Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897187502> ?p ?o ?g. }
- W2897187502 endingPage "3015" @default.
- W2897187502 startingPage "3001" @default.
- W2897187502 abstract "In this paper, we investigate the problem of RGB-D egocentric action recognition. Unlike conventional human action videos that are passively recorded by static cameras, egocentric videos are self-generated from wearable sensors that are more flexible and provide the close-ups with the visual attention of the wearers when they act. Moreover, RGB-D videos contain the spatial appearance and temporal information in the RGB modality and reflect the 3D structure of the scenes in the depth modality. To adequately learn the nonlinear structure of heterogeneous representations from different modalities and exploit their complementary characteristics, we develop a multi-stream deep neural networks (MDNN) method, which aims to preserve the distinctive property for each modality and simultaneously explore their sharable information in a unified deep architecture. Specifically, we deploy a Cauchy estimator to maximize the correlations of the sharable components and enforce the orthogonality constraints on the distinctive components to guarantee their high independencies. Since the egocentric action recognition is usually sensitive to hand poses, we extend our MDNN by integrating with the hand cues to enhance the recognition accuracy. Extensive experimental results on a newly collected data set and two additional benchmarks are presented to demonstrate the effectiveness of our proposed method for RGB-D egocentric action recognition." @default.
- W2897187502 created "2018-10-26" @default.
- W2897187502 creator A5010357390 @default.
- W2897187502 creator A5073314550 @default.
- W2897187502 creator A5077076810 @default.
- W2897187502 creator A5084679040 @default.
- W2897187502 creator A5090079801 @default.
- W2897187502 date "2019-10-01" @default.
- W2897187502 modified "2023-10-15" @default.
- W2897187502 title "Multi-Stream Deep Neural Networks for RGB-D Egocentric Action Recognition" @default.
- W2897187502 cites W1522734439 @default.
- W2897187502 cites W1536675765 @default.
- W2897187502 cites W1578285471 @default.
- W2897187502 cites W1578985305 @default.
- W2897187502 cites W1595717062 @default.
- W2897187502 cites W1606858007 @default.
- W2897187502 cites W1870859634 @default.
- W2897187502 cites W1871385855 @default.
- W2897187502 cites W1893516992 @default.
- W2897187502 cites W1895914852 @default.
- W2897187502 cites W1903029394 @default.
- W2897187502 cites W1922904362 @default.
- W2897187502 cites W1981822424 @default.
- W2897187502 cites W1983364832 @default.
- W2897187502 cites W1989469598 @default.
- W2897187502 cites W1991762259 @default.
- W2897187502 cites W1993229407 @default.
- W2897187502 cites W1997567675 @default.
- W2897187502 cites W2016053056 @default.
- W2897187502 cites W2020163092 @default.
- W2897187502 cites W2021923564 @default.
- W2897187502 cites W2031688197 @default.
- W2897187502 cites W2035299679 @default.
- W2897187502 cites W2037231462 @default.
- W2897187502 cites W2044248322 @default.
- W2897187502 cites W2063362452 @default.
- W2897187502 cites W2070999216 @default.
- W2897187502 cites W2082497897 @default.
- W2897187502 cites W2105101328 @default.
- W2897187502 cites W2109761267 @default.
- W2897187502 cites W2117539524 @default.
- W2897187502 cites W2120645068 @default.
- W2897187502 cites W2126574503 @default.
- W2897187502 cites W2130055251 @default.
- W2897187502 cites W2134123547 @default.
- W2897187502 cites W2136668269 @default.
- W2897187502 cites W2139395976 @default.
- W2897187502 cites W2142194269 @default.
- W2897187502 cites W2142674578 @default.
- W2897187502 cites W2142694332 @default.
- W2897187502 cites W2147806277 @default.
- W2897187502 cites W2149276562 @default.
- W2897187502 cites W2162762857 @default.
- W2897187502 cites W2163915297 @default.
- W2897187502 cites W2165605600 @default.
- W2897187502 cites W2167626157 @default.
- W2897187502 cites W2194775991 @default.
- W2897187502 cites W2204609240 @default.
- W2897187502 cites W2212494831 @default.
- W2897187502 cites W2219155316 @default.
- W2897187502 cites W2309561466 @default.
- W2897187502 cites W2336162022 @default.
- W2897187502 cites W2432964524 @default.
- W2897187502 cites W2434184923 @default.
- W2897187502 cites W2508429489 @default.
- W2897187502 cites W2519358758 @default.
- W2897187502 cites W2528234130 @default.
- W2897187502 cites W2528883599 @default.
- W2897187502 cites W2531151744 @default.
- W2897187502 cites W2560474170 @default.
- W2897187502 cites W2570848768 @default.
- W2897187502 cites W2586564970 @default.
- W2897187502 cites W2605973302 @default.
- W2897187502 cites W2616937431 @default.
- W2897187502 cites W2732252438 @default.
- W2897187502 cites W2734834614 @default.
- W2897187502 cites W2737602873 @default.
- W2897187502 cites W2740103755 @default.
- W2897187502 cites W2743674619 @default.
- W2897187502 cites W2750400961 @default.
- W2897187502 cites W2752912576 @default.
- W2897187502 cites W2753064086 @default.
- W2897187502 cites W2765232003 @default.
- W2897187502 cites W2769743454 @default.
- W2897187502 cites W2777300582 @default.
- W2897187502 cites W2777985721 @default.
- W2897187502 cites W2778252923 @default.
- W2897187502 cites W2788159735 @default.
- W2897187502 cites W2793037070 @default.
- W2897187502 cites W2798644314 @default.
- W2897187502 cites W2798702867 @default.
- W2897187502 cites W2798730128 @default.
- W2897187502 cites W2896416928 @default.
- W2897187502 cites W2963076553 @default.
- W2897187502 cites W2963150697 @default.
- W2897187502 cites W2963192057 @default.
- W2897187502 cites W2963221612 @default.
- W2897187502 cites W2963898179 @default.