News
|
[June 2023] |
Joined Apple as MLR intern, working on diffusion models. |
[May 2022] |
"Hyperbolic Deep Learning in Computer Vision: A Survey" is available online. |
[Oct 2022] |
Organized a tutorial on Hyperbolic Representation Learning at ECCV 2022 |
[Sep 2022] |
Visited Mediterranean Machine Learning Summer School, got the best poster award. [Paper] |
[July 2022] |
Visited International Computer Vision Summer School in Sicily. [Paper] |
[May 2022] |
Hyperbolic Image Segmentation is accepted as oral presentation to NCCV2022. [Paper] |
[March 2022] |
Hyperbolic Image Segmentation is accepted to CVPR2022. [Paper] |
[Sep 2021] |
Hyperbolic Busemann Learning with Ideal Prototypes is accepted to NeurIPS2021. [Paper]
|
[Oct 2020] |
Joined VisLab as Ph.D. student. |
Research
I'm interested in computer vision and understanding images and videos. I'm interested in
exploring
images and video understanding in non-Euclidean spaces, such as hyperbolic space.
|
|
Hyperbolic Deep Learning in Computer Vision
Pascal Mettes,
Mina Ghadimi Atigh,
Martin Keller-Ressel,
Jeffrey Gu,
Serena Yeung
arXiv, 2023
arXiv
In this survey, We outline how hyperbolic learning is performed in all themes and discuss the main research problems that benefit from current advances in hyperbolic learning for computer vision.
|
|
Hyperbolic Image Segmentation
Mina Ghadimi Atigh,
Julian Schoep,
Erman Acar,
Nanne van Noord,
Pascal Mettes
CVPR, 2022
project page
/
arXiv
Hyperbolic Image Segmentation opens up new possibilities and practical benefits for
segmentation, such as uncertainty estimation and boundary information for free, zero-label
generalization, and increased performance in low-dimensional output embeddings.
|
|
Hyperbolic Busemann Learning with Ideal Prototypes
Mina Ghadimi Atigh,
Martin Keller-Ressel,
Pascal Mettes
NeurIPS, 2021
project page
/
Paper
/
arXiv
Where existing works on prototype-based learning in hyperbolic space requires prior knowledge
to operate, Hyperbolic Busemann Learning places prototypes at the ideal boundary of the
Poincar`e ball. This enables a prototype positioning without the need for prior
knowledge.
|
|
Convolutional Relational Machine for Group Activity Recognition
Sina Mokhtarzadeh Azar,
Mina Ghadimi Atigh,
Ahmad Nickabadi,
Alexandre Alahi
CVPR, 2019
project page
/
Paper
/
arXiv
We propose a Convolutional Relational Machine for group activity recognition by extracting
the relationships between persons. We show that the activity map is a useful representation
that effectively encodes the spatial relations.
|
|
A Multi-Stream Convolutional Neural Network Framework for Group Activity
Recognition
Sina Mokhtarzadeh Azar,
Mina Ghadimi Atigh,
Ahmad Nickabadi
arXiv, 2018
arXiv
In this paper, we presented multi-stream convolutional networks as a framework for group
activity recognition. In this framework, new modalities both in spatial and temporal domains
can be easily plugged in to improve the model’s power.
|
|
Zoom-RNN: A Novel Method for Person Recognition Using Recurrent Neural
Networks
Sina Mokhtarzadeh Azar,
Sajjad Azami
Mina Ghadimi Atigh,
Mohammad Javadi,
Ahmad Nickabadi
Arxiv, 2018
arXiv
In this paper, we proposed a novel method for combining cues of different body regions for
the task of person recognition in photo album. Our approach uses two distinct recurrent
neural networks to extract information present in different parts of a human photo in order
to improve recognition performance.
|
Teaching Assistance
|
[September 2023] |
Applied Machine Learning |
[September 2022] |
Applied Machine Learning |
[September 2021] |
Applied Machine Learning |
[September 2020] |
Applied Machine Learning |
Thanks Jon for the template!
|
|