75 citations · 88 across the 11 of their papers we have counts for
13 papers
Loss-Invariant Projections as Passive Probes of Learned Representations
Akshay Chandrasekhar, Pavlo Melnyk
Learned feature representations in neural networks often contain structure beyond that directly used by the final task output. We study this structure using $\textit{passive probes…
CQF-HMR: Continuous Quaternion Flows for Probabilistic 3D Human Mesh Recovery from a Single Image
Cuong Le, Bao-Long Tran, Pavlo Melnyk +3
Recovering 3D digital humans from a single 2D image is an ill-posed computer vision problem due to the loss of depth information. Probabilistic 3D human pose estimation compensates…
Benchmark Dataset for Catalysis on 2D MXenes
Pavlo Melnyk, Anmar Karmush, Mårten Wadenbäck +4
Merging first-principles calculations with machine learning (ML), we aim to accelerate the exploration of catalytic behaviour in novel materials. We focus on two-dimensional (2D) T…
QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture
Cuong Le, Pavlo Melnyk, Urs Waldmann +2
Vision-based 3D human motion capture from videos remains a challenge in computer vision. Traditional 3D pose estimation approaches often ignore the temporal consistency between fra…
Flow Matching for Probabilistic Monocular 3D Human Pose Estimation
Cuong Le, Pavlo Melnyk, Bastian Wandt +1
Recovering 3D human poses from a monocular camera view is a highly ill-posed problem due to the depth ambiguity. Earlier studies on 3D human pose lifting from 2D often contain inco…
On the Role of Rotation Equivariance in Monocular 2D-to-3D Human Pose Lifting
Pavlo Melnyk, Cuong Le, Urs Waldmann +2
We consider monocular 3D human pose estimation (HPE), where the goal is to predict 3D human skeletal joints from a single 2D image, typically via 2D keypoint detection followed by…
ICML 2023 Topological Deep Learning Challenge : Design and Results
Mathilde Papillon, Mustafa Hajij, Helen Jenne +53
This paper presents the computational challenge on topological deep learning that was hosted within the ICML 2023 Workshop on Topology and Geometry in Machine Learning. The competi…
Learning to Augment: Hallucinating Data for Domain Generalized Segmentation
Qiyu Sun, Pavlo Melnyk, Michael Felsberg +1
Domain generalized semantic segmentation (DGSS) is an essential but highly challenging task, in which the model is trained only on source data and any target data is not available.…
O Learning Deep O()-Equivariant Hyperspheres
Pavlo Melnyk, Michael Felsberg, Mårten Wadenbäck +2
In this paper, we utilize hyperspheres and regular -simplexes and propose an approach to learning deep features equivariant under the transformations of D reflections and rot…
TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis
Pavlo Melnyk, Andreas Robinson, Michael Felsberg +1
In many practical applications, 3D point cloud analysis requires rotation invariance. In this paper, we present a learnable descriptor invariant under 3D rotations and reflections,…
Steerable 3D Spherical Neurons
Pavlo Melnyk, Michael Felsberg, Mårten Wadenbäck
Emerging from low-level vision theory, steerable filters found their counterpart in prior work on steerable convolutional neural networks equivariant to rigid transformations. In o…
Embed Me If You Can: A Geometric Perceptron
Pavlo Melnyk, Michael Felsberg, Mårten Wadenbäck
Solving geometric tasks involving point clouds by using machine learning is a challenging problem. Standard feed-forward neural networks combine linear or, if the bias parameter is…
A High-Performance CNN Method for Offline Handwritten Chinese Character Recognition and Visualization
Pavlo Melnyk, Zhiqiang You, Keqin Li
Recent researches introduced fast, compact and efficient convolutional neural networks (CNNs) for offline handwritten Chinese character recognition (HCCR). However, many of them di…