Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385804949> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4385804949 abstract "Automatic target recognition (ATR) using image data is an important computer vision task with widespread applications in remote sensing for surveillance, object tracking, urban planning, agriculture, and more. Although there have been continuous advancements in this task, there is still significant room for further advancements, particularly with aerial images. This work extracts rich information from multimodal synthetic aperture radar (SAR) and electro-optical (EO) aerial images to perform object classification.Compared to EO images, the advantages of SAR images are that they can be captured at night and in any weather condition. Compared to EO images, the disadvantage of SAR images is that they are noisy. Overcoming the noise inherent to SAR images is a challenging, but worthwhile, task because of the additional information SAR images provide the model.This work proposes a training strategy that involves the creation of appearance labels to generate triplet pairs for training the network with both triplet loss and cross-entropy loss. During the development phase of the 2023 Perception Beyond Visual Spectrum (PBVS) Multi-modal Aerial Image Object Classification (MAVOC) challenge, our ResNet-34 model achieved a top-1 accuracy of 64.29% for Track 1 and our ensemble learning model achieved a top-1 accuracy 75.84% for Track 2. These values are 542% and 247% higher than the baseline values. Overall, this work ranked 3 <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>rd</sup> in both Track 1 and Track 2." @default.
- W4385804949 created "2023-08-15" @default.
- W4385804949 creator A5023566658 @default.
- W4385804949 creator A5038036261 @default.
- W4385804949 creator A5042751665 @default.
- W4385804949 creator A5055325527 @default.
- W4385804949 date "2023-06-01" @default.
- W4385804949 modified "2023-09-26" @default.
- W4385804949 title "Appearance Label Balanced Triplet Loss for Multi-modal Aerial View Object Classification" @default.
- W4385804949 cites W2292481059 @default.
- W4385804949 cites W2410591237 @default.
- W4385804949 cites W2588453093 @default.
- W4385804949 cites W2615263668 @default.
- W4385804949 cites W2746325398 @default.
- W4385804949 cites W2899198451 @default.
- W4385804949 cites W2902666195 @default.
- W4385804949 cites W2948594896 @default.
- W4385804949 cites W2948672349 @default.
- W4385804949 cites W2980096013 @default.
- W4385804949 cites W3001106372 @default.
- W4385804949 cites W3099206234 @default.
- W4385804949 cites W3103856189 @default.
- W4385804949 cites W3138516171 @default.
- W4385804949 cites W3173207688 @default.
- W4385804949 cites W3175740673 @default.
- W4385804949 cites W3175761677 @default.
- W4385804949 cites W3207506706 @default.
- W4385804949 cites W4206435359 @default.
- W4385804949 cites W4281669974 @default.
- W4385804949 cites W4285037013 @default.
- W4385804949 cites W4292787468 @default.
- W4385804949 cites W4292829057 @default.
- W4385804949 doi "https://doi.org/10.1109/cvprw59228.2023.00060" @default.
- W4385804949 hasPublicationYear "2023" @default.
- W4385804949 type Work @default.
- W4385804949 citedByCount "0" @default.
- W4385804949 crossrefType "proceedings-article" @default.
- W4385804949 hasAuthorship W4385804949A5023566658 @default.
- W4385804949 hasAuthorship W4385804949A5038036261 @default.
- W4385804949 hasAuthorship W4385804949A5042751665 @default.
- W4385804949 hasAuthorship W4385804949A5055325527 @default.
- W4385804949 hasConcept C153180895 @default.
- W4385804949 hasConcept C154945302 @default.
- W4385804949 hasConcept C2776151529 @default.
- W4385804949 hasConcept C31972630 @default.
- W4385804949 hasConcept C41008148 @default.
- W4385804949 hasConcept C87360688 @default.
- W4385804949 hasConceptScore W4385804949C153180895 @default.
- W4385804949 hasConceptScore W4385804949C154945302 @default.
- W4385804949 hasConceptScore W4385804949C2776151529 @default.
- W4385804949 hasConceptScore W4385804949C31972630 @default.
- W4385804949 hasConceptScore W4385804949C41008148 @default.
- W4385804949 hasConceptScore W4385804949C87360688 @default.
- W4385804949 hasLocation W43858049491 @default.
- W4385804949 hasOpenAccess W4385804949 @default.
- W4385804949 hasPrimaryLocation W43858049491 @default.
- W4385804949 hasRelatedWork W1497101000 @default.
- W4385804949 hasRelatedWork W2095705906 @default.
- W4385804949 hasRelatedWork W2730449274 @default.
- W4385804949 hasRelatedWork W2754428891 @default.
- W4385804949 hasRelatedWork W2782964878 @default.
- W4385804949 hasRelatedWork W2922421953 @default.
- W4385804949 hasRelatedWork W2980691083 @default.
- W4385804949 hasRelatedWork W3002270006 @default.
- W4385804949 hasRelatedWork W3046346900 @default.
- W4385804949 hasRelatedWork W4281560450 @default.
- W4385804949 isParatext "false" @default.
- W4385804949 isRetracted "false" @default.
- W4385804949 workType "article" @default.