Search Results for author: Zahra Gharaee

Found 15 papers, 9 papers with code

Video Relationship Detection Using Mixture of Experts

1 code implementation IEEE Access 2023 Ala Shaabana, Zahra Gharaee, Paul Fieguth

Secondly, classifiers trained by a single, monolithic neural network often lack stability and generalization.

Action Recognition Object +4

Disentanglement in Implicit Causal Models via Switch Variable

no code implementations16 Feb 2024 Shayan Shirahmad Gale Bagi, Zahra Gharaee, Oliver Schulte, Mark Crowley

Learning causal representations from observational and interventional data in the absence of known ground-truth graph structures necessitates implicit latent causal representation learning.

Disentanglement

Memory-Efficient Continual Learning Object Segmentation for Long Video

no code implementations26 Sep 2023 Amir Nazemi, Mohammad Javad Shafiee, Zahra Gharaee, Paul Fieguth

We propose two novel techniques to reduce the memory requirement of Online VOS methods while improving modeling accuracy and generalization on long videos.

Continual Learning Object +4

Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting

1 code implementation17 Feb 2023 Shayan Shirahmad Gale Bagi, Zahra Gharaee, Oliver Schulte, Mark Crowley

First, we propose a novel causal model that explains the generative factors in motion forecasting datasets using features that are common across all environments and with features that are specific to each environment.

Motion Forecasting Representation Learning +2

Self-supervised learning of object pose estimation using keypoint prediction

no code implementations14 Feb 2023 Zahra Gharaee, Felix Järemo Lawin, Per-Erik Forssén

We designed a network to generate a proxy ground-truth heatmap from a set of keypoints distributed all over the category-specific mean shape, where each is represented by a unique color on a labeled texture.

Pose Estimation Pose Prediction +1

Machine Learning Challenges of Biological Factors in Insect Image Data

no code implementations4 Nov 2022 Nicholas Pellegrino, Zahra Gharaee, Paul Fieguth

The BIOSCAN project, led by the International Barcode of Life Consortium, seeks to study changes in biodiversity on a global scale.

Predicting the intended action using internal simulation of perception

no code implementations9 Feb 2022 Zahra Gharaee

Based on the experiments of this article, applying internally simulated perceptual states represented by action pattern vectors improves the performance of the recognition task in all experiments.

Future prediction

Graph Representation Learning for Road Type Classification

1 code implementation16 Jul 2021 Zahra Gharaee, Shreyas Kowshik, Oliver Stromann, Michael Felsberg

We present a novel learning-based approach to graph representations of road networks employing state-of-the-art graph convolutional neural networks.

Classification Descriptive +3

Action in Mind: A Neural Network Approach to Action Recognition and Segmentation

no code implementations30 Apr 2021 Zahra Gharaee

The proposed action recognition architecture of this thesis is composed of several processing layers including a preprocessing layer, an ordered vector representation layer and three layers of neural networks.

Action Recognition Action Segmentation +3

Online recognition of unsegmented actions with hierarchical SOM architecture

1 code implementation23 Apr 2021 Zahra Gharaee

Automatic recognition of an online series of unsegmented actions requires a method for segmentation that determines when an action starts and when it ends.

Hierarchical growing grid networks for skeleton based action recognition

1 code implementation22 Apr 2021 Zahra Gharaee

Apart from two layers of growing grid networks the architecture is composed of a preprocessing layer, an ordered vector representation layer and a one-layer supervised neural network.

Action Recognition Skeleton Based Action Recognition

First and Second Order Dynamics in a Hierarchical SOM system for Action Recognition

1 code implementation13 Apr 2021 Zahra Gharaee, Peter Gärdenfors, Magnus Johnsson

Human recognition of the actions of other humans is very efficient and is based on patterns of movements.

Action Recognition

Online Recognition of Actions Involving Objects

1 code implementation13 Apr 2021 Zahra Gharaee, Peter Gärdenfors, Magnus Johnsson

The second information processing stream is carried out by a second system that determines which object among several in the agent's vicinity the action is applied to.

Action Recognition

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