FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2796249144> ?p ?o ?g. }

• W2796249144 abstract "In this paper, we study the task of detecting semantic parts of an object, e.g., a wheel of a car, under partial occlusion. We propose that all models should be trained without seeing occlusions while being able to transfer the learned knowledge to deal with occlusions. This setting alleviates the difficulty in collecting an exponentially large dataset to cover occlusion patterns and is more essential. In this scenario, the proposal-based deep networks, like RCNN-series, often produce unsatisfactory results, because both the proposal extraction and classification stages may be confused by the irrelevant occluders. To address this, [25] proposed a voting mechanism that combines multiple local visual cues to detect semantic parts. The semantic parts can still be detected even though some visual cues are missing due to occlusions. However, this method is manually-designed, thus is hard to be optimized in an end-to-end manner. In this paper, we present DeepVoting, which incorporates the robustness shown by [25] into a deep network, so that the whole pipeline can be jointly optimized. Specifically, it adds two layers after the intermediate features of a deep network, e.g., the pool-4 layer of VGGNet. The first layer extracts the evidence of local visual cues, and the second layer performs a voting mechanism by utilizing the spatial relationship between visual cues and semantic parts. We also propose an improved version DeepVoting+ by learning visual cues from context outside objects. In experiments, DeepVoting achieves significantly better performance than several baseline methods, including Faster-RCNN, for semantic part detection under occlusion. In addition, DeepVoting enjoys explainability as the detection results can be diagnosed via looking up the voting cues." @default.
• W2796249144 created "2018-04-13" @default.
• W2796249144 creator A5004325726 @default.
• W2796249144 creator A5022344556 @default.
• W2796249144 creator A5050613147 @default.
• W2796249144 creator A5075290241 @default.
• W2796249144 creator A5086706224 @default.
• W2796249144 date "2018-06-01" @default.
• W2796249144 modified "2023-10-13" @default.
• W2796249144 title "DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection Under Partial Occlusion" @default.
• W2796249144 cites W1536680647 @default.
• W2796249144 cites W1903029394 @default.
• W2796249144 cites W2031489346 @default.
• W2796249144 cites W2066624635 @default.
• W2796249144 cites W2088049833 @default.
• W2796249144 cites W2097117768 @default.
• W2796249144 cites W2104408738 @default.
• W2796249144 cites W2124592697 @default.
• W2796249144 cites W2161969291 @default.
• W2796249144 cites W2168356304 @default.
• W2796249144 cites W2194775991 @default.
• W2796249144 cites W2202499615 @default.
• W2796249144 cites W2462457117 @default.
• W2796249144 cites W2962914239 @default.
• W2796249144 cites W2962933856 @default.
• W2796249144 cites W2963037989 @default.
• W2796249144 cites W2964128011 @default.
• W2796249144 cites W326271615 @default.
• W2796249144 doi "https://doi.org/10.1109/cvpr.2018.00149" @default.
• W2796249144 hasPublicationYear "2018" @default.
• W2796249144 type Work @default.
• W2796249144 sameAs 2796249144 @default.
• W2796249144 citedByCount "34" @default.
• W2796249144 countsByYear W27962491442018 @default.
• W2796249144 countsByYear W27962491442019 @default.
• W2796249144 countsByYear W27962491442020 @default.
• W2796249144 countsByYear W27962491442021 @default.
• W2796249144 countsByYear W27962491442022 @default.
• W2796249144 countsByYear W27962491442023 @default.
• W2796249144 crossrefType "proceedings-article" @default.
• W2796249144 hasAuthorship W2796249144A5004325726 @default.
• W2796249144 hasAuthorship W2796249144A5022344556 @default.
• W2796249144 hasAuthorship W2796249144A5050613147 @default.
• W2796249144 hasAuthorship W2796249144A5075290241 @default.
• W2796249144 hasAuthorship W2796249144A5086706224 @default.
• W2796249144 hasBestOaLocation W27962491442 @default.
• W2796249144 hasConcept C104317684 @default.
• W2796249144 hasConcept C108583219 @default.
• W2796249144 hasConcept C111370547 @default.
• W2796249144 hasConcept C151730666 @default.
• W2796249144 hasConcept C153180895 @default.
• W2796249144 hasConcept C154945302 @default.
• W2796249144 hasConcept C17744445 @default.
• W2796249144 hasConcept C178790620 @default.
• W2796249144 hasConcept C185592680 @default.
• W2796249144 hasConcept C199360897 @default.
• W2796249144 hasConcept C199539241 @default.
• W2796249144 hasConcept C2776151529 @default.
• W2796249144 hasConcept C2779227376 @default.
• W2796249144 hasConcept C2779343474 @default.
• W2796249144 hasConcept C31972630 @default.
• W2796249144 hasConcept C41008148 @default.
• W2796249144 hasConcept C43521106 @default.
• W2796249144 hasConcept C520049643 @default.
• W2796249144 hasConcept C55493867 @default.
• W2796249144 hasConcept C63479239 @default.
• W2796249144 hasConcept C74296488 @default.
• W2796249144 hasConcept C86803240 @default.
• W2796249144 hasConcept C94625758 @default.
• W2796249144 hasConceptScore W2796249144C104317684 @default.
• W2796249144 hasConceptScore W2796249144C108583219 @default.
• W2796249144 hasConceptScore W2796249144C111370547 @default.
• W2796249144 hasConceptScore W2796249144C151730666 @default.
• W2796249144 hasConceptScore W2796249144C153180895 @default.
• W2796249144 hasConceptScore W2796249144C154945302 @default.
• W2796249144 hasConceptScore W2796249144C17744445 @default.
• W2796249144 hasConceptScore W2796249144C178790620 @default.
• W2796249144 hasConceptScore W2796249144C185592680 @default.
• W2796249144 hasConceptScore W2796249144C199360897 @default.
• W2796249144 hasConceptScore W2796249144C199539241 @default.
• W2796249144 hasConceptScore W2796249144C2776151529 @default.
• W2796249144 hasConceptScore W2796249144C2779227376 @default.
• W2796249144 hasConceptScore W2796249144C2779343474 @default.
• W2796249144 hasConceptScore W2796249144C31972630 @default.
• W2796249144 hasConceptScore W2796249144C41008148 @default.
• W2796249144 hasConceptScore W2796249144C43521106 @default.
• W2796249144 hasConceptScore W2796249144C520049643 @default.
• W2796249144 hasConceptScore W2796249144C55493867 @default.
• W2796249144 hasConceptScore W2796249144C63479239 @default.
• W2796249144 hasConceptScore W2796249144C74296488 @default.
• W2796249144 hasConceptScore W2796249144C86803240 @default.
• W2796249144 hasConceptScore W2796249144C94625758 @default.
• W2796249144 hasLocation W27962491441 @default.
• W2796249144 hasLocation W27962491442 @default.
• W2796249144 hasLocation W27962491443 @default.
• W2796249144 hasOpenAccess W2796249144 @default.
• W2796249144 hasPrimaryLocation W27962491441 @default.
• W2796249144 hasRelatedWork W2035976912 @default.
• W2796249144 hasRelatedWork W2541791370 @default.
• W2796249144 hasRelatedWork W2754428891 @default.

• next