194 citations · 649 across the 42 of their papers we have counts for
8 papers · 1 filter
3D Human Pose and Shape Estimation via HybrIK-Transformer
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. HybrIK has three major compo…
ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics
Boris N. Oreshkin, Florent Bocquelet, Félix G. Harvey +2
Our work focuses on the development of a learnable neural representation of human pose for advanced AI assisted animation tooling. Specifically, we tackle the problem of constructi…
Optimization over Random and Gradient Probabilistic Pixel Sampling for Fast, Robust Multi-Resolution Image Registration
Boris N. Oreshkin, Tal Arbel
This paper presents an approach to fast image registration through probabilistic pixel sampling. We propose a practical scheme to leverage the benefits of two state-of-the-art pixe…
Uncertainty driven probabilistic voxel selection for image registration
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. usin…
Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings
Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin +2
Significant progress has been made recently in developing few-shot object segmentation methods. Learning is shown to be successful in few-shot segmentation settings, using pixel-le…
One-Shot Weakly Supervised Video Object Segmentation
Mennatullah Siam, Naren Doraiswamy, Boris N. Oreshkin +2
Conventional few-shot object segmentation methods learn object segmentation from a few labelled support images with strongly labelled segmentation masks. Recent work has shown to p…
CLAREL: Classification via retrieval loss for zero-shot learning
Boris N. Oreshkin, Negar Rostamzadeh, Pedro O. Pinheiro +1
We address the problem of learning fine-grained cross-modal representations. We propose an instance-based deep metric learning approach in joint visual and textual space. The key n…
Adaptive Masked Proxies for Few-Shot Segmentation
Mennatullah Siam, Boris Oreshkin, Martin Jagersand
Deep learning has thrived by training on large-scale datasets. However, in robotics applications sample efficiency is critical. We propose a novel adaptive masked proxies method th…