FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3173669596> ?p ?o ?g. }

• W3173669596 endingPage "2162" @default.
• W3173669596 startingPage "2154" @default.
• W3173669596 abstract "Pedestrians with challenging patterns, e.g. small scale or heavy occlusion, appear frequently in practical applications like autonomous driving, which remains tremendous obstacle to higher robustness of detectors. Although plenty of previous works have been dedicated to these problems, properly matching patterns of pedestrian and parameters of detector, i.e., constructing a detector with proper parameter sizes for certain pedestrian patterns of different complexity, has been seldom investigated intensively. Pedestrian instances are usually handled equally with the same amount of parameters, which in our opinion is inadequate for those with more difficult patterns and leads to unsatisfactory performance. Thus, we propose in this paper a novel detection approach via adaptive pattern-parameter matching. The input pedestrian patterns, especially the complex ones, are first disentangled into simpler patterns for detection head by Pattern Disentangling Module (PDM) with various receptive fields. Then, Gating Feature Filtering Module (GFFM) dynamically decides the spatial positions where the patterns are still not simple enough and need further disentanglement by the next-level PDM. Cooperating with these two key components, our approach can adaptively select the best matched parameter size for the input patterns according to their complexity. Moreover, to further explore the relationship between parameter sizes and their performance on the corresponding patterns, two parameter selection policies are designed: 1) extending parameter size to maximum, aiming at more difficult patterns for different occlusion types; 2) specializing parameter size by group division, aiming at complex patterns for scale variations. Extensive experiments on two popular benchmarks, Caltech and CityPersons, show that our proposed method achieves superior performance compared with other state-of-the-art methods on subsets of different scales and occlusion types." @default.
• W3173669596 created "2021-07-05" @default.
• W3173669596 creator A5018448460 @default.
• W3173669596 creator A5074514262 @default.
• W3173669596 creator A5086401510 @default.
• W3173669596 creator A5088499239 @default.
• W3173669596 date "2021-05-18" @default.
• W3173669596 modified "2023-09-26" @default.
• W3173669596 title "Adaptive Pattern-Parameter Matching for Robust Pedestrian Detection" @default.
• W3173669596 cites W1572063013 @default.
• W3173669596 cites W1686810756 @default.
• W3173669596 cites W1995558350 @default.
• W3173669596 cites W2107775979 @default.
• W3173669596 cites W2108598243 @default.
• W3173669596 cites W2161969291 @default.
• W3173669596 cites W2163352848 @default.
• W3173669596 cites W2194775991 @default.
• W3173669596 cites W2565639579 @default.
• W3173669596 cites W2594507094 @default.
• W3173669596 cites W2613599172 @default.
• W3173669596 cites W2883363148 @default.
• W3173669596 cites W2895077992 @default.
• W3173669596 cites W2949117887 @default.
• W3173669596 cites W2962850098 @default.
• W3173669596 cites W2963315052 @default.
• W3173669596 cites W2963318220 @default.
• W3173669596 cites W2963404857 @default.
• W3173669596 cites W2963681621 @default.
• W3173669596 cites W2963840672 @default.
• W3173669596 cites W2981813676 @default.
• W3173669596 cites W2989676862 @default.
• W3173669596 cites W2991471181 @default.
• W3173669596 cites W2995649684 @default.
• W3173669596 cites W2999759184 @default.
• W3173669596 cites W3034307881 @default.
• W3173669596 cites W3034638324 @default.
• W3173669596 cites W639708223 @default.
• W3173669596 doi "https://doi.org/10.1609/aaai.v35i3.16313" @default.
• W3173669596 hasPublicationYear "2021" @default.
• W3173669596 type Work @default.
• W3173669596 sameAs 3173669596 @default.
• W3173669596 citedByCount "4" @default.
• W3173669596 countsByYear W31736695962022 @default.
• W3173669596 countsByYear W31736695962023 @default.
• W3173669596 crossrefType "journal-article" @default.
• W3173669596 hasAuthorship W3173669596A5018448460 @default.
• W3173669596 hasAuthorship W3173669596A5074514262 @default.
• W3173669596 hasAuthorship W3173669596A5086401510 @default.
• W3173669596 hasAuthorship W3173669596A5088499239 @default.
• W3173669596 hasBestOaLocation W31736695961 @default.
• W3173669596 hasConcept C104317684 @default.
• W3173669596 hasConcept C105795698 @default.
• W3173669596 hasConcept C11413529 @default.
• W3173669596 hasConcept C119857082 @default.
• W3173669596 hasConcept C121332964 @default.
• W3173669596 hasConcept C127413603 @default.
• W3173669596 hasConcept C153180895 @default.
• W3173669596 hasConcept C154945302 @default.
• W3173669596 hasConcept C165064840 @default.
• W3173669596 hasConcept C17744445 @default.
• W3173669596 hasConcept C185592680 @default.
• W3173669596 hasConcept C199539241 @default.
• W3173669596 hasConcept C22212356 @default.
• W3173669596 hasConcept C26517878 @default.
• W3173669596 hasConcept C2776650193 @default.
• W3173669596 hasConcept C2777113093 @default.
• W3173669596 hasConcept C2778755073 @default.
• W3173669596 hasConcept C2780156472 @default.
• W3173669596 hasConcept C33923547 @default.
• W3173669596 hasConcept C38652104 @default.
• W3173669596 hasConcept C41008148 @default.
• W3173669596 hasConcept C55493867 @default.
• W3173669596 hasConcept C62520636 @default.
• W3173669596 hasConcept C63479239 @default.
• W3173669596 hasConcept C76155785 @default.
• W3173669596 hasConcept C94915269 @default.
• W3173669596 hasConcept C97256817 @default.
• W3173669596 hasConceptScore W3173669596C104317684 @default.
• W3173669596 hasConceptScore W3173669596C105795698 @default.
• W3173669596 hasConceptScore W3173669596C11413529 @default.
• W3173669596 hasConceptScore W3173669596C119857082 @default.
• W3173669596 hasConceptScore W3173669596C121332964 @default.
• W3173669596 hasConceptScore W3173669596C127413603 @default.
• W3173669596 hasConceptScore W3173669596C153180895 @default.
• W3173669596 hasConceptScore W3173669596C154945302 @default.
• W3173669596 hasConceptScore W3173669596C165064840 @default.
• W3173669596 hasConceptScore W3173669596C17744445 @default.
• W3173669596 hasConceptScore W3173669596C185592680 @default.
• W3173669596 hasConceptScore W3173669596C199539241 @default.
• W3173669596 hasConceptScore W3173669596C22212356 @default.
• W3173669596 hasConceptScore W3173669596C26517878 @default.
• W3173669596 hasConceptScore W3173669596C2776650193 @default.
• W3173669596 hasConceptScore W3173669596C2777113093 @default.
• W3173669596 hasConceptScore W3173669596C2778755073 @default.
• W3173669596 hasConceptScore W3173669596C2780156472 @default.
• W3173669596 hasConceptScore W3173669596C33923547 @default.
• W3173669596 hasConceptScore W3173669596C38652104 @default.
• W3173669596 hasConceptScore W3173669596C41008148 @default.

• next