FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100718911> ?p ?o ?g. }

• W3100718911 endingPage "206444" @default.
• W3100718911 startingPage "206427" @default.
• W3100718911 abstract "Deep learning-based action recognition in videos has obtained much attention because of achieving remarkable performance in diverse applications. However, due to the heterogeneous background and noisy spatio-temporal cues, extracting highly discriminative features is still quite challenging. To deal with this problem, numerous methods have been published based on the attention mechanism and skeleton modality. Instead of focusing on data pre-processing, we shed light on the feature map and concentrate on extracting highly discriminative features. First, we introduce Batch-wise Entropy Supervised Stream (BESS) to extend feature discrimination similar to the uncertainty of the corresponding batch. Secondly, to obtain a more generalized model, we propose a Stream to Harmonize the feature discrimination by Augmenting both Features (HAFS) of ResNext101 and BESS. These two streams are hallucinated by the distillation and feature fusion technique effectively into HAFS. We introduce a new metric to assess the characteristics of the feature map. This metric depicts the relationship between the feature discrimination and recognition accuracy. Finally, we comprehensively evaluate our approach on two benchmark datasets, HMDB51 and UCF101. Experimental results demonstrate that, extending and then harmonizing the feature discrimination is one of the effective ways of generating highly discriminative features. Experimental outcomes indicate the superiority of our proposed technique over the existing state-of-the-art methods." @default.
• W3100718911 created "2020-11-23" @default.
• W3100718911 creator A5000263913 @default.
• W3100718911 creator A5024023328 @default.
• W3100718911 creator A5042329558 @default.
• W3100718911 creator A5069559264 @default.
• W3100718911 creator A5086225474 @default.
• W3100718911 date "2020-01-01" @default.
• W3100718911 modified "2023-09-27" @default.
• W3100718911 title "Batch Entropy Supervised Convolutional Neural Networks for Feature Extraction and Harmonizing for Action Recognition" @default.
• W3100718911 cites W1522734439 @default.
• W3100718911 cites W1578985305 @default.
• W3100718911 cites W1923404803 @default.
• W3100718911 cites W1947481528 @default.
• W3100718911 cites W1977995219 @default.
• W3100718911 cites W1983364832 @default.
• W3100718911 cites W1993229407 @default.
• W3100718911 cites W1995875735 @default.
• W3100718911 cites W2016053056 @default.
• W3100718911 cites W2074034193 @default.
• W3100718911 cites W2097117768 @default.
• W3100718911 cites W2098339052 @default.
• W3100718911 cites W2105101328 @default.
• W3100718911 cites W2126574503 @default.
• W3100718911 cites W2126579184 @default.
• W3100718911 cites W2142194269 @default.
• W3100718911 cites W2143267104 @default.
• W3100718911 cites W2161565164 @default.
• W3100718911 cites W2172156083 @default.
• W3100718911 cites W2194775991 @default.
• W3100718911 cites W2339712187 @default.
• W3100718911 cites W2342662179 @default.
• W3100718911 cites W2398232863 @default.
• W3100718911 cites W2442651457 @default.
• W3100718911 cites W2462996230 @default.
• W3100718911 cites W2463402750 @default.
• W3100718911 cites W2467483865 @default.
• W3100718911 cites W2471775118 @default.
• W3100718911 cites W2510185399 @default.
• W3100718911 cites W2510249351 @default.
• W3100718911 cites W2549139847 @default.
• W3100718911 cites W2594613244 @default.
• W3100718911 cites W2736596806 @default.
• W3100718911 cites W2746726611 @default.
• W3100718911 cites W2779380177 @default.
• W3100718911 cites W2809440904 @default.
• W3100718911 cites W2883429621 @default.
• W3100718911 cites W2900712384 @default.
• W3100718911 cites W2901090508 @default.
• W3100718911 cites W2912735527 @default.
• W3100718911 cites W2926527602 @default.
• W3100718911 cites W2940457086 @default.
• W3100718911 cites W2947084868 @default.
• W3100718911 cites W2962858109 @default.
• W3100718911 cites W2962934715 @default.
• W3100718911 cites W2963166524 @default.
• W3100718911 cites W2963246338 @default.
• W3100718911 cites W2963524571 @default.
• W3100718911 cites W2963901033 @default.
• W3100718911 cites W2964094092 @default.
• W3100718911 cites W2964303945 @default.
• W3100718911 cites W2994365842 @default.
• W3100718911 cites W3001281877 @default.
• W3100718911 cites W3002271958 @default.
• W3100718911 cites W3007930095 @default.
• W3100718911 cites W3011934803 @default.
• W3100718911 cites W3015483809 @default.
• W3100718911 cites W3043878998 @default.
• W3100718911 cites W3098538019 @default.
• W3100718911 cites W4255421341 @default.
• W3100718911 cites W874179280 @default.
• W3100718911 doi "https://doi.org/10.1109/access.2020.3037529" @default.
• W3100718911 hasPublicationYear "2020" @default.
• W3100718911 type Work @default.
• W3100718911 sameAs 3100718911 @default.
• W3100718911 citedByCount "7" @default.
• W3100718911 countsByYear W31007189112021 @default.
• W3100718911 countsByYear W31007189112022 @default.
• W3100718911 countsByYear W31007189112023 @default.
• W3100718911 crossrefType "journal-article" @default.
• W3100718911 hasAuthorship W3100718911A5000263913 @default.
• W3100718911 hasAuthorship W3100718911A5024023328 @default.
• W3100718911 hasAuthorship W3100718911A5042329558 @default.
• W3100718911 hasAuthorship W3100718911A5069559264 @default.
• W3100718911 hasAuthorship W3100718911A5086225474 @default.
• W3100718911 hasBestOaLocation W31007189111 @default.
• W3100718911 hasConcept C106301342 @default.
• W3100718911 hasConcept C119857082 @default.
• W3100718911 hasConcept C121332964 @default.
• W3100718911 hasConcept C13280743 @default.
• W3100718911 hasConcept C138885662 @default.
• W3100718911 hasConcept C153180895 @default.
• W3100718911 hasConcept C154945302 @default.
• W3100718911 hasConcept C185798385 @default.
• W3100718911 hasConcept C205649164 @default.
• W3100718911 hasConcept C2776401178 @default.
• W3100718911 hasConcept C41008148 @default.
• W3100718911 hasConcept C41895202 @default.

• next