Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890144450> ?p ?o ?g. }
- W2890144450 endingPage "1021" @default.
- W2890144450 startingPage "1011" @default.
- W2890144450 abstract "Continuous gesture recognition aims at recognizing the ongoing gestures from continuous gesture sequences and is more meaningful for the scenarios, where the start and end frames of each gesture instance are generally unknown in practical applications. This paper presents an effective deep architecture for continuous gesture recognition. First, continuous gesture sequences are segmented into isolated gesture instances using the proposed temporal dilated Res3D network. A balanced squared hinge loss function is proposed to deal with the imbalance between boundaries and nonboundaries. Temporal dilation can preserve the temporal information for the dense detection of the boundaries at fine granularity, and the large temporal receptive field makes the segmentation results more reasonable and effective. Then, the recognition network is constructed based on the 3-D convolutional neural network (3DCNN), the convolutional long-short-term-memory network (ConvLSTM), and the 2-D convolutional neural network (2DCNN) for isolated gesture recognition. The “3DCNN-ConvLSTM-2DCNN” architecture is more effective to learn long-term and deep spatiotemporal features. The proposed segmentation and recognition networks obtain the Jaccard index of 0.7163 on the Chalearn LAP ConGD dataset, which is 0.106 higher than the winner of 2017 ChaLearn LAP Large-Scale Continuous Gesture Recognition Challenge." @default.
- W2890144450 created "2018-09-27" @default.
- W2890144450 creator A5001104491 @default.
- W2890144450 creator A5009750573 @default.
- W2890144450 creator A5028794275 @default.
- W2890144450 creator A5049303874 @default.
- W2890144450 creator A5060136500 @default.
- W2890144450 creator A5077947981 @default.
- W2890144450 date "2019-04-01" @default.
- W2890144450 modified "2023-10-16" @default.
- W2890144450 title "Continuous Gesture Segmentation and Recognition Using 3DCNN and Convolutional LSTM" @default.
- W2890144450 cites W1969595749 @default.
- W2890144450 cites W1985891935 @default.
- W2890144450 cites W2123254310 @default.
- W2890144450 cites W2174874265 @default.
- W2890144450 cites W2254019339 @default.
- W2890144450 cites W2301789900 @default.
- W2890144450 cites W2471695703 @default.
- W2890144450 cites W2475715656 @default.
- W2890144450 cites W2513281263 @default.
- W2890144450 cites W2519328139 @default.
- W2890144450 cites W2550143307 @default.
- W2890144450 cites W2593722617 @default.
- W2890144450 cites W2595328592 @default.
- W2890144450 cites W2604113307 @default.
- W2890144450 cites W2607014458 @default.
- W2890144450 cites W2607799870 @default.
- W2890144450 cites W2609582631 @default.
- W2890144450 cites W2609984075 @default.
- W2890144450 cites W2739107216 @default.
- W2890144450 cites W2751125921 @default.
- W2890144450 cites W2751445731 @default.
- W2890144450 cites W2752803734 @default.
- W2890144450 cites W2755876276 @default.
- W2890144450 cites W2765354204 @default.
- W2890144450 cites W2767624150 @default.
- W2890144450 cites W2769039400 @default.
- W2890144450 cites W2769602762 @default.
- W2890144450 cites W2770472008 @default.
- W2890144450 cites W2771248633 @default.
- W2890144450 cites W2791276322 @default.
- W2890144450 cites W2798498022 @default.
- W2890144450 cites W2962766910 @default.
- W2890144450 cites W2962850830 @default.
- W2890144450 cites W2963192057 @default.
- W2890144450 cites W2963247196 @default.
- W2890144450 cites W2963524571 @default.
- W2890144450 cites W2964184470 @default.
- W2890144450 cites W2964214371 @default.
- W2890144450 cites W2964216094 @default.
- W2890144450 cites W2964216549 @default.
- W2890144450 cites W3100481960 @default.
- W2890144450 cites W586264567 @default.
- W2890144450 cites W639708223 @default.
- W2890144450 cites W790225446 @default.
- W2890144450 doi "https://doi.org/10.1109/tmm.2018.2869278" @default.
- W2890144450 hasPublicationYear "2019" @default.
- W2890144450 type Work @default.
- W2890144450 sameAs 2890144450 @default.
- W2890144450 citedByCount "61" @default.
- W2890144450 countsByYear W28901444502019 @default.
- W2890144450 countsByYear W28901444502020 @default.
- W2890144450 countsByYear W28901444502021 @default.
- W2890144450 countsByYear W28901444502022 @default.
- W2890144450 countsByYear W28901444502023 @default.
- W2890144450 crossrefType "journal-article" @default.
- W2890144450 hasAuthorship W2890144450A5001104491 @default.
- W2890144450 hasAuthorship W2890144450A5009750573 @default.
- W2890144450 hasAuthorship W2890144450A5028794275 @default.
- W2890144450 hasAuthorship W2890144450A5049303874 @default.
- W2890144450 hasAuthorship W2890144450A5060136500 @default.
- W2890144450 hasAuthorship W2890144450A5077947981 @default.
- W2890144450 hasConcept C108583219 @default.
- W2890144450 hasConcept C147168706 @default.
- W2890144450 hasConcept C153180895 @default.
- W2890144450 hasConcept C154945302 @default.
- W2890144450 hasConcept C159437735 @default.
- W2890144450 hasConcept C203519979 @default.
- W2890144450 hasConcept C207347870 @default.
- W2890144450 hasConcept C28490314 @default.
- W2890144450 hasConcept C31972630 @default.
- W2890144450 hasConcept C41008148 @default.
- W2890144450 hasConcept C50644808 @default.
- W2890144450 hasConcept C81363708 @default.
- W2890144450 hasConcept C89600930 @default.
- W2890144450 hasConceptScore W2890144450C108583219 @default.
- W2890144450 hasConceptScore W2890144450C147168706 @default.
- W2890144450 hasConceptScore W2890144450C153180895 @default.
- W2890144450 hasConceptScore W2890144450C154945302 @default.
- W2890144450 hasConceptScore W2890144450C159437735 @default.
- W2890144450 hasConceptScore W2890144450C203519979 @default.
- W2890144450 hasConceptScore W2890144450C207347870 @default.
- W2890144450 hasConceptScore W2890144450C28490314 @default.
- W2890144450 hasConceptScore W2890144450C31972630 @default.
- W2890144450 hasConceptScore W2890144450C41008148 @default.
- W2890144450 hasConceptScore W2890144450C50644808 @default.
- W2890144450 hasConceptScore W2890144450C81363708 @default.
- W2890144450 hasConceptScore W2890144450C89600930 @default.