Recent Submissions

  • Channel Quality Aware Active Queue Management 

    SCHORMANS, JA; Computer Science and Electronic Engineering (CEEC), 2017 (IEEE, 2017-11)
    Queue management plays an important role in the performance of IP based networks and cellular networks in particular where large buffers are often deployed in order to absorb bursts resulting from the dynamic nature of the ...
  • Transfer learning for music classification and regression tasks 

    CHOI, K; FAZEKAS, G; SANDLER, M; kyunghyun, C; The 18th International Society of Music Information Retrieval (ISMIR) Conference (International Society of Music Information, 2017)
    In this paper, we present a transfer learning approach for music classification and regression tasks. We propose to use a pre-trained convnet feature, a concatenated feature vector using the activations of feature maps ...
  • Computational Models of Miscommunication Phenomena 

    PURVER, MRJ; HOUGH, J; HOWES, C (Wiley, 2018-03)
    Miscommunication phenomena such as repair in dialogue are important indicators of the quality of communication. Automatic detection is therefore a key step toward tools that can characterize communication quality and thus ...
  • Polyphonic Music Sequence Transduction with Meter-Constrained LSTM Networks 

    YCART, A; BENETOS, E; IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE International Conference on Acoustics, Speech and Signal Processing, 2018)
    Automatic transcription of polyphonic music remains a challenging task in the field of Music Information Retrieval. In this paper, we propose a new method to post-process the output of a multi-pitch detection model using ...
  • Deep globally constrained MRFs for Human Pose Estimation 

    MARRAS, I; PALASEK, P; PATRAS, I; IEEE International Conference on Computer Vision (ICCV) (IEEE, 2017-12)
    This work introduces a novel Convolutional Network architecture (ConvNet) for the task of human pose estimation, that is the localization of body joints in a single static image. We propose a coarse to fine architecture ...
Return to top