no code implementations • 26 Apr 2024 • Slawek Smyl, Boris N. Oreshkin, Paweł Pełka, Grzegorz Dudek
We show that our general approach can be seamlessly applied to two distinct neural architectures leading to the state-of-the-art distributional forecasting results in the context of short-term electricity demand forecasting task.
1 code implementation • 9 Feb 2023 • Boris N. Oreshkin
HybrIK relies on a combination of analytical inverse kinematics and deep learning to produce more accurate 3D pose estimation from 2D monocular images.
Ranked #22 on 3D Human Pose Estimation on 3DPW
1 code implementation • 16 Aug 2022 • Vikram Voleti, Boris N. Oreshkin, Florent Bocquelet, Félix G. Harvey, Louis-Simon Ménard, Christopher Pal
Inverse Kinematics (IK) systems are often rigid with respect to their input character, thus requiring user intervention to be adapted to new skeletons.
4 code implementations • 30 Jan 2022 • Cristian Challu, Kin G. Olivares, Boris N. Oreshkin, Federico Garza, Max Mergenthaler-Canseco, Artur Dubrawski
Recent progress in neural forecasting accelerated improvements in the performance of large-scale forecasting systems.
1 code implementation • 18 Jan 2022 • Boris N. Oreshkin, Antonios Valkanas, Félix G. Harvey, Louis-Simon Ménard, Florent Bocquelet, Mark J. Coates
We show that the task of synthesizing human motion conditioned on a set of key frames can be solved more accurately and effectively if a deep learning based interpolator operates in the delta mode using the spherical linear interpolator as a baseline.
Ranked #1 on Motion Synthesis on LaFAN1
no code implementations • 20 Sep 2021 • Philippe Chatigny, Shengrui Wang, Jean-Marc Patenaude, Boris N. Oreshkin
We study the problem of efficiently scaling ensemble-based deep neural networks for multi-step time series (TS) forecasting on a large set of time series.
1 code implementation • ICLR 2022 • Boris N. Oreshkin, Florent Bocquelet, Félix G. Harvey, Bay Raitt, Dominic Laflamme
Our work focuses on the development of a learnable neural representation of human pose for advanced AI assisted animation tooling.
no code implementations • 31 Dec 2020 • Boris N. Oreshkin
Regularization, also known in radar literature as sample covariance loading, can be used to combat both ill conditioning of the original problem and contamination of the empirical covariance by the desired signal for the adaptive algorithms based on sample covariance matrix inversion.
no code implementations • 9 Oct 2020 • Boris N. Oreshkin, Peter A. Bakulev
Adaptive algorithms based on sample matrix inversion belong to an important class of algorithms used in radar target detection to overcome prior uncertainty of interference covariance.
no code implementations • 2 Oct 2020 • Boris N. Oreshkin, Tal Arbel
This paper presents an approach to fast image registration through probabilistic pixel sampling.
no code implementations • 2 Oct 2020 • Boris N. Oreshkin, Tal Arbel
This paper presents a novel probabilistic voxel selection strategy for medical image registration in time-sensitive contexts, where the goal is aggressive voxel sampling (e. g. using less than 1% of the total number) while maintaining registration accuracy and low failure rate.
1 code implementation • 24 Sep 2020 • Boris N. Oreshkin, Grzegorz Dudek, Paweł Pełka, Ekaterina Turkina
We show that our proposed deep neural network modeling approach based on the deep neural architecture is effective at solving the mid-term electricity load forecasting problem.
1 code implementation • 30 Jul 2020 • Boris N. Oreshkin, Arezou Amini, Lucy Coyle, Mark J. Coates
Forecasting of multivariate time-series is an important problem that has applications in traffic management, cellular network configuration, and quantitative finance.
3 code implementations • 7 Feb 2020 • Boris N. Oreshkin, Dmitri Carpov, Nicolas Chapados, Yoshua Bengio
Can meta-learning discover generic ways of processing time series (TS) from a diverse dataset so as to greatly improve generalization on new TS coming from different datasets?
no code implementations • 26 Jan 2020 • Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin, Hengshuai Yao, Martin Jagersand
Our results show that few-shot segmentation benefits from utilizing word embeddings, and that we are able to perform few-shot segmentation using stacked joint visual semantic processing with weak image-level labels.
no code implementations • 18 Dec 2019 • Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin, Hengshuai Yao, Martin Jagersand
Conventional few-shot object segmentation methods learn object segmentation from a few labelled support images with strongly labelled segmentation masks.
no code implementations • 31 May 2019 • Boris N. Oreshkin, Negar Rostamzadeh, Pedro O. Pinheiro, Christopher Pal
We address the problem of learning fine-grained cross-modal representations.
18 code implementations • ICLR 2020 • Boris N. Oreshkin, Dmitri Carpov, Nicolas Chapados, Yoshua Bengio
We focus on solving the univariate times series point forecasting problem using deep learning.
Time Series Time-Series Few-Shot Learning with Heterogeneous Channels +1
1 code implementation • NeurIPS 2019 • Chen Xing, Negar Rostamzadeh, Boris N. Oreshkin, Pedro O. Pinheiro
Through a series of experiments, we show that by this adaptive combination of the two modalities, our model outperforms current uni-modality few-shot learning methods and modality-alignment methods by a large margin on all benchmarks and few-shot scenarios tested.
3 code implementations • NeurIPS 2018 • Boris N. Oreshkin, Pau Rodriguez, Alexandre Lacoste
We further propose a simple and effective way of conditioning a learner on the task sample set, resulting in learning a task-dependent metric space.