The Experts below are selected from a list of 67878 Experts worldwide ranked by ideXlab platform

Luc Van Gool - One of the best experts on this subject based on the ideXlab platform.

  • spatio temporal Channel Correlation networks for action classification
    European Conference on Computer Vision, 2018
    Co-Authors: Ali Diba, Mohsen Fayyaz, Vivek Sharma, Mohammad Mahdi Arzani, Rahman Yousefzadeh, Juergen Gall, Luc Van Gool
    Abstract:

    The work in this paper is driven by the question if spatio-temporal Correlations are enough for 3D convolutional neural networks (CNN)? Most of the traditional 3D networks use local spatio-temporal features. We introduce a new block that models Correlations between Channels of a 3D CNN with respect to temporal and spatial features. This new block can be added as a residual unit to different parts of 3D CNNs. We name our novel block ‘Spatio-Temporal Channel Correlation’ (STC). By embedding this block to the current state-of-the-art architectures such as ResNext and ResNet, we improve the performance by 2–3% on the Kinetics dataset. Our experiments show that adding STC blocks to current state-of-the-art architectures outperforms the state-of-the-art methods on the HMDB51, UCF101 and Kinetics datasets. The other issue in training 3D CNNs is about training them from scratch with a huge labeled dataset to get a reasonable performance. So the knowledge learned in 2D CNNs is completely ignored. Another contribution in this work is a simple and effective technique to transfer knowledge from a pre-trained 2D CNN to a randomly initialized 3D CNN for a stable weight initialization. This allows us to significantly reduce the number of training samples for 3D CNNs. Thus, by fine-tuning this network, we beat the performance of generic and recent methods in 3D CNNs, which were trained on large video datasets, e.g. Sports-1M, and fine-tuned on the target datasets, e.g. HMDB51/UCF101.

  • spatio temporal Channel Correlation networks for action classification
    arXiv: Computer Vision and Pattern Recognition, 2018
    Co-Authors: Ali Diba, Mohsen Fayyaz, Vivek Sharma, Mohammad Mahdi Arzani, Rahman Yousefzadeh, Juergen Gall, Luc Van Gool
    Abstract:

    The work in this paper is driven by the question if spatio-temporal Correlations are enough for 3D convolutional neural networks (CNN)? Most of the traditional 3D networks use local spatio-temporal features. We introduce a new block that models Correlations between Channels of a 3D CNN with respect to temporal and spatial features. This new block can be added as a residual unit to different parts of 3D CNNs. We name our novel block 'Spatio-Temporal Channel Correlation' (STC). By embedding this block to the current state-of-the-art architectures such as ResNext and ResNet, we improved the performance by 2-3\% on Kinetics dataset. Our experiments show that adding STC blocks to current state-of-the-art architectures outperforms the state-of-the-art methods on the HMDB51, UCF101 and Kinetics datasets. The other issue in training 3D CNNs is about training them from scratch with a huge labeled dataset to get a reasonable performance. So the knowledge learned in 2D CNNs is completely ignored. Another contribution in this work is a simple and effective technique to transfer knowledge from a pre-trained 2D CNN to a randomly initialized 3D CNN for a stable weight initialization. This allows us to significantly reduce the number of training samples for 3D CNNs. Thus, by fine-tuning this network, we beat the performance of generic and recent methods in 3D CNNs, which were trained on large video datasets, e.g. Sports-1M, and fine-tuned on the target datasets, e.g. HMDB51/UCF101.

Xiaohu Yu - One of the best experts on this subject based on the ideXlab platform.

  • subspace based noise variance and snr estimation for ofdm systems mobile radio applications
    Wireless Communications and Networking Conference, 2005
    Co-Authors: Xiaodong Xu, Ya Jing, Xiaohu Yu
    Abstract:

    Noise variance and hence signal to noise ratio (SNR) estimates are very important for the Channel quality control in communication systems. Noting that in mobile communications the multipath time delays are slowly varying in time, in this paper we derive a subspace-based estimation method for orthogonal frequency division multiplexing (OFDM) systems, which is based on an eigenvector decomposition of the estimated Channel Correlation matrix. Simulation results show that the proposed estimator can obtain accurate real time measurements of the noise variance and SNR after an observation interval of about 20 OFDM symbols for various fading Channels.

Xiaodong Xu - One of the best experts on this subject based on the ideXlab platform.

  • subspace based noise variance and snr estimation for mimo ofdm systems
    Journal of Electronics (china), 2006
    Co-Authors: Xiaodong Xu, Ya Jing, Junhui Zhao, Xiaohu You
    Abstract:

    This paper proposes a subspace-based noise variance and Signal-to-Noise Ratio (SNR) estimation algorithm for Multi-Input Multi-Output (MIMO) wireless Orthogonal Frequency Division Multiplexing (OFDM) systems. The special training sequences with the property of orthogonality and phase shift orthogonality are used in pilot tones to obtain the estimated Channel Correlation matrix. Partitioning the observation space into a delay subspace and a noise subspace, we achieve the measurement of noise variance and SNR. Simulation results show that the proposed estimator can obtain accurate and real-time measurements of the noise variance and SNR for various multipath fading Channels, demonstrating its strong robustness against different Channels.

  • subspace based noise variance and snr estimation for ofdm systems mobile radio applications
    Wireless Communications and Networking Conference, 2005
    Co-Authors: Xiaodong Xu, Ya Jing, Xiaohu Yu
    Abstract:

    Noise variance and hence signal to noise ratio (SNR) estimates are very important for the Channel quality control in communication systems. Noting that in mobile communications the multipath time delays are slowly varying in time, in this paper we derive a subspace-based estimation method for orthogonal frequency division multiplexing (OFDM) systems, which is based on an eigenvector decomposition of the estimated Channel Correlation matrix. Simulation results show that the proposed estimator can obtain accurate real time measurements of the noise variance and SNR after an observation interval of about 20 OFDM symbols for various fading Channels.

Ali Diba - One of the best experts on this subject based on the ideXlab platform.

  • spatio temporal Channel Correlation networks for action classification
    European Conference on Computer Vision, 2018
    Co-Authors: Ali Diba, Mohsen Fayyaz, Vivek Sharma, Mohammad Mahdi Arzani, Rahman Yousefzadeh, Juergen Gall, Luc Van Gool
    Abstract:

    The work in this paper is driven by the question if spatio-temporal Correlations are enough for 3D convolutional neural networks (CNN)? Most of the traditional 3D networks use local spatio-temporal features. We introduce a new block that models Correlations between Channels of a 3D CNN with respect to temporal and spatial features. This new block can be added as a residual unit to different parts of 3D CNNs. We name our novel block ‘Spatio-Temporal Channel Correlation’ (STC). By embedding this block to the current state-of-the-art architectures such as ResNext and ResNet, we improve the performance by 2–3% on the Kinetics dataset. Our experiments show that adding STC blocks to current state-of-the-art architectures outperforms the state-of-the-art methods on the HMDB51, UCF101 and Kinetics datasets. The other issue in training 3D CNNs is about training them from scratch with a huge labeled dataset to get a reasonable performance. So the knowledge learned in 2D CNNs is completely ignored. Another contribution in this work is a simple and effective technique to transfer knowledge from a pre-trained 2D CNN to a randomly initialized 3D CNN for a stable weight initialization. This allows us to significantly reduce the number of training samples for 3D CNNs. Thus, by fine-tuning this network, we beat the performance of generic and recent methods in 3D CNNs, which were trained on large video datasets, e.g. Sports-1M, and fine-tuned on the target datasets, e.g. HMDB51/UCF101.

  • spatio temporal Channel Correlation networks for action classification
    arXiv: Computer Vision and Pattern Recognition, 2018
    Co-Authors: Ali Diba, Mohsen Fayyaz, Vivek Sharma, Mohammad Mahdi Arzani, Rahman Yousefzadeh, Juergen Gall, Luc Van Gool
    Abstract:

    The work in this paper is driven by the question if spatio-temporal Correlations are enough for 3D convolutional neural networks (CNN)? Most of the traditional 3D networks use local spatio-temporal features. We introduce a new block that models Correlations between Channels of a 3D CNN with respect to temporal and spatial features. This new block can be added as a residual unit to different parts of 3D CNNs. We name our novel block 'Spatio-Temporal Channel Correlation' (STC). By embedding this block to the current state-of-the-art architectures such as ResNext and ResNet, we improved the performance by 2-3\% on Kinetics dataset. Our experiments show that adding STC blocks to current state-of-the-art architectures outperforms the state-of-the-art methods on the HMDB51, UCF101 and Kinetics datasets. The other issue in training 3D CNNs is about training them from scratch with a huge labeled dataset to get a reasonable performance. So the knowledge learned in 2D CNNs is completely ignored. Another contribution in this work is a simple and effective technique to transfer knowledge from a pre-trained 2D CNN to a randomly initialized 3D CNN for a stable weight initialization. This allows us to significantly reduce the number of training samples for 3D CNNs. Thus, by fine-tuning this network, we beat the performance of generic and recent methods in 3D CNNs, which were trained on large video datasets, e.g. Sports-1M, and fine-tuned on the target datasets, e.g. HMDB51/UCF101.

Georgios B Giannakis - One of the best experts on this subject based on the ideXlab platform.

  • ICASSP (4) - Differential space-time modulation with transmit-beamforming for correlated MIMO fading Channels
    2003 IEEE International Conference on Acoustics Speech and Signal Processing 2003. Proceedings. (ICASSP '03)., 2003
    Co-Authors: Georgios B Giannakis
    Abstract:

    While the knowledge of each Channel realization is not available in a system with differential space-time modulation, Channel Correlation can be easily estimated without training at the receiver, and exploited by the transmitter to enhance the error probability performance. We develop a transmission scheme that combines transmit-beamforming with differential space-time modulation based on orthogonal space-time block coding. Error probability is analyzed for both correlated and independent Channels. Based on the error probability analysis, we derive power loading coefficients to improve performance.