The Experts below are selected from a list of 264 Experts worldwide ranked by ideXlab platform

Jian Zhang - One of the best experts on this subject based on the ideXlab platform.

  • Deep learning for robust outdoor vehicle visual tracking
    2017 IEEE International Conference on Multimedia and Expo (ICME), 2017
    Co-Authors: Xing Du, Jian Zhang
    Abstract:

    Robust visual tracking for outdoor vehicle is still a challenging problem due to large appearance variations caused by illumination variation, occlusion and scale variation, etc. In this paper, a deep-learning-based approach for robust outdoor vehicle tracking is proposed. Firstly, a stacked denoising auto-encoder is pre-trained to learn the feature representation way of images. Then, a k-sparse constraint is added to the stacked denoising auto-encoder and the encoder of k-sparse stacked denoising auto-encoder (kSSDAE) is connected with a Classification layer to construct a Classification Neural Network. After fine-tuning, the Classification Neural Network is applied to online tracking under particle filter framework. Extensive tracking experiments are conducted on a challenging single object online tracking evaluation platform benchmark to verify the effectiveness of our tracker. Experiments show that our tracker outperforms most state-of-the-art trackers.

  • ICME - Deep learning for robust outdoor vehicle visual tracking
    2017 IEEE International Conference on Multimedia and Expo (ICME), 2017
    Co-Authors: Xing Du, Jian Zhang
    Abstract:

    Robust visual tracking for outdoor vehicle is still a challenging problem due to large appearance variations caused by illumination variation, occlusion and scale variation, etc. In this paper, a deep-learning-based approach for robust outdoor vehicle tracking is proposed. Firstly, a stacked denoising auto-encoder is pre-trained to learn the feature representation way of images. Then, a k-sparse constraint is added to the stacked denoising auto-encoder and the encoder of k-sparse stacked denoising auto-encoder (kSSDAE) is connected with a Classification layer to construct a Classification Neural Network. After fine-tuning, the Classification Neural Network is applied to online tracking under particle filter framework. Extensive tracking experiments are conducted on a challenging single object online tracking evaluation platform benchmark to verify the effectiveness of our tracker. Experiments show that our tracker outperforms most state-of-the-art trackers.

S. Nariani - One of the best experts on this subject based on the ideXlab platform.

  • A two-dimensional shift invariant image Classification Neural Network which overcomes the stability/plasticity dilemma
    1990 IJCNN International Joint Conference on Neural Networks, 1990
    Co-Authors: B.l. Pulito, T.r. Damarla, S. Nariani
    Abstract:

    A Neural Network for two-dimensional visual pattern learning and Classification is outlined. The new architecture combines the important aspects of two previously developed Network designs, simultaneously taking advantage of the unique properties of both. The structure of the Neocognitron Network is incorporated to allow shift-invariant and partial scale-invariant recognition, while the top-down attentional and matching mechanisms found in the adaptive resonance theory (ART) model are used to solve the stability-plasticity dilemma. The new Network is self-organizing, shift invariant and able to switch automatically between its stable and plastic modes. Computer simulation results for a group of edge extracted patterns are detailed. The Neural design uses viable Neural mechanisms similar to those thought to exist in biological Neural systems

  • IJCNN - A two-dimensional shift invariant image Classification Neural Network which overcomes the stability/plasticity dilemma
    1990 IJCNN International Joint Conference on Neural Networks, 1990
    Co-Authors: B.l. Pulito, T.r. Damarla, S. Nariani
    Abstract:

    A Neural Network for two-dimensional visual pattern learning and Classification is outlined. The new architecture combines the important aspects of two previously developed Network designs, simultaneously taking advantage of the unique properties of both. The structure of the Neocognitron Network is incorporated to allow shift-invariant and partial scale-invariant recognition, while the top-down attentional and matching mechanisms found in the adaptive resonance theory (ART) model are used to solve the stability-plasticity dilemma. The new Network is self-organizing, shift invariant and able to switch automatically between its stable and plastic modes. Computer simulation results for a group of edge extracted patterns are detailed. The Neural design uses viable Neural mechanisms similar to those thought to exist in biological Neural systems

Xing Du - One of the best experts on this subject based on the ideXlab platform.

  • Deep learning for robust outdoor vehicle visual tracking
    2017 IEEE International Conference on Multimedia and Expo (ICME), 2017
    Co-Authors: Xing Du, Jian Zhang
    Abstract:

    Robust visual tracking for outdoor vehicle is still a challenging problem due to large appearance variations caused by illumination variation, occlusion and scale variation, etc. In this paper, a deep-learning-based approach for robust outdoor vehicle tracking is proposed. Firstly, a stacked denoising auto-encoder is pre-trained to learn the feature representation way of images. Then, a k-sparse constraint is added to the stacked denoising auto-encoder and the encoder of k-sparse stacked denoising auto-encoder (kSSDAE) is connected with a Classification layer to construct a Classification Neural Network. After fine-tuning, the Classification Neural Network is applied to online tracking under particle filter framework. Extensive tracking experiments are conducted on a challenging single object online tracking evaluation platform benchmark to verify the effectiveness of our tracker. Experiments show that our tracker outperforms most state-of-the-art trackers.

  • ICME - Deep learning for robust outdoor vehicle visual tracking
    2017 IEEE International Conference on Multimedia and Expo (ICME), 2017
    Co-Authors: Xing Du, Jian Zhang
    Abstract:

    Robust visual tracking for outdoor vehicle is still a challenging problem due to large appearance variations caused by illumination variation, occlusion and scale variation, etc. In this paper, a deep-learning-based approach for robust outdoor vehicle tracking is proposed. Firstly, a stacked denoising auto-encoder is pre-trained to learn the feature representation way of images. Then, a k-sparse constraint is added to the stacked denoising auto-encoder and the encoder of k-sparse stacked denoising auto-encoder (kSSDAE) is connected with a Classification layer to construct a Classification Neural Network. After fine-tuning, the Classification Neural Network is applied to online tracking under particle filter framework. Extensive tracking experiments are conducted on a challenging single object online tracking evaluation platform benchmark to verify the effectiveness of our tracker. Experiments show that our tracker outperforms most state-of-the-art trackers.

B.l. Pulito - One of the best experts on this subject based on the ideXlab platform.

  • A two-dimensional shift invariant image Classification Neural Network which overcomes the stability/plasticity dilemma
    1990 IJCNN International Joint Conference on Neural Networks, 1990
    Co-Authors: B.l. Pulito, T.r. Damarla, S. Nariani
    Abstract:

    A Neural Network for two-dimensional visual pattern learning and Classification is outlined. The new architecture combines the important aspects of two previously developed Network designs, simultaneously taking advantage of the unique properties of both. The structure of the Neocognitron Network is incorporated to allow shift-invariant and partial scale-invariant recognition, while the top-down attentional and matching mechanisms found in the adaptive resonance theory (ART) model are used to solve the stability-plasticity dilemma. The new Network is self-organizing, shift invariant and able to switch automatically between its stable and plastic modes. Computer simulation results for a group of edge extracted patterns are detailed. The Neural design uses viable Neural mechanisms similar to those thought to exist in biological Neural systems

  • IJCNN - A two-dimensional shift invariant image Classification Neural Network which overcomes the stability/plasticity dilemma
    1990 IJCNN International Joint Conference on Neural Networks, 1990
    Co-Authors: B.l. Pulito, T.r. Damarla, S. Nariani
    Abstract:

    A Neural Network for two-dimensional visual pattern learning and Classification is outlined. The new architecture combines the important aspects of two previously developed Network designs, simultaneously taking advantage of the unique properties of both. The structure of the Neocognitron Network is incorporated to allow shift-invariant and partial scale-invariant recognition, while the top-down attentional and matching mechanisms found in the adaptive resonance theory (ART) model are used to solve the stability-plasticity dilemma. The new Network is self-organizing, shift invariant and able to switch automatically between its stable and plastic modes. Computer simulation results for a group of edge extracted patterns are detailed. The Neural design uses viable Neural mechanisms similar to those thought to exist in biological Neural systems

Dit-yan Yeung - One of the best experts on this subject based on the ideXlab platform.

  • Learning a Deep Compact Image Representation for Visual Tracking
    Advances in neural information processing systems, 2013
    Co-Authors: Naiyan Wang, Dit-yan Yeung
    Abstract:

    In this paper, we study the challenging problem of tracking the trajectory of a moving object in a video with possibly very complex background. In contrast to most existing trackers which only learn the appearance of the tracked object online, we take a different approach, inspired by recent advances in deep learning architectures, by putting more emphasis on the (unsupervised) feature learning problem. Specifically, by using auxiliary natural images, we train a stacked denoising autoencoder offline to learn generic image features that are more robust against variations. This is then followed by knowledge transfer from offline training to the online tracking process. Online tracking involves a Classification Neural Network which is constructed from the encoder part of the trained autoencoder as a feature extractor and an additional Classification layer. Both the feature extractor and the classifier can be further tuned to adapt to appearance changes of the moving object. Comparison with the state-of-the-art trackers on some challenging benchmark video sequences shows that our deep learning tracker is more accurate while maintaining low computational cost with real-time performance when our MATLAB implementation of the tracker is used with a modest graphics processing unit (GPU).