Sort by: Year Popularity Relevance

Weakly Supervised Temporal Action Localization Using Deep Metric Learning

,  - 2020

Temporal action localization is an important step towards video understanding. Most current action localization methods depend on untrimmed videos with full temporal annotations of action instances. However, it is expensive and time-consuming to annotate both action labels and temporal boundaries of videos. To this end, we propose a weakly superv...


BiOnt: Deep Learning using Multiple Biomedical Ontologies for Relation Extraction

,  - 2020

Successful biomedical relation extraction can provide evidence to researchers and clinicians about possible unknown associations between biomedical entities, advancing the current knowledge we have about those entities and their inherent mechanisms. Most biomedical relation extraction systems do not resort to external sources of knowledge, such a...


Improving GANs for Speech Enhancement

, , , , , ,  - 2020

Generative adversarial networks (GAN) have recently been shown to be efficient for speech enhancement. Most, if not all, existing speech enhancement GANs (SEGANs) make use of a single generator to perform one-stage enhancement mapping. In this work, we propose two novel SEGAN frameworks, iterated SEGAN (ISEGAN) and deep SEGAN (DSEGAN). In the two...


Expected Information Maximization: Using the I-Projection for Mixture Density Estimation

, ,  - 2020

Modelling highly multi-modal data is a challenging problem in machine learning. Most algorithms are based on maximizing the likelihood, which corresponds to the M(oment)-projection of the data distribution to the model distribution. The M-projection forces the model to average over modes it cannot represent. In contrast, the I(information)-projec...


Adaptive Parameterization for Neural Dialogue Generation

, , , , ,  - 2020

Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting diverse conversations, its adaptability is rather limited and the model is hence prone to generate generic re...


Head and Tail Localization of C. elegans

, ,  - 2020

C. elegans is commonly used in neuroscience for behaviour analysis because of it's compact nervous system with well-described connectivity. Localizing the animal and distinguishing between its head and tail are important tasks to track the worm during behavioural assays and to perform quantitative analyses. We demonstrate a neural network based a...


Analysis of Gender Inequality In Face Recognition Accuracy

, , , , ,  - 2020

We present a comprehensive analysis of how and why face recognition accuracy differs between men and women. We show that accuracy is lower for women due to the combination of (1) the impostor distribution for women having a skew toward higher similarity scores, and (2) the genuine distribution for women having a skew toward lower similarity score...


Advbox: a toolbox to generate adversarial examples that fool neural networks

, , , , ,  - 2020

In recent years, neural networks have been extensively deployed for computer vision tasks, particularly visual classification problems, where new algorithms reported to achieve or even surpass the human performance. Recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturba...


Unpaired Multi-modal Segmentation via Knowledge Distillation

, , ,  - 2020

Multi-modal learning is typically performed with network architectures containing modality-specific layers and shared layers, utilizing co-registered images of different modalities. We propose a novel learning scheme for unpaired cross-modality image segmentation, with a highly compact architecture achieving superior segmentation accuracy. In our...


A Branching and Merging Convolutional Network with Homogeneous Filter Capsules

, ,  - 2020

We present a convolutional neural network design with additional branches after certain convolutions so that we can extract features with differing effective receptive fields and levels of abstraction. From each branch, we transform each of the final filters into a pair of homogeneous vector capsules. As the capsules are formed from entire filter...