The Experts below are selected from a list of 67674 Experts worldwide ranked by ideXlab platform

Sicheng Zhao - One of the best experts on this subject based on the ideXlab platform.

  • emotiongan unsupervised domain adaptation for learning Discrete Probability distributions of image emotions
    ACM Multimedia, 2018
    Co-Authors: Sicheng Zhao, Guiguang Ding, Xin Zhao, Kurt Keutzer
    Abstract:

    Deep neural networks have performed well on various benchmark vision tasks with large-scale labeled training data; however, such training data is expensive and time-consuming to obtain. Due to domain shift or dataset bias, directly transferring models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain often results in poor performance. In this paper, we consider the domain adaptation problem in image emotion recognition. Specifically, we study how to adapt the Discrete Probability distributions of image emotions from a source domain to a target domain in an unsupervised manner. We develop a novel adversarial model for emotion distribution learning, termed EmotionGAN, which alternately optimizes the Generative Adversarial Network (GAN) loss, semantic consistency loss, and regression loss. The EmotionGAN model can adapt source domain images such that they appear as if they were drawn from the target domain, while preserving the annotation information. Extensive experiments are conducted on the FlickrLDL and TwitterLDL datasets, and the results demonstrate the superiority of the proposed method as compared to state-of-the-art approaches.

  • ACM Multimedia - EmotionGAN: Unsupervised Domain Adaptation for Learning Discrete Probability Distributions of Image Emotions
    2018 ACM Multimedia Conference on Multimedia Conference - MM '18, 2018
    Co-Authors: Sicheng Zhao, Guiguang Ding, Xin Zhao, Kurt Keutzer
    Abstract:

    Deep neural networks have performed well on various benchmark vision tasks with large-scale labeled training data; however, such training data is expensive and time-consuming to obtain. Due to domain shift or dataset bias, directly transferring models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain often results in poor performance. In this paper, we consider the domain adaptation problem in image emotion recognition. Specifically, we study how to adapt the Discrete Probability distributions of image emotions from a source domain to a target domain in an unsupervised manner. We develop a novel adversarial model for emotion distribution learning, termed EmotionGAN, which alternately optimizes the Generative Adversarial Network (GAN) loss, semantic consistency loss, and regression loss. The EmotionGAN model can adapt source domain images such that they appear as if they were drawn from the target domain, while preserving the annotation information. Extensive experiments are conducted on the FlickrLDL and TwitterLDL datasets, and the results demonstrate the superiority of the proposed method as compared to state-of-the-art approaches.

  • Discrete Probability distribution prediction of image emotions with shared sparse learning
    IEEE Transactions on Affective Computing, 2018
    Co-Authors: Sicheng Zhao, Youbao Tang, Guiguang Ding, Xin Zhao, Qingming Huang
    Abstract:

    Computationally modelling the affective content of images has been extensively studied recently because of its wide applications in entertainment, advertisement, and education. Significant progress has been made on designing discriminative features to bridge the affective gap. Assuming that viewers can reach a consensus on the emotion of images, most existing works focused on assigning the dominant emotion category or the average dimension values to an image. However, the image emotions perceived by viewers are subjective by nature with the influence of personal and situational factors. In this paper, we propose a novel machine learning approach that characterizes the categorical image emotions as a Discrete Probability distribution (DPD). To associate emotion with the visual features extracted from images, we present shared sparse learning to learn the combination coefficients, with which the DPD of an unseen image is predicted by linearly combining the DPDs of the training images. Furthermore, we extend our method to the setup where multi-features are available and learn the optimal weights for each feature to reflect the importance of different features. Extensive experiments are carried out on Abstract, Emotion6 and IESN datasets and the results demonstrate the superiority of the proposed method, as compared to the state-of-the-art approaches.

  • approximating Discrete Probability distribution of image emotions by multi modal features fusion
    International Joint Conference on Artificial Intelligence, 2017
    Co-Authors: Sicheng Zhao, Guiguang Ding
    Abstract:

    Existing works on image emotion recognition mainly assigned the dominant emotion category or average dimension values to an image based on the assumption that viewers can reach a consensus on the emotion of images. However, the image emotions perceived by viewers are subjective by nature and highly related to the personal and situational factors. On the other hand, image emotions can be conveyed by different features, such as semantics and aesthetics. In this paper, we propose a novel machine learning approach that formulates the categorical image emotions as a Discrete Probability distribution (DPD). To associate emotions with the extracted visual features, we present a weighted multi-modal shared sparse leaning to learn the combination coefficients, with which the DPD of an unseen image can be predicted by linearly integrating the DPDs of the training images. The representation abilities of different modalities are jointly explored and the optimal weight of each modality is automatically learned. Extensive experiments on three datasets verify the superiority of the proposed method, as compared to the state-of-the-art.

  • IJCAI - Approximating Discrete Probability distribution of image emotions by multi-modal features fusion
    Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017
    Co-Authors: Sicheng Zhao, Guiguang Ding
    Abstract:

    Existing works on image emotion recognition mainly assigned the dominant emotion category or average dimension values to an image based on the assumption that viewers can reach a consensus on the emotion of images. However, the image emotions perceived by viewers are subjective by nature and highly related to the personal and situational factors. On the other hand, image emotions can be conveyed by different features, such as semantics and aesthetics. In this paper, we propose a novel machine learning approach that formulates the categorical image emotions as a Discrete Probability distribution (DPD). To associate emotions with the extracted visual features, we present a weighted multi-modal shared sparse leaning to learn the combination coefficients, with which the DPD of an unseen image can be predicted by linearly integrating the DPDs of the training images. The representation abilities of different modalities are jointly explored and the optimal weight of each modality is automatically learned. Extensive experiments on three datasets verify the superiority of the proposed method, as compared to the state-of-the-art.

Kurt Keutzer - One of the best experts on this subject based on the ideXlab platform.

  • emotiongan unsupervised domain adaptation for learning Discrete Probability distributions of image emotions
    ACM Multimedia, 2018
    Co-Authors: Sicheng Zhao, Guiguang Ding, Xin Zhao, Kurt Keutzer
    Abstract:

    Deep neural networks have performed well on various benchmark vision tasks with large-scale labeled training data; however, such training data is expensive and time-consuming to obtain. Due to domain shift or dataset bias, directly transferring models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain often results in poor performance. In this paper, we consider the domain adaptation problem in image emotion recognition. Specifically, we study how to adapt the Discrete Probability distributions of image emotions from a source domain to a target domain in an unsupervised manner. We develop a novel adversarial model for emotion distribution learning, termed EmotionGAN, which alternately optimizes the Generative Adversarial Network (GAN) loss, semantic consistency loss, and regression loss. The EmotionGAN model can adapt source domain images such that they appear as if they were drawn from the target domain, while preserving the annotation information. Extensive experiments are conducted on the FlickrLDL and TwitterLDL datasets, and the results demonstrate the superiority of the proposed method as compared to state-of-the-art approaches.

  • ACM Multimedia - EmotionGAN: Unsupervised Domain Adaptation for Learning Discrete Probability Distributions of Image Emotions
    2018 ACM Multimedia Conference on Multimedia Conference - MM '18, 2018
    Co-Authors: Sicheng Zhao, Guiguang Ding, Xin Zhao, Kurt Keutzer
    Abstract:

    Deep neural networks have performed well on various benchmark vision tasks with large-scale labeled training data; however, such training data is expensive and time-consuming to obtain. Due to domain shift or dataset bias, directly transferring models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain often results in poor performance. In this paper, we consider the domain adaptation problem in image emotion recognition. Specifically, we study how to adapt the Discrete Probability distributions of image emotions from a source domain to a target domain in an unsupervised manner. We develop a novel adversarial model for emotion distribution learning, termed EmotionGAN, which alternately optimizes the Generative Adversarial Network (GAN) loss, semantic consistency loss, and regression loss. The EmotionGAN model can adapt source domain images such that they appear as if they were drawn from the target domain, while preserving the annotation information. Extensive experiments are conducted on the FlickrLDL and TwitterLDL datasets, and the results demonstrate the superiority of the proposed method as compared to state-of-the-art approaches.

Guiguang Ding - One of the best experts on this subject based on the ideXlab platform.

  • emotiongan unsupervised domain adaptation for learning Discrete Probability distributions of image emotions
    ACM Multimedia, 2018
    Co-Authors: Sicheng Zhao, Guiguang Ding, Xin Zhao, Kurt Keutzer
    Abstract:

    Deep neural networks have performed well on various benchmark vision tasks with large-scale labeled training data; however, such training data is expensive and time-consuming to obtain. Due to domain shift or dataset bias, directly transferring models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain often results in poor performance. In this paper, we consider the domain adaptation problem in image emotion recognition. Specifically, we study how to adapt the Discrete Probability distributions of image emotions from a source domain to a target domain in an unsupervised manner. We develop a novel adversarial model for emotion distribution learning, termed EmotionGAN, which alternately optimizes the Generative Adversarial Network (GAN) loss, semantic consistency loss, and regression loss. The EmotionGAN model can adapt source domain images such that they appear as if they were drawn from the target domain, while preserving the annotation information. Extensive experiments are conducted on the FlickrLDL and TwitterLDL datasets, and the results demonstrate the superiority of the proposed method as compared to state-of-the-art approaches.

  • ACM Multimedia - EmotionGAN: Unsupervised Domain Adaptation for Learning Discrete Probability Distributions of Image Emotions
    2018 ACM Multimedia Conference on Multimedia Conference - MM '18, 2018
    Co-Authors: Sicheng Zhao, Guiguang Ding, Xin Zhao, Kurt Keutzer
    Abstract:

    Deep neural networks have performed well on various benchmark vision tasks with large-scale labeled training data; however, such training data is expensive and time-consuming to obtain. Due to domain shift or dataset bias, directly transferring models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain often results in poor performance. In this paper, we consider the domain adaptation problem in image emotion recognition. Specifically, we study how to adapt the Discrete Probability distributions of image emotions from a source domain to a target domain in an unsupervised manner. We develop a novel adversarial model for emotion distribution learning, termed EmotionGAN, which alternately optimizes the Generative Adversarial Network (GAN) loss, semantic consistency loss, and regression loss. The EmotionGAN model can adapt source domain images such that they appear as if they were drawn from the target domain, while preserving the annotation information. Extensive experiments are conducted on the FlickrLDL and TwitterLDL datasets, and the results demonstrate the superiority of the proposed method as compared to state-of-the-art approaches.

  • Discrete Probability distribution prediction of image emotions with shared sparse learning
    IEEE Transactions on Affective Computing, 2018
    Co-Authors: Sicheng Zhao, Youbao Tang, Guiguang Ding, Xin Zhao, Qingming Huang
    Abstract:

    Computationally modelling the affective content of images has been extensively studied recently because of its wide applications in entertainment, advertisement, and education. Significant progress has been made on designing discriminative features to bridge the affective gap. Assuming that viewers can reach a consensus on the emotion of images, most existing works focused on assigning the dominant emotion category or the average dimension values to an image. However, the image emotions perceived by viewers are subjective by nature with the influence of personal and situational factors. In this paper, we propose a novel machine learning approach that characterizes the categorical image emotions as a Discrete Probability distribution (DPD). To associate emotion with the visual features extracted from images, we present shared sparse learning to learn the combination coefficients, with which the DPD of an unseen image is predicted by linearly combining the DPDs of the training images. Furthermore, we extend our method to the setup where multi-features are available and learn the optimal weights for each feature to reflect the importance of different features. Extensive experiments are carried out on Abstract, Emotion6 and IESN datasets and the results demonstrate the superiority of the proposed method, as compared to the state-of-the-art approaches.

  • approximating Discrete Probability distribution of image emotions by multi modal features fusion
    International Joint Conference on Artificial Intelligence, 2017
    Co-Authors: Sicheng Zhao, Guiguang Ding
    Abstract:

    Existing works on image emotion recognition mainly assigned the dominant emotion category or average dimension values to an image based on the assumption that viewers can reach a consensus on the emotion of images. However, the image emotions perceived by viewers are subjective by nature and highly related to the personal and situational factors. On the other hand, image emotions can be conveyed by different features, such as semantics and aesthetics. In this paper, we propose a novel machine learning approach that formulates the categorical image emotions as a Discrete Probability distribution (DPD). To associate emotions with the extracted visual features, we present a weighted multi-modal shared sparse leaning to learn the combination coefficients, with which the DPD of an unseen image can be predicted by linearly integrating the DPDs of the training images. The representation abilities of different modalities are jointly explored and the optimal weight of each modality is automatically learned. Extensive experiments on three datasets verify the superiority of the proposed method, as compared to the state-of-the-art.

  • IJCAI - Approximating Discrete Probability distribution of image emotions by multi-modal features fusion
    Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017
    Co-Authors: Sicheng Zhao, Guiguang Ding
    Abstract:

    Existing works on image emotion recognition mainly assigned the dominant emotion category or average dimension values to an image based on the assumption that viewers can reach a consensus on the emotion of images. However, the image emotions perceived by viewers are subjective by nature and highly related to the personal and situational factors. On the other hand, image emotions can be conveyed by different features, such as semantics and aesthetics. In this paper, we propose a novel machine learning approach that formulates the categorical image emotions as a Discrete Probability distribution (DPD). To associate emotions with the extracted visual features, we present a weighted multi-modal shared sparse leaning to learn the combination coefficients, with which the DPD of an unseen image can be predicted by linearly integrating the DPDs of the training images. The representation abilities of different modalities are jointly explored and the optimal weight of each modality is automatically learned. Extensive experiments on three datasets verify the superiority of the proposed method, as compared to the state-of-the-art.

Xin Zhao - One of the best experts on this subject based on the ideXlab platform.

  • ACM Multimedia - EmotionGAN: Unsupervised Domain Adaptation for Learning Discrete Probability Distributions of Image Emotions
    2018 ACM Multimedia Conference on Multimedia Conference - MM '18, 2018
    Co-Authors: Sicheng Zhao, Guiguang Ding, Xin Zhao, Kurt Keutzer
    Abstract:

    Deep neural networks have performed well on various benchmark vision tasks with large-scale labeled training data; however, such training data is expensive and time-consuming to obtain. Due to domain shift or dataset bias, directly transferring models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain often results in poor performance. In this paper, we consider the domain adaptation problem in image emotion recognition. Specifically, we study how to adapt the Discrete Probability distributions of image emotions from a source domain to a target domain in an unsupervised manner. We develop a novel adversarial model for emotion distribution learning, termed EmotionGAN, which alternately optimizes the Generative Adversarial Network (GAN) loss, semantic consistency loss, and regression loss. The EmotionGAN model can adapt source domain images such that they appear as if they were drawn from the target domain, while preserving the annotation information. Extensive experiments are conducted on the FlickrLDL and TwitterLDL datasets, and the results demonstrate the superiority of the proposed method as compared to state-of-the-art approaches.

  • emotiongan unsupervised domain adaptation for learning Discrete Probability distributions of image emotions
    ACM Multimedia, 2018
    Co-Authors: Sicheng Zhao, Guiguang Ding, Xin Zhao, Kurt Keutzer
    Abstract:

    Deep neural networks have performed well on various benchmark vision tasks with large-scale labeled training data; however, such training data is expensive and time-consuming to obtain. Due to domain shift or dataset bias, directly transferring models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain often results in poor performance. In this paper, we consider the domain adaptation problem in image emotion recognition. Specifically, we study how to adapt the Discrete Probability distributions of image emotions from a source domain to a target domain in an unsupervised manner. We develop a novel adversarial model for emotion distribution learning, termed EmotionGAN, which alternately optimizes the Generative Adversarial Network (GAN) loss, semantic consistency loss, and regression loss. The EmotionGAN model can adapt source domain images such that they appear as if they were drawn from the target domain, while preserving the annotation information. Extensive experiments are conducted on the FlickrLDL and TwitterLDL datasets, and the results demonstrate the superiority of the proposed method as compared to state-of-the-art approaches.

  • Discrete Probability distribution prediction of image emotions with shared sparse learning
    IEEE Transactions on Affective Computing, 2018
    Co-Authors: Sicheng Zhao, Youbao Tang, Guiguang Ding, Xin Zhao, Qingming Huang
    Abstract:

    Computationally modelling the affective content of images has been extensively studied recently because of its wide applications in entertainment, advertisement, and education. Significant progress has been made on designing discriminative features to bridge the affective gap. Assuming that viewers can reach a consensus on the emotion of images, most existing works focused on assigning the dominant emotion category or the average dimension values to an image. However, the image emotions perceived by viewers are subjective by nature with the influence of personal and situational factors. In this paper, we propose a novel machine learning approach that characterizes the categorical image emotions as a Discrete Probability distribution (DPD). To associate emotion with the visual features extracted from images, we present shared sparse learning to learn the combination coefficients, with which the DPD of an unseen image is predicted by linearly combining the DPDs of the training images. Furthermore, we extend our method to the setup where multi-features are available and learn the optimal weights for each feature to reflect the importance of different features. Extensive experiments are carried out on Abstract, Emotion6 and IESN datasets and the results demonstrate the superiority of the proposed method, as compared to the state-of-the-art approaches.

P.p. Vaidyanathan - One of the best experts on this subject based on the ideXlab platform.

  • A multirate DSP model for estimation of Discrete Probability density functions
    IEEE Transactions on Signal Processing, 2005
    Co-Authors: Byung-jun Yoon, P.p. Vaidyanathan
    Abstract:

    The problem of estimating a Probability density function (PDF) from measurements has been widely studied by many researchers. Even though much work has been done in the area of PDF estimation, most of it was focused on the continuous case. We propose a new model-based approach for modeling and estimating Discrete Probability density functions or Probability mass functions. This approach is based on multirate signal processing theory, and it has several advantages over the conventional histogram method. We illustrate the PDF estimation procedure and analyze the statistical properties of the PDF estimates. Based on this model, a novel scheme is introduced that can be used for estimating the PDF in the presence of noise. Furthermore, the proposed ideas are extended to the more general case of estimating multivariate PDFs. Finally, we also consider practical issues such as optimizing the coefficients of a digital filter, which is an integral part of the model. This allows us to apply the proposed model to solve real-world problems. Simulation results are given where appropriate in order to demonstrate the ideas.

  • Improved estimation of Discrete Probability density functions using multirate models
    The Thrity-Seventh Asilomar Conference on Signals Systems & Computers 2003, 1
    Co-Authors: Byung-jun Yoon, P.p. Vaidyanathan
    Abstract:

    For many decades, the problem of estimating a pdf based on measurements has been of interest to many researchers. Even though much work has been done in the area of pdf estimation, most of it was focused on the continuous case. In this paper, we propose a new model based approach for estimating a Discrete Probability density function. This approach is based on multirate dsp theory, and it has several advantages over the traditional histogram method. It is shown that this method yields an unbiased pdf estimate with small variance, which is guaranteed to have a smaller estimation error than the histogram. Simulation results are given, which show the merit of the proposed method.