Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385801467> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4385801467 abstract "Unmanned Aerial Vehicle (UAV) detection in the wild is a challenging task due to the presence of background noise and the varying size of the object. To address these obstacles, we propose a novel learning framework for robust UAV detectors, which we call Difference-based Multi-scale Learning (DML). We argue that motion information matters in UAV detection because of the low recognition in one frame. Our method utilizes the frame difference of multiple previous frames, extracting motion information and blocking background noise. We also fuse multiple spatial-temporal scales for training and inferencing, enabling fusion from different sources. In addition, to better evaluate the performance of UAV detection in different scales, we propose Multi-Scale Average Precision (MSAP) metric to aggregate the detection accuracy over multiple scales. Through extensive experiments, we demonstrate that our proposed approach improves the detection accuracy of baseline models. Notably, we achieve SOTA performance in the 3rd Anti-UAV Challenge, with 2nd place in Track 2 and 4th place in Track 1. <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup>" @default.
- W4385801467 created "2023-08-15" @default.
- W4385801467 creator A5033216637 @default.
- W4385801467 creator A5048621299 @default.
- W4385801467 creator A5069226662 @default.
- W4385801467 creator A5069404739 @default.
- W4385801467 creator A5081115024 @default.
- W4385801467 creator A5091210790 @default.
- W4385801467 date "2023-06-01" @default.
- W4385801467 modified "2023-09-26" @default.
- W4385801467 title "Motion Matters: Difference-based Multi-scale Learning for Infrared UAV Detection" @default.
- W4385801467 cites W1536680647 @default.
- W4385801467 cites W1901129140 @default.
- W4385801467 cites W1972557522 @default.
- W4385801467 cites W2161969291 @default.
- W4385801467 cites W2412782625 @default.
- W4385801467 cites W2490270993 @default.
- W4385801467 cites W2495775297 @default.
- W4385801467 cites W2891964040 @default.
- W4385801467 cites W2988452521 @default.
- W4385801467 cites W2994494428 @default.
- W4385801467 cites W2997408160 @default.
- W4385801467 cites W3014167990 @default.
- W4385801467 cites W3087893884 @default.
- W4385801467 cites W3106250896 @default.
- W4385801467 cites W3127708505 @default.
- W4385801467 cites W3198759525 @default.
- W4385801467 cites W3207847139 @default.
- W4385801467 cites W3209059509 @default.
- W4385801467 cites W3212264119 @default.
- W4385801467 cites W4312516520 @default.
- W4385801467 cites W4313065862 @default.
- W4385801467 doi "https://doi.org/10.1109/cvprw59228.2023.00302" @default.
- W4385801467 hasPublicationYear "2023" @default.
- W4385801467 type Work @default.
- W4385801467 citedByCount "0" @default.
- W4385801467 crossrefType "proceedings-article" @default.
- W4385801467 hasAuthorship W4385801467A5033216637 @default.
- W4385801467 hasAuthorship W4385801467A5048621299 @default.
- W4385801467 hasAuthorship W4385801467A5069226662 @default.
- W4385801467 hasAuthorship W4385801467A5069404739 @default.
- W4385801467 hasAuthorship W4385801467A5081115024 @default.
- W4385801467 hasAuthorship W4385801467A5091210790 @default.
- W4385801467 hasConcept C104114177 @default.
- W4385801467 hasConcept C115961682 @default.
- W4385801467 hasConcept C121332964 @default.
- W4385801467 hasConcept C126042441 @default.
- W4385801467 hasConcept C127413603 @default.
- W4385801467 hasConcept C153180895 @default.
- W4385801467 hasConcept C154945302 @default.
- W4385801467 hasConcept C176217482 @default.
- W4385801467 hasConcept C21547014 @default.
- W4385801467 hasConcept C2776151529 @default.
- W4385801467 hasConcept C2778755073 @default.
- W4385801467 hasConcept C31972630 @default.
- W4385801467 hasConcept C41008148 @default.
- W4385801467 hasConcept C62520636 @default.
- W4385801467 hasConcept C76155785 @default.
- W4385801467 hasConcept C94915269 @default.
- W4385801467 hasConcept C99498987 @default.
- W4385801467 hasConceptScore W4385801467C104114177 @default.
- W4385801467 hasConceptScore W4385801467C115961682 @default.
- W4385801467 hasConceptScore W4385801467C121332964 @default.
- W4385801467 hasConceptScore W4385801467C126042441 @default.
- W4385801467 hasConceptScore W4385801467C127413603 @default.
- W4385801467 hasConceptScore W4385801467C153180895 @default.
- W4385801467 hasConceptScore W4385801467C154945302 @default.
- W4385801467 hasConceptScore W4385801467C176217482 @default.
- W4385801467 hasConceptScore W4385801467C21547014 @default.
- W4385801467 hasConceptScore W4385801467C2776151529 @default.
- W4385801467 hasConceptScore W4385801467C2778755073 @default.
- W4385801467 hasConceptScore W4385801467C31972630 @default.
- W4385801467 hasConceptScore W4385801467C41008148 @default.
- W4385801467 hasConceptScore W4385801467C62520636 @default.
- W4385801467 hasConceptScore W4385801467C76155785 @default.
- W4385801467 hasConceptScore W4385801467C94915269 @default.
- W4385801467 hasConceptScore W4385801467C99498987 @default.
- W4385801467 hasFunder F4320309612 @default.
- W4385801467 hasLocation W43858014671 @default.
- W4385801467 hasOpenAccess W4385801467 @default.
- W4385801467 hasPrimaryLocation W43858014671 @default.
- W4385801467 hasRelatedWork W1497101000 @default.
- W4385801467 hasRelatedWork W2095705906 @default.
- W4385801467 hasRelatedWork W2730449274 @default.
- W4385801467 hasRelatedWork W2754428891 @default.
- W4385801467 hasRelatedWork W2782964878 @default.
- W4385801467 hasRelatedWork W2922421953 @default.
- W4385801467 hasRelatedWork W2980691083 @default.
- W4385801467 hasRelatedWork W3002270006 @default.
- W4385801467 hasRelatedWork W3046346900 @default.
- W4385801467 hasRelatedWork W4281560450 @default.
- W4385801467 isParatext "false" @default.
- W4385801467 isRetracted "false" @default.
- W4385801467 workType "article" @default.