66746571 @default.
• W4322731710 hasConceptScore W4322731710C80444323 @default.
• W4322731710 hasConceptScore W4322731710C94625758 @default.
• W4322731710 hasFunder F4320311649 @default.
• W4322731710 hasLocation W43227317101 @default.
• W4322731710 hasOpenAccess W4322731710 @default.
• W4322731710 hasPrimaryLocation W43227317101 @default.
• W4322731710 hasRelatedWork W166366606 @default.
• W4322731710 hasRelatedWork W1990932233 @default.
• W4322731710 hasRelatedWork W2016546218 @default.
• W4322731710 hasRelatedWork W2098911910 @default.
• W4322731710 hasRelatedWork W2098980211 @default.
• W4322731710 hasRelatedWork W2352223314 @default.
• W4322731710 hasRelatedWork W2389073067 @default.
• W4322731710 hasRelatedWork W2509104183 @default.
• W4322731710 hasRelatedWork W2509618504 @default.
• W4322731710 hasRelatedWork W2156243485 @default.
• W4322731710 isParatext "false" @default.
• W4322731710 isRetracted "false" @default.
• W4322731710 workType "article" @default.