Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952839748> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2952839748 abstract "Infrared (IR) imaging has the potential to enable more robust action recognition systems compared to visible spectrum cameras due to lower sensitivity to lighting conditions and appearance variability. While the action recognition task on videos collected from visible spectrum imaging has received much attention, action recognition in IR videos is significantly less explored. Our objective is to exploit imaging data in this modality for the action recognition task. In this work, we propose a novel two-stream 3D convolutional neural network (CNN) architecture by introducing the discriminative code layer and the corresponding discriminative code loss function. The proposed network processes IR image and the IR-based optical flow field sequences. We pretrain the 3D CNN model on the visible spectrum Sports-1M action dataset and finetune it on the Infrared Action Recognition (InfAR) dataset. To our best knowledge, this is the first application of the 3D CNN to action recognition in the IR domain. We conduct an elaborate analysis of different fusion schemes (weighted average, single and double-layer neural nets) applied to different 3D CNN outputs. Experimental results demonstrate that our approach can achieve state-of-the-art average precision (AP) performances on the InfAR dataset: (1) the proposed two-stream 3D CNN achieves the best reported 77.5% AP, and (2) our 3D CNN model applied to the optical flow fields achieves the best reported single stream 75.42% AP." @default.
- W2952839748 created "2019-06-27" @default.
- W2952839748 creator A5004182886 @default.
- W2952839748 creator A5046467896 @default.
- W2952839748 creator A5091009689 @default.
- W2952839748 date "2017-05-18" @default.
- W2952839748 modified "2023-09-25" @default.
- W2952839748 title "Learning Spatiotemporal Features for Infrared Action Recognition with 3D Convolutional Neural Networks" @default.
- W2952839748 cites W1522734439 @default.
- W2952839748 cites W1606858007 @default.
- W2952839748 cites W1825675169 @default.
- W2952839748 cites W1903029394 @default.
- W2952839748 cites W1920196880 @default.
- W2952839748 cites W1947481528 @default.
- W2952839748 cites W1981419085 @default.
- W2952839748 cites W2007510844 @default.
- W2952839748 cites W2020163092 @default.
- W2952839748 cites W2038765747 @default.
- W2952839748 cites W2064851185 @default.
- W2952839748 cites W2090042335 @default.
- W2952839748 cites W2102605133 @default.
- W2952839748 cites W2105101328 @default.
- W2952839748 cites W2151103935 @default.
- W2952839748 cites W2161566726 @default.
- W2952839748 cites W2162762921 @default.
- W2952839748 cites W2308045930 @default.
- W2952839748 cites W2473890477 @default.
- W2952839748 cites W2547599103 @default.
- W2952839748 cites W2950971447 @default.
- W2952839748 cites W2952186347 @default.
- W2952839748 cites W2953084276 @default.
- W2952839748 cites W2963628945 @default.
- W2952839748 cites W2964227963 @default.
- W2952839748 doi "https://doi.org/10.48550/arxiv.1705.06709" @default.
- W2952839748 hasPublicationYear "2017" @default.
- W2952839748 type Work @default.
- W2952839748 sameAs 2952839748 @default.
- W2952839748 citedByCount "1" @default.
- W2952839748 countsByYear W29528397482018 @default.
- W2952839748 crossrefType "posted-content" @default.
- W2952839748 hasAuthorship W2952839748A5004182886 @default.
- W2952839748 hasAuthorship W2952839748A5046467896 @default.
- W2952839748 hasAuthorship W2952839748A5091009689 @default.
- W2952839748 hasBestOaLocation W29528397481 @default.
- W2952839748 hasConcept C115961682 @default.
- W2952839748 hasConcept C153180895 @default.
- W2952839748 hasConcept C154945302 @default.
- W2952839748 hasConcept C155542232 @default.
- W2952839748 hasConcept C177264268 @default.
- W2952839748 hasConcept C199360897 @default.
- W2952839748 hasConcept C2776760102 @default.
- W2952839748 hasConcept C2777212361 @default.
- W2952839748 hasConcept C2987834672 @default.
- W2952839748 hasConcept C41008148 @default.
- W2952839748 hasConcept C81363708 @default.
- W2952839748 hasConcept C97931131 @default.
- W2952839748 hasConceptScore W2952839748C115961682 @default.
- W2952839748 hasConceptScore W2952839748C153180895 @default.
- W2952839748 hasConceptScore W2952839748C154945302 @default.
- W2952839748 hasConceptScore W2952839748C155542232 @default.
- W2952839748 hasConceptScore W2952839748C177264268 @default.
- W2952839748 hasConceptScore W2952839748C199360897 @default.
- W2952839748 hasConceptScore W2952839748C2776760102 @default.
- W2952839748 hasConceptScore W2952839748C2777212361 @default.
- W2952839748 hasConceptScore W2952839748C2987834672 @default.
- W2952839748 hasConceptScore W2952839748C41008148 @default.
- W2952839748 hasConceptScore W2952839748C81363708 @default.
- W2952839748 hasConceptScore W2952839748C97931131 @default.
- W2952839748 hasLocation W29528397481 @default.
- W2952839748 hasOpenAccess W2952839748 @default.
- W2952839748 hasPrimaryLocation W29528397481 @default.
- W2952839748 hasRelatedWork W2295107390 @default.
- W2952839748 hasRelatedWork W2406522397 @default.
- W2952839748 hasRelatedWork W2531896461 @default.
- W2952839748 hasRelatedWork W2584229793 @default.
- W2952839748 hasRelatedWork W2614114106 @default.
- W2952839748 hasRelatedWork W2725397116 @default.
- W2952839748 hasRelatedWork W2791383351 @default.
- W2952839748 hasRelatedWork W2796065044 @default.
- W2952839748 hasRelatedWork W3128999341 @default.
- W2952839748 hasRelatedWork W4285814600 @default.
- W2952839748 isParatext "false" @default.
- W2952839748 isRetracted "false" @default.
- W2952839748 magId "2952839748" @default.
- W2952839748 workType "article" @default.