Search Results for author: Kobus Barnard

Found 13 papers, 6 papers with code

Nowcasting-Nets: Deep Neural Network Structures for Precipitation Nowcasting Using IMERG

1 code implementation16 Aug 2021 Mohammad Reza Ehsani, Ariyan Zarei, Hoshin V. Gupta, Kobus Barnard, Ali Behrangi

However, the development of such a system is complicated by the chaotic nature of the atmosphere, and the consequent rapid changes that can occur in the structures of precipitation systems In this work, we develop two approaches (hereafter referred to as Nowcasting-Nets) that use Recurrent and Convolutional deep neural network structures to address the challenge of precipitation nowcasting.

Modular Procedural Generation for Voxel Maps

no code implementations18 Apr 2021 Adarsh Pyarelal, Aditya Banerjee, Kobus Barnard

The benefits of this approach include rapid, scalable, and efficient development of virtual environments, the ability to control the statistics of the environment at a semantic level, and the ability to generate novel environments in response to player actions in real time.

Attentional Local Contrast Networks for Infrared Small Target Detection

2 code implementations15 Dec 2020 Yimian Dai, Yiquan Wu, Fei Zhou, Kobus Barnard

To mitigate the issue of minimal intrinsic features for pure data-driven methods, in this paper, we propose a novel model-driven deep network for infrared small target detection, which combines discriminative networks and conventional model-driven methods to make use of both labeled data and the domain knowledge.

Asymmetric Contextual Modulation for Infrared Small Target Detection

2 code implementations30 Sep 2020 Yimian Dai, Yiquan Wu, Fei Zhou, Kobus Barnard

Single-frame infrared small target detection remains a challenge not only due to the scarcity of intrinsic target characteristics but also because of lacking a public dataset.

Attentional Feature Fusion

2 code implementations29 Sep 2020 Yimian Dai, Fabian Gieseke, Stefan Oehmcke, Yiquan Wu, Kobus Barnard

Feature fusion, the combination of features from different layers or branches, is an omnipresent part of modern network architectures.

Image Classification

Attention as Activation

1 code implementation15 Jul 2020 Yimian Dai, Stefan Oehmcke, Fabian Gieseke, Yiquan Wu, Kobus Barnard

Inspired by their similarity, we propose a novel type of activation units called attentional activation (ATAC) units as a unification of activation functions and attention mechanisms.

Multiple-gaze geometry: Inferring novel 3D locations from gazes observed in monocular video

no code implementations ECCV 2018 Ernesto Brau, Jinyan Guan, Tanya Jeffries, Kobus Barnard

We provide a Bayesian generative model for the temporal scene that captures the joint probability of camera parameters, locations of people, their gaze, what they are looking at, and locations of visual attention.

Association Scene Understanding +1

Branching Gaussian Processes with Applications to Spatiotemporal Reconstruction of 3D Trees

no code implementations14 Aug 2016 Kyle Simek, Ravishankar Palanivelu, Kobus Barnard

We propose a new general-purpose prior, a branching Gaussian processes (BGP), that models spatial smoothness and temporal dynamics of curves while enforcing attachment between them.

3D Reconstruction Gaussian Processes

A Statistical Model for Recreational Trails in Aerial Images

no code implementations CVPR 2013 Andrew Predoehl, Scott Morris, Kobus Barnard

We present a statistical model of aerial images of recreational trails, and a method to infer trail routes in such images.

Learning models of object structure

no code implementations NeurIPS 2009 Joseph Schlecht, Kobus Barnard

Model topologies are learned across groups of images, and one or more such topologies is linked to an object category (e. g. chairs).

Cannot find the paper you are looking for? You can Submit a new open access paper.