no code implementations • 26 Apr 2024 • Anubhav Bhatti, Prithila Angkan, Behnam Behinaein, Zunayed Mahmud, Dirk Rodenburg, Heather Braund, P. James Mclellan, Aaron Ruberto, Geoffery Harrison, Daryl Wilson, Adam Szulewski, Dan Howes, Ali Etemad, Paul Hungler
In contrast, for LOSO, the best performance is achieved by the deep learning model with ECG, EDA, and EEG.
no code implementations • 23 Apr 2024 • Vandad Davoodnia, Saeed Ghorbani, Marc-André Carbonneau, Alexandre Messier, Ali Etemad
At the core of our method, a pose compiler module refines predictions from a 2D keypoints estimator that operates on a single image by leveraging temporal and cross-view information.
no code implementations • 19 Apr 2024 • Vandad Davoodnia, Saeed Ghorbani, Alexandre Messier, Ali Etemad
Next, we design a regression-based inverse-kinematic skeletal transformer that maps the joint positions to pose and shape representations from heavily noisy observations.
no code implementations • 21 Mar 2024 • Shuvendu Roy, Chunjong Park, Aldi Fahrezi, Ali Etemad
FSCIL requires both stability and adaptability, i. e., preserving proficiency in previously learned tasks while learning new ones.
Ranked #2 on Few-Shot Class-Incremental Learning on CUB-200-2011
no code implementations • 14 Mar 2024 • Dimitris Spathis, Aaqib Saeed, Ali Etemad, Sana Tonekaboni, Stefanos Laskaridis, Shohreh Deldari, Chi Ian Tang, Patrick Schwab, Shyam Tailor
This non-archival index is not complete, as some accepted papers chose to opt-out of inclusion.
no code implementations • 25 Jan 2024 • Aaqib Saeed, Dimitris Spathis, JungWoo Oh, Edward Choi, Ali Etemad
We show that FHLR achieves significantly better performance when learning from noisy labels and achieves state-of-the-art by a large margin, with up to 19% accuracy improvement under symmetric and asymmetric noise.
no code implementations • 2 Dec 2023 • Renan A. Rojas-Gomez, Karan Singhal, Ali Etemad, Alex Bijamov, Warren R. Morningstar, Philip Andrew Mansfield
Existing data augmentation in self-supervised learning, while diverse, fails to preserve the inherent structure of natural images.
no code implementations • 12 Nov 2023 • Shuvendu Roy, Ali Etemad
ViewFX learns view-invariant features of expression using a proposed self-supervised contrastive loss which brings together different views of the same subject with a particular expression in the embedding space.
no code implementations • 23 Oct 2023 • Divij Gupta, Ali Etemad
Recent advances in deep learning have made it increasingly feasible to estimate heart rate remotely in smart environments by analyzing videos.
no code implementations • 9 Sep 2023 • Debaditya Shome, Ali Etemad
We propose EmoDistill, a novel speech emotion recognition (SER) framework that leverages cross-modal knowledge distillation during training to learn strong linguistic and prosodic representations of emotion from speech.
1 code implementation • 3 Sep 2023 • Mohsen Zand, Ali Etemad, Michael Greenspan
We use normalizing flows to parameterize the noisy data at any arbitrary step of the diffusion process and utilize it as the prior in the reverse diffusion process.
1 code implementation • 31 Aug 2023 • Mohsen Zand, Ali Etemad, Michael Greenspan
Our experiments on two challenging benchmark datasets, CMU Mocap and Human3. 6M, demonstrate that our proposed method is able to effectively model the sequence information for motion prediction and outperform other techniques to set a new state-of-the-art.
1 code implementation • 25 Aug 2023 • Debaditya Shome, Pritam Sarkar, Ali Etemad
In this work, we introduce Region-Disentangled Diffusion Model (RDDM), a novel diffusion model designed to capture the complex temporal dynamics of ECG.
no code implementations • 1 Aug 2023 • Dustin Pulver, Prithila Angkan, Paul Hungler, Ali Etemad
We pre-train our model using self-supervised masked autoencoding on emotion-related EEG datasets and use transfer learning with both frozen weights and fine-tuning to perform downstream cognitive load classification.
no code implementations • 7 Jul 2023 • Haleh Damirchi, Michael Greenspan, Ali Etemad
Quantitative results demonstrate the superiority of our proposed model over the current state-of-the-art, which consistently achieves the lowest error for 3 time horizons of 0. 5, 1. 0 and 1. 5 seconds.
1 code implementation • 6 Jul 2023 • Shuvendu Roy, Ali Etemad
Even though some prior works have focused on reducing the need for large amounts of labelled data using different unsupervised methods, another promising approach called active learning is barely explored in the context of FER.
1 code implementation • 26 Jun 2023 • Mahdiyar Molahasani, Ali Etemad, Michael Greenspan
A continual learning solution is proposed to address the out-of-distribution generalization problem for pedestrian detection.
no code implementations • 23 Jun 2023 • Mahdiyar Molahasani, Michael Greenspan, Ali Etemad
Next, we assert that by treating the learning of the Head and Tail as two separate and sequential steps, Continual Learning (CL) methods can effectively update the weights of the learner to learn the Tail without forgetting the Head.
no code implementations • 12 Jun 2023 • Sayantan Das, Mojtaba Kolahdouzi, Levent Özparlak, Will Hickie, Ali Etemad
We present a novel approach for the detection of deepfake videos using a pair of vision transformers pre-trained by a self-supervised masked autoencoding setup.
no code implementations • 11 Jun 2023 • Mojtaba Kolahdouzi, Ali Etemad
We present a novel approach to mitigate bias in facial expression recognition (FER) models.
1 code implementation • NeurIPS 2023 • Pritam Sarkar, Ahmad Beirami, Ali Etemad
Video self-supervised learning (VSSL) has made significant progress in recent years.
1 code implementation • 2 Jun 2023 • Shuvendu Roy, Ali Etemad
We propose UnMixMatch, a semi-supervised learning framework which can learn effective representations from unconstrained unlabelled data in order to scale up performance.
no code implementations • 2 Jun 2023 • Shuvendu Roy, Ali Etemad
While semi-supervised learning has shown promise in FER, most current methods from general computer vision literature have not been explored in the context of FER.
Facial Expression Recognition Facial Expression Recognition (FER) +1
2 code implementations • 1 Jun 2023 • Shuvendu Roy, Ali Etemad
Our approach improves the generalization of large foundation models when fine-tuned on downstream tasks in a few-shot setting.
Ranked #2 on Prompt Engineering on Oxford-IIIT Pet Dataset
no code implementations • 1 Jun 2023 • Divij Gupta, Ali Etemad
Remote Photoplethysmography (rPPG) is the process of estimating PPG from facial videos.
no code implementations • 19 May 2023 • Farhad Pourpanah, Chee Peng Lim, Ali Etemad, Q. M. Jonathan Wu
Firstly, SSL-ART adopts an unsupervised fuzzy ART network to create a number of prototype nodes using unlabeled samples.
no code implementations • 13 Apr 2023 • Sahar Soltanieh, Javad Hashemi, Ali Etemad
To further assess the performance of these methods on both In-Distribution (ID) and Out-of-Distribution (OOD) ECG data, we conduct cross-dataset training and testing experiments.
1 code implementation • 9 Apr 2023 • Prithila Angkan, Behnam Behinaein, Zunayed Mahmud, Anubhav Bhatti, Dirk Rodenburg, Paul Hungler, Ali Etemad
Through this paper, we introduce a novel driver cognitive load assessment dataset, CL-Drive, which contains Electroencephalogram (EEG) signals along with other physiological signals such as Electrocardiography (ECG) and Electrodermal Activity (EDA) as well as eye tracking data.
no code implementations • 14 Mar 2023 • Amirhossein Hajavi, Ali Etemad
With the ubiquity of smart devices that use speaker recognition (SR) systems as a means of authenticating individuals and personalizing their services, fairness of SR systems has becomes an important point of focus.
no code implementations • 10 Mar 2023 • Vandad Davoodnia, Ali Etemad
Moreover, we observe that increasing the number of temporal crops in the early stages of the network positively impacts the performance while pre-training the network in a self-supervised setting using a masked auto-encoder approach also further improves the results.
1 code implementation • 25 Feb 2023 • Guangyi Zhang, Ali Etemad
However, PLL methods have not yet been adopted for EEG representation learning or implemented for emotion recognition tasks.
no code implementations • 6 Feb 2023 • Amirhossein Hajavi, Ali Etemad
In this work, we propose a novel approach for deep audio representation learning using audio-visual data when the video modality is absent at inference.
no code implementations • 27 Nov 2022 • Shuvendu Roy, Ali Etemad
All these labelled samples are then used along with the unlabelled data throughout the training process.
1 code implementation • 25 Nov 2022 • Pritam Sarkar, Ali Etemad
First, masked data reconstruction is performed to learn modality-specific representations from audio and visual streams.
Ranked #1 on Self-Supervised Action Recognition on Kinetics-400
no code implementations • 13 Sep 2022 • Mojtaba Kolahdouzi, Alireza Sepas-Moghaddam, Ali Etemad
We perform extensive experiments on four large-scale in-the-wild facial expression datasets - namely AffectNet, FER2013, ExpW, and RAF-DB - and one lab-controlled dataset (CK+) to evaluate our approach.
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • 2 Sep 2022 • Shuvendu Roy, Ali Etemad
We present ConCur, a contrastive video representation learning method that uses curriculum learning to impose a dynamic sampling strategy in contrastive training.
no code implementations • 26 Aug 2022 • Setareh Rahimi Taghanaki, Michael Rainbow, Ali Etemad
We aim to develop a model that learns strong representations from accelerometer signals, in order to perform robust human activity classification, while reducing the model's reliance on class labels.
2 code implementations • 31 Jul 2022 • Shuvendu Roy, Ali Etemad
To reduce the reliance of deep neural solutions on labeled data, state-of-the-art semi-supervised methods have been proposed in the literature.
Facial Expression Recognition Facial Expression Recognition (FER) +1
no code implementations • 20 Jul 2022 • Gelareh Hajian, Evelyn Morin, Ali Etemad
We propose a novel method to accurately model the generated force under isotonic, isokinetic (quasi-dynamic), and fully dynamic conditions.
1 code implementation • 14 Jul 2022 • Mohsen Zand, Ali Etemad, Michael Greenspan
We present ObjectBox, a novel single-stage anchor-free and highly generalizable object detection approach.
1 code implementation • 18 Jun 2022 • Zunayed Mahmud, Paul Hungler, Ali Etemad
The eye region isolation is performed with a U-Net style network which we train using a synthetic dataset that contains eye region masks for the visible eyeball and the iris region.
no code implementations • 13 Jun 2022 • Vandad Davoodnia, Saeed Ghorbani, Ali Etemad
In-bed pose estimation has shown value in fields such as hospital patient monitoring, sleep studies, and smart homes.
no code implementations • 9 Jun 2022 • Anubhav Bhatti, Behnam Behinaein, Paul Hungler, Ali Etemad
We perform extensive experiments on three public multimodal wearable datasets, WESAD, SWELL-KW, and CASE, and demonstrate that our method can effectively regulate and share information between different modalities to learn better representations.
no code implementations • 1 Jun 2022 • Leyla Khaleghi, Joshua Marshall, Ali Etemad
3D hand pose estimation (HPE) is the process of locating the joints of the hand in 3D from any visual input.
no code implementations • 30 May 2022 • Sahar Soltanieh, Ali Etemad, Javad Hashemi
For instance, when adding Gaussian noise, a sigma in the range of 0. 1 to 0. 2 achieves better results, while poor training occurs when the added noise is too small or too large (outside of the specified range).
1 code implementation • 13 May 2022 • Pritam Sarkar, Aaron Posen, Ali Etemad
We introduce AVCAffe, the first Audio-Visual dataset consisting of Cognitive load and Affect attributes.
1 code implementation • 21 Feb 2022 • Mohsen Zand, Haleh Damirchi, Andrew Farley, Mahdiyar Molahasani, Michael Greenspan, Ali Etemad
As the detection and localization tasks are well-correlated and can be jointly tackled, our model benefits from a multitask solution by learning multiscale representations of encoded crowd images, and subsequently fusing them.
1 code implementation • 11 Feb 2022 • Guangyi Zhang, Vandad Davoodnia, Ali Etemad
To reduce the potential distribution mismatch between the large amounts of unlabeled data and the limited amount of labeled data, PARSE uses pairwise representation alignment.
no code implementations • 15 Dec 2021 • Zunayed Mahmud, Paul Hungler, Ali Etemad
We first create a synthetic dataset containing eye region masks detailing the visible eyeball and iris using a simulator.
no code implementations • 5 Dec 2021 • Mojtaba Kolahdouzi, Alireza Sepas-Moghaddam, Ali Etemad
We propose an end-to-end architecture for facial expression recognition.
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • 2 Dec 2021 • Shashi Suman, Francois Rivest, Ali Etemad
In this paper, we propose a Bayesian Reinforcement learning framework that can approximate the current occupant state in a partially observable smart home environment using its thermal preference, and then identify the occupant as a new user or someone is already known to the system.
Hierarchical Reinforcement Learning reinforcement-learning +1
1 code implementation • 9 Nov 2021 • Pritam Sarkar, Ali Etemad
We present CrissCross, a self-supervised framework for learning audio-visual representations.
Ranked #1 on Audio Classification on DCASE
no code implementations • 24 Sep 2021 • Guangyi Zhang, Ali Etemad
Recently, supervised methods, which often require substantial amounts of class labels, have achieved promising results for EEG representation learning.
1 code implementation • 24 Sep 2021 • Leyla Khaleghi, Alireza Sepas Moghaddam, Joshua Marshall, Ali Etemad
Recent works have shown that videos or multi-view images carry rich information regarding the hand, allowing for the development of more robust HPE systems.
no code implementations • 1 Sep 2021 • Setareh Rahimi Taghanaki, Michael Rainbow, Ali Etemad
To develop a system capable of classifying running styles using wearables, we collect a dataset from 10 healthy runners performing 8 different pre-defined running styles.
no code implementations • 22 Aug 2021 • Behnam Behinaein, Anubhav Bhatti, Dirk Rodenburg, Paul Hungler, Ali Etemad
Electrocardiogram (ECG) has been widely used for emotion recognition.
no code implementations • 15 Aug 2021 • Shuvendu Roy, Ali Etemad
The model is then fine-tuned with labeled data in a supervised setting.
no code implementations • 6 Aug 2021 • Shuvendu Roy, Ali Etemad
Experiments are performed on the Oulu-CASIA dataset and the performance is compared to other works in FER.
no code implementations • 4 Aug 2021 • Anubhav Bhatti, Behnam Behinaein, Dirk Rodenburg, Paul Hungler, Ali Etemad
Classification of human emotions can play an essential role in the design and improvement of human-machine systems.
no code implementations • 28 Jul 2021 • Guangyi Zhang, Ali Etemad
We evaluate our framework using both a stacked autoencoder and an attention-based recurrent autoencoder.
1 code implementation • CVPR 2021 • Alireza Sepas-Moghaddam, Fernando Pereira, Paulo Lobato Correia, Ali Etemad
We validate the performance of our proposed architecture in the context of two multi-perspective visual recognition tasks namely lip reading and face recognition.
no code implementations • 30 Apr 2021 • Guangyi Zhang, Ali Etemad
Then, we employ the teacher network to learn the discriminative features embedded in capsules by adopting a lightweight model (student network) to mimic the teacher using the privileged knowledge.
no code implementations • 24 Apr 2021 • Mohsen Zand, Ali Etemad, Michael Greenspan
A novel object detection method is presented that handles freely rotated objects of arbitrary sizes, including tiny objects as small as $2\times 2$ pixels.
1 code implementation • 9 Apr 2021 • Mohsen Zand, Ali Etemad, Michael Greenspan
We specifically propose to use conditional priors to factorize the latent space for the time dependent modeling.
1 code implementation • 6 Apr 2021 • Yangzheng Wu, Mohsen Zand, Ali Etemad, Michael Greenspan
We propose a novel keypoint voting scheme based on intersecting spheres, that is more accurate than existing schemes and allows for fewer, more disperse keypoints.
Ranked #1 on 6D Pose Estimation using RGBD on YCB-Video (ADDS AUC metric)
1 code implementation • ICCV 2021 • Hardik Uppal, Alireza Sepas-Moghaddam, Michael Greenspan, Ali Etemad
Moreover, face recognition experiments demonstrate that our hallucinated depth along with the input RGB images boosts performance across various architectures when compared to a single RGB modality by average values of +1. 2%, +2. 6%, and +2. 6% for IIIT-D, EURECOM, and LFW datasets respectively.
no code implementations • 5 Apr 2021 • Vandad Davoodnia, Ali Etemad
Sleep posture analysis is widely used for clinical patient monitoring and sleep studies.
no code implementations • 26 Feb 2021 • Shashi Suman, Ali Etemad, Francois Rivest
We then investigate the possibility of human behavior being altered as a result of the smart home and the human model adapting to one-another.
no code implementations • 18 Feb 2021 • Alireza Sepas-Moghaddam, Ali Etemad
Gait recognition is an appealing biometric modality which aims to identify individuals based on the way they walk.
no code implementations • 10 Jan 2021 • Alireza Sepas-Moghaddam, Ali Etemad, Fernando Pereira, Paulo Lobato Correia
A subset of the in the wild dataset contains facial images with different expressions, annotated for usage in the context of face expression recognition tests.
1 code implementation • 3 Jan 2021 • Hardik Uppal, Alireza Sepas-Moghaddam, Michael Greenspan, Ali Etemad
Our novel attention mechanism directs the deep network "where to look" for visual features in the RGB image by focusing the attention of the network using depth features extracted by a Convolution Neural Network (CNN).
2 code implementations • 3 Nov 2020 • Pritam Sarkar, Silvia Lobmaier, Bibiana Fabre, Diego González, Alexander Mueller, Martin G. Frasch, Marta C. Antonelli, Ali Etemad
Our DL models accurately detect the chronic stress exposure group (AUROC=0. 982+/-0. 002), the individual psychological stress score (R2=0. 943+/-0. 009) and FSI at 34 weeks of gestation (R2=0. 946+/-0. 013), as well as the maternal hair cortisol at birth reflecting chronic stress exposure (0. 931+/-0. 006).
no code implementations • 21 Oct 2020 • Setareh Rahimi Taghanaki, Michael Rainbow, Ali Etemad
We propose the use of self-supervised learning for human activity recognition with smartphone accelerometer data.
no code implementations • 18 Oct 2020 • Alireza Sepas-Moghaddam, Ali Etemad
Our proposed model has been extensively tested on two large-scale CASIA-B and OU-MVLP gait datasets using four different test protocols and has been compared to a number of state-of-the-art and baseline solutions.
no code implementations • 18 Oct 2020 • Alireza Sepas-Moghaddam, Saeed Ghorbani, Nikolaus F. Troje, Ali Etemad
In this context, we propose a novel deep network, learning to transfer multi-scale partial gait representations using capsules to obtain more discriminative gait features.
2 code implementations • 30 Sep 2020 • Pritam Sarkar, Ali Etemad
Electrocardiogram (ECG) is the electrical measurement of cardiac activity, whereas Photoplethysmogram (PPG) is the optical measurement of volumetric changes in blood circulation.
no code implementations • 28 Sep 2020 • Amirhossein Hajavi, Ali Etemad
Our model uses thin-ResNet for extracting speaker embeddings from utterances and a Siamese capsule network and dynamic routing as the Back-end to calculate a similarity score between the embeddings.
no code implementations • 23 Sep 2020 • Tedd Kourkounakis, Amirhossein Hajavi, Ali Etemad
We also evaluate FluentNet on this dataset, showing the strong performance of our model versus a number of benchmark techniques.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 23 Sep 2020 • Arthur Cruz de Araujo, Ali Etemad
The acquisition of massive data on parcel delivery motivates postal operators to foster the development of predictive systems to improve customer service.
no code implementations • 3 Sep 2020 • Amirhossein Hajavi, Ali Etemad
We evaluate the proposed model on three tasks of speaker recognition, speech emotion recognition, and spoken digit recognition.
no code implementations • 24 Aug 2020 • Kyle Ross, Paul Hungler, Ali Etemad
The results show the wide-spread applicability for stacked convolutional autoencoders to be used with machine learning for affective computing.
1 code implementation • 19 Aug 2020 • Guangyi Zhang, Ali Etemad
Moreover, our proposed method learns the temporal information via differential entropy and logarithm power spectrum density features extracted from EEG signals in a Euclidean space using a deep long short-term memory network with a soft attention mechanism.
no code implementations • 18 Jun 2020 • Vandad Davoodnia, Monet Slinowsky, Ali Etemad
Smart devices in the Internet of Things (IoT) paradigm provide a variety of unobtrusive and pervasive means for continuous monitoring of bio-metrics and health information.
1 code implementation • 29 Feb 2020 • Hardik Uppal, Alireza Sepas-Moghaddam, Michael Greenspan, Ali Etemad
A novel attention aware method is proposed to fuse two image modalities, RGB and depth, for enhanced RGB-D facial recognition.
2 code implementations • 4 Feb 2020 • Pritam Sarkar, Ali Etemad
Six different signal transformations are applied to the ECG signals, and transformation recognition is performed as pretext tasks.
no code implementations • 17 Dec 2019 • Guangyi Zhang, Ali Etemad
To enable the system to focus on the most salient parts of the learned multimodal representations, we propose an architecture composed of a capsule attention mechanism following a deep Long Short-Term Memory (LSTM) network.
no code implementations • IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019 • Tedd Kourkounakis, Amirhossein Hajavi, Ali Etemad
Stuttering is a speech impediment affecting tens of millions of people on an everyday basis.
2 code implementations • 14 Oct 2019 • Pritam Sarkar, Ali Etemad
Our proposed architecture consists of two main networks, a signal transformation recognition network and an emotion recognition network.
no code implementations • 21 Aug 2019 • Vandad Davoodnia, Saeed Ghorbani, Ali Etemad
Recent advances in deep pose estimation models have proven to be effective in a wide range of applications such as health monitoring, sports, animations, and robotics.
no code implementations • 6 Aug 2019 • Guangyi Zhang, Vandad Davoodnia, Alireza Sepas-Moghaddam, Yaoxue Zhang, Ali Etemad
Classifying limb movements using brain activity is an important task in Brain-computer Interfaces (BCI) that has been successfully used in multiple application domains, ranging from human-computer interaction to medical and biomedical applications.
no code implementations • 31 Jul 2019 • Saeed Ghorbani, Ali Etemad, Nikolaus F. Troje
Optical marker-based motion capture is a vital tool in applications such as motion and behavioural analysis, animation, and biomechanics.
no code implementations • 31 Jul 2019 • Pritam Sarkar, Kyle Ross, Aaron J. Ruberto, Dirk Rodenburg, Paul Hungler, Ali Etemad
Simulations are a pedagogical means of enabling a risk-free way for healthcare practitioners to learn, maintain, or enhance their knowledge and skills.
no code implementations • 22 Jul 2019 • Amirhossein Hajavi, Ali Etemad
Todays interactive devices such as smart-phone assistants and smart speakers often deal with short-duration speech segments.
no code implementations • 11 May 2019 • Alireza Sepas-Moghaddam, Ali Etemad, Fernando Pereira, Paulo Lobato Correia
In this context, this paper proposes two novel LSTM cell architectures that are able to jointly learn from multiple sequences simultaneously acquired, targeting to create richer and more effective models for recognition tasks.