Abstract

Abstract

Abstract

Abstract
This study explored the viability of out-the-box, pre-trained ConvNet models as a tool to generate features for large-scale classification tasks. A juxtaposition with generative methods for vocabulary generation was drawn. Both methods were chosen in an attempt to integrate other datasets (transfer learning) and unlabelled data, respectively. Both methods were used together, studying the viability of a ConvNet model to estimate category labels of unlabelled images. All experiments pertaining to this study were carried out over a two-class set, later expanded into a 5-category dataset. The pre-trained models used were obtained from the Caffe Model Zoo. The study showed that the pre-trained model achieved best results for the binary dataset, with an accuracy of 0.945. However, for the 5-class dataset, generative vocabularies outperformed the ConvNet (0.91 vs. 0.861). Furthermore, when replacing labelled images with unlabelled ones during training, acceptable accuracy scores were obtained (as high as 0.903). Additionally, it was observed that linear kernels perform particularly well when utilized with generative models. This was especially relevant when compared to ConvNets, which require days of training even when utilizing multiple GPUs for computations.

Abstract
Developing robust and universal methods for unsupervised segmentation of moving objects in video sequences has proved to be a hard and challenging task. The best solutions are, in general, computationally heavy preventing their use in real-time applications. This research addresses this problem by proposing a robust and computationally efficient method, BMOG, that significantly boosts the performance of the widely used MOG2 method. The complexity of BMOG is kept low, proving its suitability for real-time applications. The proposed solution explores a novel classification mechanism that combines color space discrimination capabilities with hysteresis and a dynamic learning rate for background model update.

Abstract
In this paper we present the INESC Key Detection (IKD) system which incorporates a novel method for dynamically biasing key mode estimation using the spatial displacement of beat-synchronous Tonal Interval Vectors (TIVs). We evaluate the performance of the IKD system at finding the global key on three annotated audio datasets and using three key-defining profiles. Results demonstrate the effectiveness of the mode bias in favoring either the major or minor mode, thus allowing users to fine tune this variable to improve correct key estimates on style-specific music datasets or to balance predictions across key modes on unknown input sources.