Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385267443> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4385267443 endingPage "437" @default.
- W4385267443 startingPage "430" @default.
- W4385267443 abstract "Object detection plays a vital role in computer vision. As a typical application of object detection, road damage detection has strong practicability. Road damage includes longitudinal crack, transverse crack, etc. Compared with universal objects, the length-width ratio of road damage is usually extreme, and the road damage appears like a line. Thus, in the paper, we utilize this characteristic of road damage to propose linear refinement attention. Our linear refinement attention consists of two parts: linear pooling and linear convolution. They are connected in series and refine the intermediate feature maps’ global and local features, respectively. They both first capture high-level semantic features, then transform the captured features into weight, and finally utilize the weight to refine the input. The most common dataset for road damage detection is Road Damage Dataset 2020 (RDD2020). According to our observation, many images in RDD2020 lack labels, leading to unreasonable evaluation. Thus, we optimized the dataset to ensure a professional and accurate evaluation. We conducted many experiments, and the results show that our method can capture the features of road damage more accurately and improve the mAP steadily compared with the baseline." @default.
- W4385267443 created "2023-07-27" @default.
- W4385267443 creator A5006366039 @default.
- W4385267443 creator A5019477857 @default.
- W4385267443 date "2023-01-01" @default.
- W4385267443 modified "2023-09-27" @default.
- W4385267443 title "Linear Refinement Attention for Road Damage Detection" @default.
- W4385267443 cites W2752782242 @default.
- W4385267443 cites W2884585870 @default.
- W4385267443 cites W2979945072 @default.
- W4385267443 cites W3034502973 @default.
- W4385267443 cites W3099452838 @default.
- W4385267443 cites W3136227916 @default.
- W4385267443 cites W3137274716 @default.
- W4385267443 cites W3137588588 @default.
- W4385267443 cites W3138867123 @default.
- W4385267443 cites W3161660388 @default.
- W4385267443 cites W3177052299 @default.
- W4385267443 doi "https://doi.org/10.1007/978-981-99-3951-0_47" @default.
- W4385267443 hasPublicationYear "2023" @default.
- W4385267443 type Work @default.
- W4385267443 citedByCount "0" @default.
- W4385267443 crossrefType "book-chapter" @default.
- W4385267443 hasAuthorship W4385267443A5006366039 @default.
- W4385267443 hasAuthorship W4385267443A5019477857 @default.
- W4385267443 hasConcept C138885662 @default.
- W4385267443 hasConcept C153180895 @default.
- W4385267443 hasConcept C154945302 @default.
- W4385267443 hasConcept C2776151529 @default.
- W4385267443 hasConcept C2776401178 @default.
- W4385267443 hasConcept C31972630 @default.
- W4385267443 hasConcept C41008148 @default.
- W4385267443 hasConcept C41895202 @default.
- W4385267443 hasConcept C45347329 @default.
- W4385267443 hasConcept C50644808 @default.
- W4385267443 hasConcept C70437156 @default.
- W4385267443 hasConceptScore W4385267443C138885662 @default.
- W4385267443 hasConceptScore W4385267443C153180895 @default.
- W4385267443 hasConceptScore W4385267443C154945302 @default.
- W4385267443 hasConceptScore W4385267443C2776151529 @default.
- W4385267443 hasConceptScore W4385267443C2776401178 @default.
- W4385267443 hasConceptScore W4385267443C31972630 @default.
- W4385267443 hasConceptScore W4385267443C41008148 @default.
- W4385267443 hasConceptScore W4385267443C41895202 @default.
- W4385267443 hasConceptScore W4385267443C45347329 @default.
- W4385267443 hasConceptScore W4385267443C50644808 @default.
- W4385267443 hasConceptScore W4385267443C70437156 @default.
- W4385267443 hasLocation W43852674431 @default.
- W4385267443 hasOpenAccess W4385267443 @default.
- W4385267443 hasPrimaryLocation W43852674431 @default.
- W4385267443 hasRelatedWork W1497101000 @default.
- W4385267443 hasRelatedWork W1504288058 @default.
- W4385267443 hasRelatedWork W2095705906 @default.
- W4385267443 hasRelatedWork W2291847203 @default.
- W4385267443 hasRelatedWork W2331674254 @default.
- W4385267443 hasRelatedWork W2754428891 @default.
- W4385267443 hasRelatedWork W2782964878 @default.
- W4385267443 hasRelatedWork W2922421953 @default.
- W4385267443 hasRelatedWork W3002270006 @default.
- W4385267443 hasRelatedWork W4281560450 @default.
- W4385267443 isParatext "false" @default.
- W4385267443 isRetracted "false" @default.
- W4385267443 workType "book-chapter" @default.