Related papers: SL-DML: Signal Level Deep Metric Learning for Mult…

Image modality recognition is essential for efficient imaging workflows in current clinical environments, where multiple imaging modalities are used to better comprehend complex diseases. Emerging biomarkers from novel, rare modalities are…

We describe a novel metric-based learning approach that introduces a multimodal framework and uses deep audio and geophone encoders in siamese configuration to design an adaptable and lightweight supervised model. This framework eliminates…

There has been a remarkable progress in learning a model which could recognise novel classes with only a few labeled examples in the last few years. Few-shot learning (FSL) for action recognition is a challenging task of recognising novel…

Deep embeddings answer one simple question: How similar are two images? Learning these embeddings is the bedrock of verification, zero-shot learning, and visual search. The most prominent approaches optimize a deep convolutional network…

Zero-shot learning (ZSL) aims to recognize the novel object categories using the semantic representation of categories, and the key idea is to explore the knowledge of how the novel class is semantically related to the familiar classes.…

In this work, we present a novel approach to multi-view action recognition where we guide learned action representations to be separated from view-relevant information in a video. When trying to classify action instances captured from…

Recognition of objects with subtle differences has been used in many practical applications, such as car model recognition and maritime vessel identification. For discrimination of the objects in fine-grained detail, we focus on deep…

Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training…

The use of a few examples for each class to train a predictive model that can be generalized to novel classes is a crucial and valuable research direction in artificial intelligence. This work addresses this problem by proposing a few-shot…

One-shot learning is usually tackled by using generative models or discriminative embeddings. Discriminative methods based on deep learning, which are very effective in other learning scenarios, are ill-suited for one-shot learning as they…

Unlike areas such as computer vision and speech recognition where convolutional and recurrent neural networks-based approaches have proven effective to the nature of the respective areas of application, deep learning (DL) still lacks a…

3D Human Motion Indexing and Retrieval is an interesting problem due to the rise of several data-driven applications aimed at analyzing and/or re-utilizing 3D human skeletal data, such as data-driven animation, analysis of sports…

Human activity recognition is one of the most important tasks in computer vision and has proved useful in different fields such as healthcare, sports training and security. There are a number of approaches that have been explored to solve…

We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real-time systems. We…

We propose a novel distance-based regularization method for deep metric learning called Multi-level Distance Regularization (MDR). MDR explicitly disturbs a learning procedure by regularizing pairwise distances between embedding vectors…

One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale skeleton action…

Remote magnetic sensing can be used to monitor the position of objects in real-time, enabling ground transport monitoring, underground infrastructure mapping and hazardous detection. However, magnetic signals are typically weak and complex,…

Sound event detection is to infer the event by understanding the surrounding environmental sounds. Due to the scarcity of rare sound events, it becomes challenging for the well-trained detectors which have learned too much prior knowledge.…

Zero-shot learning (ZSL) models rely on learning a joint embedding space where both textual/semantic description of object classes and visual representation of object images can be projected to for nearest neighbour search. Despite the…

With the remarkable success achieved by the Convolutional Neural Networks (CNNs) in object recognition recently, deep learning is being widely used in the computer vision community. Deep Metric Learning (DML), integrating deep learning with…