FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313306311> ?p ?o ?g. }

• W4313306311 endingPage "1166" @default.
• W4313306311 startingPage "1159" @default.
• W4313306311 abstract "Efficiently and accurately detecting people from 3D point cloud data is of great importance in many robotic and autonomous driving applications. This fundamental perception task is still very challenging due to <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>(i)</i> significant deformations of human body pose and gesture over time and <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>(ii)</i> point cloud sparsity and scarcity for pedestrian objects. Recent efficient 3D object detection approaches rely on pillar features. However, these pillar features do not carry sufficient expressive representations to deal with all the aforementioned challenges in detecting people. To address this shortcoming, we first introduce a stackable Pillar Aware Attention (PAA) module to enhance pillar feature extraction while suppressing noises in point clouds. By integrating multi-point-channel-pooling, point-wise, channel-wise, and task-aware attention into a simple module, representation capabilities of pillar features are boosted while only requiring little additional computational resources. We also present Mini-BiFPN, a small yet effective feature network that creates bidirectional information flow and multi-level cross-scale feature fusion to better integrate multi-resolution features. Our proposed framework, namely PiFeNet, has been evaluated on three popular large-scale datasets for 3D pedestrian Detection, i.e. KITTI, JRDB, and nuScenes. It achieves state-of-the-art performance on KITTI Bird-eye-view (BEV) as well as JRDB, and competitive performance on nuScenes. Our approach is a real-time detector with 26 frame-per-second (FPS)." @default.
• W4313306311 created "2023-01-06" @default.
• W4313306311 creator A5017901486 @default.
• W4313306311 creator A5034608678 @default.
• W4313306311 creator A5042932236 @default.
• W4313306311 creator A5077320973 @default.
• W4313306311 date "2023-02-01" @default.
• W4313306311 modified "2023-09-27" @default.
• W4313306311 title "Accurate and Real-Time 3D Pedestrian Detection Using an Efficient Attentive Pillar Network" @default.
• W4313306311 cites W2115579991 @default.
• W4313306311 cites W2752782242 @default.
• W4313306311 cites W2897529137 @default.
• W4313306311 cites W2949708697 @default.
• W4313306311 cites W2951517617 @default.
• W4313306311 cites W2955058313 @default.
• W4313306311 cites W2963091558 @default.
• W4313306311 cites W2963351448 @default.
• W4313306311 cites W2963400571 @default.
• W4313306311 cites W2963587345 @default.
• W4313306311 cites W2963727135 @default.
• W4313306311 cites W2964062501 @default.
• W4313306311 cites W2968296999 @default.
• W4313306311 cites W2980547801 @default.
• W4313306311 cites W2981413347 @default.
• W4313306311 cites W2981689412 @default.
• W4313306311 cites W2981949127 @default.
• W4313306311 cites W2997814983 @default.
• W4313306311 cites W2998254148 @default.
• W4313306311 cites W3003618643 @default.
• W4313306311 cites W3004237909 @default.
• W4313306311 cites W3004414032 @default.
• W4313306311 cites W3025802147 @default.
• W4313306311 cites W3034239557 @default.
• W4313306311 cites W3034314779 @default.
• W4313306311 cites W3034602892 @default.
• W4313306311 cites W3034681945 @default.
• W4313306311 cites W3034971973 @default.
• W4313306311 cites W3035346742 @default.
• W4313306311 cites W3035461736 @default.
• W4313306311 cites W3035574168 @default.
• W4313306311 cites W3108426750 @default.
• W4313306311 cites W3109675406 @default.
• W4313306311 cites W3113028524 @default.
• W4313306311 cites W3144974485 @default.
• W4313306311 cites W3166089996 @default.
• W4313306311 cites W3172509117 @default.
• W4313306311 cites W3177052299 @default.
• W4313306311 cites W3204415296 @default.
• W4313306311 cites W3205844608 @default.
• W4313306311 cites W3206826736 @default.
• W4313306311 cites W3209035582 @default.
• W4313306311 cites W4214755140 @default.
• W4313306311 cites W4293811845 @default.
• W4313306311 cites W4312294656 @default.
• W4313306311 cites W4313015590 @default.
• W4313306311 doi "https://doi.org/10.1109/lra.2022.3233234" @default.
• W4313306311 hasPublicationYear "2023" @default.
• W4313306311 type Work @default.
• W4313306311 citedByCount "0" @default.
• W4313306311 crossrefType "journal-article" @default.
• W4313306311 hasAuthorship W4313306311A5017901486 @default.
• W4313306311 hasAuthorship W4313306311A5034608678 @default.
• W4313306311 hasAuthorship W4313306311A5042932236 @default.
• W4313306311 hasAuthorship W4313306311A5077320973 @default.
• W4313306311 hasBestOaLocation W43133063112 @default.
• W4313306311 hasConcept C127162648 @default.
• W4313306311 hasConcept C127413603 @default.
• W4313306311 hasConcept C131979681 @default.
• W4313306311 hasConcept C138885662 @default.
• W4313306311 hasConcept C154945302 @default.
• W4313306311 hasConcept C201995342 @default.
• W4313306311 hasConcept C22212356 @default.
• W4313306311 hasConcept C2776401178 @default.
• W4313306311 hasConcept C2777113093 @default.
• W4313306311 hasConcept C2780156472 @default.
• W4313306311 hasConcept C2780451532 @default.
• W4313306311 hasConcept C31258907 @default.
• W4313306311 hasConcept C31972630 @default.
• W4313306311 hasConcept C41008148 @default.
• W4313306311 hasConcept C41895202 @default.
• W4313306311 hasConcept C52622490 @default.
• W4313306311 hasConcept C70437156 @default.
• W4313306311 hasConcept C81363708 @default.
• W4313306311 hasConceptScore W4313306311C127162648 @default.
• W4313306311 hasConceptScore W4313306311C127413603 @default.
• W4313306311 hasConceptScore W4313306311C131979681 @default.
• W4313306311 hasConceptScore W4313306311C138885662 @default.
• W4313306311 hasConceptScore W4313306311C154945302 @default.
• W4313306311 hasConceptScore W4313306311C201995342 @default.
• W4313306311 hasConceptScore W4313306311C22212356 @default.
• W4313306311 hasConceptScore W4313306311C2776401178 @default.
• W4313306311 hasConceptScore W4313306311C2777113093 @default.
• W4313306311 hasConceptScore W4313306311C2780156472 @default.
• W4313306311 hasConceptScore W4313306311C2780451532 @default.
• W4313306311 hasConceptScore W4313306311C31258907 @default.
• W4313306311 hasConceptScore W4313306311C31972630 @default.
• W4313306311 hasConceptScore W4313306311C41008148 @default.
• W4313306311 hasConceptScore W4313306311C41895202 @default.

• next