4.4k citations
- Queen Mary University of LondonGB2 papers
- Universidad Carlos III de MadridES2 papers
- Arizona State UniversityUS1 paper
- Artificial Intelligence Research InstituteES1 paper
- Centre d'Études et d'Expertise sur les Risques, l'Environnement, la Mobilité et l'AménagementFR1 paper
- Clínica Las CondesCL1 paper
- Imperial College LondonGB1 paper
- Institut de Recherche en Informatique de ToulouseFR1 paper
- Institution of Engineering and TechnologyGB1 paper
- Meta Vision Systems (United Kingdom)GB1 paper
- Politécnico Colombiano Jaime Isaza CadavidCO1 paper
- Roche (France)FR1 paper
6 papers
Real-time tracker with fast recovery from target loss
Alessandro Bay, Panagiotis Sidiropoulos, Eduard Vazquez +1
In this paper, we introduce a variation of a state-of-the-art real-time tracker (CFNet), which adds to the original algorithm robustness to target loss without a significant comput…
Learning to Recognize 3D Human Action from A New Skeleton-based Representation Using Deep Convolutional Neural Networks
Huy-Hieu Pham, Louahdi Khoudour, Alain Crouzil +2
Recognizing human actions in untrimmed videos is an important challenging task. An effective 3D motion representation and a powerful learning model are two key factors influencing…
Convolutional Recurrent Predictor: Implicit Representation for Multi-target Filtering and Tracking
Mehryar Emambakhsh, Alessandro Bay, Eduard Vazquez
Defining a multi-target motion model, which is an important step of tracking algorithms, can be very challenging. Using fixed models (as in several generative Bayesian algorithms,…
Motorcycle detection and classification in urban Scenarios using a model based on Faster R-CNN
Jorge E. Espinosa, Sergio A. Velastin, John W. Branch
This paper introduces a Deep Learning Convolutional Neural Network model based on Faster-RCNN for motorcycle detection and classification on urban environments. The model is evalua…
A Brief Survey of Deep Reinforcement Learning
Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage +1
Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual wor…
Differential Geometric Retrieval of Deep Features
Y Qian, E Vazquez, B Sengupta
Comparing images to recommend items from an image-inventory is a subject of continued interest. Added with the scalability of deep-learning architectures the once `manual' job of h…