Search Results for author: Yalda Mohsenzadeh

Found 14 papers, 4 papers with code

Multi-modal News Understanding with Professionally Labelled Videos (ReutersViLNews)

no code implementations23 Jan 2024 Shih-Han Chou, Matthew Kowal, Yasmin Niknam, Diana Moyano, Shayaan Mehdi, Richard Pito, Cheng Zhang, Ian Knopke, Sedef Akinli Kocak, Leonid Sigal, Yalda Mohsenzadeh

Towards a solution for designing this ability in algorithms, we present a large-scale analysis on an in-house dataset collected by the Reuters News Agency, called Reuters Video-Language News (ReutersViLNews) dataset which focuses on high-level video-language understanding with an emphasis on long-form news.

Miscellaneous Video Description

Look-Ahead Selective Plasticity for Continual Learning of Visual Tasks

1 code implementation2 Nov 2023 Rouzbeh Meshkinnejad, Jie Mei, Daniel Lizotte, Yalda Mohsenzadeh

Contrastive representation learning has emerged as a promising technique for continual learning as it can learn representations that are robust to catastrophic forgetting and generalize well to unseen future tasks.

Continual Learning Representation Learning

Anomaly Detection with Adversarially Learned Perturbations of Latent Space

no code implementations3 Jul 2022 Vahid Reza Khazaie, Anthony Wong, John Taylor Jewell, Yalda Mohsenzadeh

The Adversarial Distorter is a convolutional encoder that learns to produce effective perturbations and the autoencoder is a deep convolutional neural network that aims to reconstruct the images from the perturbed latent feature space.

Unsupervised Anomaly Detection

Augment to Detect Anomalies with Continuous Labelling

no code implementations3 Jul 2022 Vahid Reza Khazaie, Anthony Wong, Yalda Mohsenzadeh

Therefore, training a regressor on these augmented samples will result in more separable distributions of labels for normal and real anomalous data points.

Anomaly Detection Image Augmentation

Controlling Memorability of Face Images

no code implementations24 Feb 2022 Mohammad Younesi, Yalda Mohsenzadeh

In our proposed method, we first found a hyperplane in the latent space of StyleGAN to separate high and low memorable images.

Attribute

The Impact of Spatiotemporal Augmentations on Self-Supervised Audiovisual Representation Learning

no code implementations13 Oct 2021 Haider Al-Tahan, Yalda Mohsenzadeh

Hence, we extensively investigate composition of temporal augmentations suitable for learning audiovisual representations; we find lossy spatio-temporal transformations that do not corrupt the temporal coherency of videos are the most effective.

Contrastive Learning Representation Learning +1

CONTROLLING THE MEMORABILITY OF REAL AND UNREAL FACE IMAGES

no code implementations29 Sep 2021 Mohammad Younesi, Yalda Mohsenzadeh

In our proposed method, we first find a hyperplane in the latent space of StyleGAN to separate high and low memorable images.

Attribute

OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection

1 code implementation27 Mar 2021 John Taylor Jewell, Vahid Reza Khazaie, Yalda Mohsenzadeh

In particular, context autoencoders have been successful in the novelty detection task because of the more effective representations they learn by reconstructing original images from randomly masked images.

Anomaly Detection Novelty Detection

CLAR: Contrastive Learning of Auditory Representations

no code implementations19 Oct 2020 Haider Al-Tahan, Yalda Mohsenzadeh

We illustrate that by combining all these methods and with substantially less labeled data, our framework (CLAR) achieves significant improvement on prediction performance compared to supervised approach.

Contrastive Learning Self-Supervised Learning

Latent Vector Recovery of Audio GANs

no code implementations16 Oct 2020 Andrew Keyes, Nicky Bayat, Vahid Reza Khazaie, Yalda Mohsenzadeh

Through our deep neural network based method of training on real and synthesized audio, we are able to predict a latent vector that corresponds to a reasonable reconstruction of real audio.

Inverse mapping of face GANs

1 code implementation11 Sep 2020 Nicky Bayat, Vahid Reza Khazaie, Yalda Mohsenzadeh

The vast majority of studies on latent vector recovery perform well only on generated images, we argue that our method can be used to determine a mapping between real human faces and latent-space vectors that contain most of the important face style details.

Low Resolution Face Recognition Using a Two-Branch Deep Convolutional Neural Network Architecture

no code implementations20 Jun 2017 Erfan Zangeneh, Mohammad Rahmati, Yalda Mohsenzadeh

We propose a novel couple mappings method for low resolution face recognition using deep convolutional neural networks (DCNNs).

Face Recognition Super-Resolution

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