Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225688144> ?p ?o ?g. }
- W4225688144 endingPage "2987" @default.
- W4225688144 startingPage "2975" @default.
- W4225688144 abstract "Event cameras, offering extremely high temporal resolution and high dynamic range, have brought a new perspective to addressing common object detection challenges (e.g., motion blur and low light). However, how to learn a better spatio-temporal representation and exploit rich temporal cues from asynchronous events for object detection still remains an open issue. To address this problem, we propose a novel asynchronous spatio-temporal memory network (ASTMNet) that directly consumes asynchronous events instead of event images prior to processing, which can well detect objects in a continuous manner. Technically, ASTMNet learns an asynchronous attention embedding from the continuous event stream by adopting an adaptive temporal sampling strategy and a temporal attention convolutional module. Besides, a spatio-temporal memory module is designed to exploit rich temporal cues via a lightweight yet efficient inter-weaved recurrent-convolutional architecture. Empirically, it shows that our approach outperforms the state-of-the-art methods using the feed-forward frame-based detectors on three datasets by a large margin (i.e., 7.6% in the KITTI Simulated Dataset, 10.8% in the Gen1 Automotive Dataset, and 10.5% in the 1Mpx Detection Dataset). The results demonstrate that event cameras can perform robust object detection even in cases where conventional cameras fail, e.g., fast motion and challenging light conditions." @default.
- W4225688144 created "2022-05-05" @default.
- W4225688144 creator A5023918894 @default.
- W4225688144 creator A5048136889 @default.
- W4225688144 creator A5053118577 @default.
- W4225688144 creator A5055115466 @default.
- W4225688144 creator A5058066577 @default.
- W4225688144 creator A5081538036 @default.
- W4225688144 date "2022-01-01" @default.
- W4225688144 modified "2023-10-16" @default.
- W4225688144 title "Asynchronous Spatio-Temporal Memory Network for Continuous Event-Based Object Detection" @default.
- W4225688144 cites W1632573554 @default.
- W4225688144 cites W1980178290 @default.
- W4225688144 cites W2011589116 @default.
- W4225688144 cites W2016574277 @default.
- W4225688144 cites W2064675550 @default.
- W4225688144 cites W206948248 @default.
- W4225688144 cites W2150066425 @default.
- W4225688144 cites W2157331557 @default.
- W4225688144 cites W2163288878 @default.
- W4225688144 cites W2194775991 @default.
- W4225688144 cites W2469278928 @default.
- W4225688144 cites W2570343428 @default.
- W4225688144 cites W2745933219 @default.
- W4225688144 cites W2769320958 @default.
- W4225688144 cites W2883294120 @default.
- W4225688144 cites W2896652992 @default.
- W4225688144 cites W2904275768 @default.
- W4225688144 cites W2909642632 @default.
- W4225688144 cites W2919115771 @default.
- W4225688144 cites W2921116036 @default.
- W4225688144 cites W2941699466 @default.
- W4225688144 cites W2944851425 @default.
- W4225688144 cites W2945249744 @default.
- W4225688144 cites W2947930228 @default.
- W4225688144 cites W2955060956 @default.
- W4225688144 cites W2963037989 @default.
- W4225688144 cites W2963144106 @default.
- W4225688144 cites W2963212638 @default.
- W4225688144 cites W2963510238 @default.
- W4225688144 cites W2963625188 @default.
- W4225688144 cites W2963853051 @default.
- W4225688144 cites W2964981172 @default.
- W4225688144 cites W2969508737 @default.
- W4225688144 cites W2969741484 @default.
- W4225688144 cites W2983367574 @default.
- W4225688144 cites W2984844508 @default.
- W4225688144 cites W2988916019 @default.
- W4225688144 cites W2990793844 @default.
- W4225688144 cites W2998281665 @default.
- W4225688144 cites W3010268791 @default.
- W4225688144 cites W3043940359 @default.
- W4225688144 cites W3095334530 @default.
- W4225688144 cites W3097883549 @default.
- W4225688144 cites W3102178346 @default.
- W4225688144 cites W3110053799 @default.
- W4225688144 cites W3133660631 @default.
- W4225688144 cites W3176165731 @default.
- W4225688144 cites W3188021906 @default.
- W4225688144 cites W3194536588 @default.
- W4225688144 cites W3202344666 @default.
- W4225688144 cites W4226051885 @default.
- W4225688144 cites W639708223 @default.
- W4225688144 doi "https://doi.org/10.1109/tip.2022.3162962" @default.
- W4225688144 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35377848" @default.
- W4225688144 hasPublicationYear "2022" @default.
- W4225688144 type Work @default.
- W4225688144 citedByCount "10" @default.
- W4225688144 countsByYear W42256881442022 @default.
- W4225688144 countsByYear W42256881442023 @default.
- W4225688144 crossrefType "journal-article" @default.
- W4225688144 hasAuthorship W4225688144A5023918894 @default.
- W4225688144 hasAuthorship W4225688144A5048136889 @default.
- W4225688144 hasAuthorship W4225688144A5053118577 @default.
- W4225688144 hasAuthorship W4225688144A5055115466 @default.
- W4225688144 hasAuthorship W4225688144A5058066577 @default.
- W4225688144 hasAuthorship W4225688144A5081538036 @default.
- W4225688144 hasConcept C115961682 @default.
- W4225688144 hasConcept C119666444 @default.
- W4225688144 hasConcept C119857082 @default.
- W4225688144 hasConcept C121332964 @default.
- W4225688144 hasConcept C151319957 @default.
- W4225688144 hasConcept C153180895 @default.
- W4225688144 hasConcept C154945302 @default.
- W4225688144 hasConcept C165696696 @default.
- W4225688144 hasConcept C2776151529 @default.
- W4225688144 hasConcept C2777708103 @default.
- W4225688144 hasConcept C2779662365 @default.
- W4225688144 hasConcept C31258907 @default.
- W4225688144 hasConcept C31972630 @default.
- W4225688144 hasConcept C38652104 @default.
- W4225688144 hasConcept C41008148 @default.
- W4225688144 hasConcept C62520636 @default.
- W4225688144 hasConcept C774472 @default.
- W4225688144 hasConcept C81363708 @default.
- W4225688144 hasConceptScore W4225688144C115961682 @default.
- W4225688144 hasConceptScore W4225688144C119666444 @default.
- W4225688144 hasConceptScore W4225688144C119857082 @default.