Search Results for author:
Found 91 papers, 31 papers with code
A Bag of Tricks for Few-Shot Class-Incremental Learning
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
A collection of the accepted papers for the Human-Centric Representation Learning workshop at AAAI 2024
This non-archival index is not complete, as some accepted papers chose to opt-out of inclusion.
Learning under Label Noise through Few-Shot Human-in-the-Loop Refinement
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.
SASSL: Enhancing Self-Supervised Learning via Neural Style Transfer
Existing data augmentation in self-supervised learning, while diverse, fails to preserve the inherent structure of natural images.
Contrastive Learning of View-Invariant Representations for Facial Expressions Recognition
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.
Remote Heart Rate Monitoring in Smart Environments from Videos with Self-supervised Pre-training
Recent advances in deep learning have made it increasingly feasible to estimate heart rate remotely in smart environments by analyzing videos.
Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representations
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.
Diffusion Models with Deterministic Normalizing Flow Priors
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.
Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Prediction
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.
Region-Disentangled Diffusion Model for High-Fidelity PPG-to-ECG Translation
In this work, we introduce Region-Disentangled Diffusion Model (RDDM), a novel diffusion model designed to capture the complex temporal dynamics of ECG.
EEG-based Cognitive Load Classification using Feature Masked Autoencoding and Emotion Transfer Learning
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.
Context-aware Pedestrian Trajectory Prediction with Multimodal Transformer
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.
Active Learning with Contrastive Pre-training for Facial Expression Recognition
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.
Continual Learning for Out-of-Distribution Pedestrian Detection
A continual learning solution is proposed to address the out-of-distribution generalization problem for pedestrian detection.
Can Continual Learning Improve Long-Tailed Recognition? Toward a Unified Framework
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.
Unmasking Deepfakes: Masked Autoencoding Spatiotemporal Transformers for Enhanced Video Forgery Detection
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.
Toward Fair Facial Expression Recognition with Improved Distribution Alignment
We present a novel approach to mitigate bias in facial expression recognition (FER) models.
Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts
Video self-supervised learning (VSSL) has made significant progress in recent years.
Exploring the Boundaries of Semi-Supervised Facial Expression Recognition: Learning from In-Distribution, Out-of-Distribution, and Unconstrained Data
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
Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data
We propose UnMixMatch, a semi-supervised learning framework which can learn effective representations from unconstrained unlabelled data in order to scale up performance.
Consistency-guided Prompt Learning for Vision-Language Models
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
Privacy-Preserving Remote Heart Rate Estimation from Facial Videos
Remote Photoplethysmography (rPPG) is the process of estimating PPG from facial videos.
An Ensemble Semi-Supervised Adaptive Resonance Theory Model with Explanation Capability for Pattern Classification
Firstly, SSL-ART adopts an unsupervised fuzzy ART network to create a number of prototype nodes using unlabeled samples.
In-Distribution and Out-of-Distribution Self-supervised ECG Representation Learning for Arrhythmia Detection
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.
Multimodal Brain-Computer Interface for In-Vehicle Driver Cognitive Load Measurement: Dataset and Baselines
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.
A Study on Bias and Fairness In Deep Speaker Recognition
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.
Human Pose Estimation from Ambiguous Pressure Recordings with Spatio-temporal Masked Transformers
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.
Partial Label Learning for Emotion Recognition from EEG
However, PLL methods have not yet been adopted for EEG representation learning or implemented for emotion recognition tasks.
Audio Representation Learning by Distilling Video as Privileged Information
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.
Impact of Labelled Set Selection and Supervision Policies on Semi-supervised Learning
All these labelled samples are then used along with the unlabelled data throughout the training process.
XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning
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
FaceTopoNet: Facial Expression Recognition using Face Topology Learning
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)
Temporal Contrastive Learning with Curriculum
We present ConCur, a contrastive video representation learning method that uses curriculum learning to impose a dynamic sampling strategy in contrastive training.
Self-Supervised Human Activity Recognition with Localized Time-Frequency Contrastive Representation Learning
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.
Analysis of Semi-Supervised Methods for Facial Expression Recognition
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
Multimodal Estimation of End Point Force During Quasi-dynamic and Dynamic Muscle Contractions Using Deep Learning
We propose a novel method to accurately model the generated force under isotonic, isokinetic (quasi-dynamic), and fully dynamic conditions.
ObjectBox: From Centers to Boxes for Anchor-Free Object Detection
We present ObjectBox, a novel single-stage anchor-free and highly generalizable object detection approach.
Multistream Gaze Estimation with Anatomical Eye Region Isolation by Synthetic to Real Transfer Learning
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.
Estimating Pose from Pressure Data for Smart Beds with Deep Image-based Pose Estimators
In-bed pose estimation has shown value in fields such as hospital patient monitoring, sleep studies, and smart homes.
AttX: Attentive Cross-Connections for Fusion of Wearable Signals in Emotion Recognition
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.
Learning Sequential Contexts using Transformer for 3D Hand Pose Estimation
3D hand pose estimation (HPE) is the process of locating the joints of the hand in 3D from any visual input.
Analysis of Augmentations for Contrastive ECG Representation Learning
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).
AVCAffe: A Large Scale Audio-Visual Dataset of Cognitive Load and Affect for Remote Work
We introduce AVCAffe, the first Audio-Visual dataset consisting of Cognitive load and Affect attributes.
Multiscale Crowd Counting and Localization By Multitask Point Supervision
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.
PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion Recognition
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.
Gaze Estimation with Eye Region Segmentation and Self-Supervised Multistream Learning
We first create a synthetic dataset containing eye region masks detailing the visible eyeball and iris using a simulator.
Face Trees for Expression Recognition
We propose an end-to-end architecture for facial expression recognition.
Facial Expression Recognition
Facial Expression Recognition (FER)
Towards Personalization of User Preferences in Partially Observable Smart Home Environments
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
Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity
We present CrissCross, a self-supervised framework for learning audio-visual representations.
Ranked #1 on
Audio Classification
on DCASE
Holistic Semi-Supervised Approaches for EEG Representation Learning
Recently, supervised methods, which often require substantial amounts of class labels, have achieved promising results for EEG representation learning.
Multi-View Video-Based 3D Hand Pose Estimation
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.
Wearable-based Classification of Running Styles with Deep Learning
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.
A Transformer Architecture for Stress Detection from ECG
Electrocardiogram (ECG) has been widely used for emotion recognition.
Self-supervised Contrastive Learning of Multi-view Facial Expressions
The model is then fine-tuned with labeled data in a supervised setting.
Spatiotemporal Contrastive Learning of Facial Expressions in Videos
Experiments are performed on the Oulu-CASIA dataset and the performance is compared to other works in FER.
Attentive Cross-modal Connections for Deep Multimodal Wearable-based Emotion Recognition
Classification of human emotions can play an essential role in the design and improvement of human-machine systems.
Deep Recurrent Semi-Supervised EEG Representation Learning for Emotion Recognition
We evaluate our framework using both a stacked autoencoder and an attention-based recurrent autoencoder.
Multi-Perspective LSTM for Joint Visual Representation Learning
We validate the performance of our proposed architecture in the context of two multi-perspective visual recognition tasks namely lip reading and face recognition.
Distilling EEG Representations via Capsules for Affective Computing
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.
Oriented Bounding Boxes for Small and Freely Rotated Objects
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.
Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics
We specifically propose to use conditional priors to factorize the latent space for the time dependent modeling.
Teacher-Student Adversarial Depth Hallucination to Improve Face Recognition
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.
Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting
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)
Identity and Posture Recognition in Smart Beds with Deep Multitask Learning
Sleep posture analysis is widely used for clinical patient monitoring and sleep studies.
Potential Impacts of Smart Homes on Human Behavior: A Reinforcement Learning Approach
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.
Deep Gait Recognition: A Survey
Gait recognition is an appealing biometric modality which aims to identify individuals based on the way they walk.
CapsField: Light Field-based Face and Expression Recognition in the Wild using Capsule Routing
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.
Depth as Attention for Face Representation Learning
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).
Detection of Maternal and Fetal Stress from the Electrocardiogram with Self-Supervised Representation Learning
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).
Self-supervised Human Activity Recognition by Learning to Predict Cross-Dimensional Motion
We propose the use of self-supervised learning for human activity recognition with smartphone accelerometer data.
View-Invariant Gait Recognition with Attentive Recurrent Learning of Partial Representations
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.
Gait Recognition using Multi-Scale Partial Representation Transformation with Capsules
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.
CardioGAN: Attentive Generative Adversarial Network with Dual Discriminators for Synthesis of ECG from PPG
Electrocardiogram (ECG) is the electrical measurement of cardiac activity, whereas Photoplethysmogram (PPG) is the optical measurement of volumetric changes in blood circulation.
Siamese Capsule Network for End-to-End Speaker Recognition In The Wild
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.
FluentNet: End-to-End Detection of Speech Disfluency with Deep Learning
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
End-to-End Prediction of Parcel Delivery Time with Deep Learning for Smart-City Applications
The acquisition of massive data on parcel delivery motivates postal operators to foster the development of predictive systems to improve customer service.
Fine-grained Early Frequency Attention for Deep Speaker Representation Learning
We evaluate the proposed model on three tasks of speaker recognition, speech emotion recognition, and spoken digit recognition.
Unsupervised Multi-Modal Representation Learning for Affective Computing with Multi-Corpus Wearable Data
The results show the wide-spread applicability for stacked convolutional autoencoders to be used with machine learning for affective computing.
Spatio-Temporal EEG Representation Learning on Riemannian Manifold and Euclidean Space
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.
Deep Multitask Learning for Pervasive BMI Estimation and Identity Recognition in Smart Beds
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.
Two-Level Attention-based Fusion Learning for RGB-D Face Recognition
A novel attention aware method is proposed to fuse two image modalities, RGB and depth, for enhanced RGB-D facial recognition.
Self-supervised ECG Representation Learning for Emotion Recognition
Six different signal transformations are applied to the ECG signals, and transformation recognition is performed as pretext tasks.
Capsule Attention for Multimodal EEG-EOG Representation Learning with Application to Driver Vigilance Estimation
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.
Detecting Multiple Speech Disfluencies using a Deep Residual Network with Bidirectional Long Short-Term Memory
Stuttering is a speech impediment affecting tens of millions of people on an everyday basis.
Self-supervised Learning for ECG-based Emotion Recognition
Our proposed architecture consists of two main networks, a signal transformation recognition network and an emotion recognition network.
In-bed Pressure-based Pose Estimation using Image Space Representation Learning
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.
Classification of Hand Movements from EEG using a Deep Attention-based LSTM Network
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.
Classification of Cognitive Load and Expertise for Adaptive Simulation using Deep Multitask Learning
Simulations are a pedagogical means of enabling a risk-free way for healthcare practitioners to learn, maintain, or enhance their knowledge and skills.
Auto-labelling of Markers in Optical Motion Capture by Permutation Learning
Optical marker-based motion capture is a vital tool in applications such as motion and behavioural analysis, animation, and biomechanics.
A Deep Neural Network for Short-Segment Speaker Recognition
Todays interactive devices such as smart-phone assistants and smart speakers often deal with short-duration speech segments.
Long Short-Term Memory with Gate and State Level Fusion for Light Field-Based Face Recognition
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.
