Enhances 2D face recognition with 3D features using active illumination.
problem Improving robustness of 2D face recognition to spoofing attacks and low-light conditions.
method Projecting a high spatial frequency pattern onto the face to recover 3D information and a 2D image simultaneously.
result Significantly boosts face recognition performance and dramatically improves robustness to spoofing attacks.
AVEC 2019 challenges AI in detecting depression and cross-cultural emotions.
problem Detecting depression and cross-cultural emotions from audiovisual data.
method Comparison of machine learning methods under standardized conditions.
result Baseline system performance on state-of-mind, depression, and cross-cultural tasks.
Gait patterns reveal emotions, offering a non-invasive method for automated recognition.
problem Automated emotion recognition from gait patterns.
method Data collection, preprocessing, and classification techniques.
result Gait patterns can indicate different emotion states, making them a promising source for emotion detection.
Deep learning improves speaker recognition verification and identification.
problem Limited progress in speaker recognition for 5-6 years.
method Applied deep learning techniques in speaker verification and identification.
result Deep learning becomes the state-of-the-art solution for speaker recognition.
CAT is a new ASR toolkit using CRF and CTC for state-of-the-art speech recognition.
problem Improving automatic speech recognition systems.
method CRF-based discriminative training with CTC-inspired state topology.
result CAT achieves state-of-the-art results with fewer parameters and is competitive with hybrid models.
Paper tackles zero-shot activity recognition using video features and text embeddings.
problem Zero-shot activity recognition with videos.
method Auto-encoder model for multimodal joint embedding, 3D convolutional action recognition for visual features, GloVe word embeddings for textual features.
result Improved zero-shot recognition results with top-n accuracy and mean Nearest Neighbor Overlap.
This paper presents the Intelligent Voice (IV) system submitted to the NIST 2016 Speaker Recognition Evaluation (SRE). The primary emphasis of SRE this year was on developing speaker recognition technology which is robust for novel languages that are much more heterogeneous than those used in the current state-of-the-a…
Self-supervised ECG learning improves emotion recognition.
problem Improving emotion recognition from ECG signals.
method Multi-task deep learning framework with signal transformations as pretext tasks.
result Significant performance improvement in emotion classification.
Deep learning and prior maps improve traffic light recognition for autonomous cars.
problem Recognizing traffic lights for autonomous cars in urban environments.
method Combining deep learning-based detection with prior maps for traffic light identification and state recognition.
result The proposed system correctly identified relevant traffic lights along predefined routes.
Paper proposes an online speech recognition model using Transformer.
problem Challenges in deploying Transformer-based E2E ASR for online speech recognition.
method Chunk self-attention encoder (chunk-SAE) and monotonic truncated attention (MTA) based self-attention decoder (SAD).
result Achieved 23.66% CER with 320 ms latency, significant improvement over offline models.
Improves neural network mapping functionality using latent feature generation.
problem Improving neural network performance in visual recognition tasks.
method Reversible learning for generating and learning latent features.
result The proposed method outperforms existing state-of-the-art methods in visual recognition.
Surface Electromyography (sEMG/EMG) is to record muscles' electrical activity from a restricted area of the skin by using electrodes. The sEMG-based gesture recognition is extremely sensitive of inter-session and inter-subject variances. We propose a model and a deep-learning-based domain adaptation method to approxima…
Survey on DNNs for speech processing, focusing on limited data challenges.
problem Challenges in training DNNs for speech tasks with limited data.
method Overview of techniques for few-shot speech processing.
result Promising few-shot techniques for speech processing.
Deep learning improves material recognition in construction monitoring.
problem Varying illuminations and low accuracy rates in material classification.
method Deep learning methods, including convolutional neural networks, were used to classify and recognize materials in construction sites.
result Achieved 97.35% accuracy rate for material classification.
We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition. Instead of explicitly combining multimodal information, which is commonplace in many state-of-the-art methods, we propo…
Improved speech emotion recognition using pre-trained language models.
problem Challenging task of speech emotion recognition for natural human-machine interaction.
method Fine-tuning pre-trained language models for text emotion recognition, combining with speech emotion recognition.
result 73.5% accuracy in speech emotion recognition on a subset of IEMOCAP dataset.
Action recognition has attracted increasing attention from RGB input in computer vision partially due to potential applications on somatic simulation and statistics of sport such as virtual tennis game and tennis techniques and tactics analysis by video. Recently, deep learning based methods have achieved promising per…
SparseSense improves HAR from sparse sensor data, outperforming state-of-the-art models.
problem Learning activity recognition from highly sparse sensor data streams.
method Set-based neural networks for end-to-end learning from sparse data.
result Significant performance improvements in HAR from passive sensor datasets.
Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs. Unlike feedforward neural networks, RNNs have cyclic connections making them powerful for modeling sequences. They have been successfully u…
CGDL improves open set recognition by learning conditional Gaussian distributions.
problem Handling unknown samples in real-world recognition tasks.
method Conditional Gaussian Distribution Learning (CGDL) with probabilistic ladder architecture.
result CGDL significantly outperforms baseline methods on standard image datasets.
Random forest can be adapted for open-set recognition with improved performance.
problem Handling unknown classes in real-world classification tasks.
method Incorporating distance metric learning and distance-based open-set recognition into random forest.
result The proposed method outperforms state-of-the-art open-set recognition methods.
Improves cross-lingual NER by projecting entities from one language to another.
problem Limited annotated corpora for named entity recognition in many languages.
method Uses machine translation twice: first for sentences, then for entities; matches based on ortho- and phonetic similarity; identifies matches using distributional statistics.
result Improves cross-lingual NER by an average of 4.1 points on 5 diverse languages.
Fawkes protects images from unauthorized facial recognition models.
problem Unauthorized training of facial recognition models poses privacy risks.
method Fawkes adds imperceptible pixel-level changes (cloaks) to images before release.
result Fawkes can protect images from misidentification by 95% and 80% even when clean images are leaked.
Paper proposes a framework to protect user anonymity in emotion recognition.
problem Preserving user anonymity in face-based emotion recognition systems.
method Adversarial learning framework using CNN architecture.
result The proposed approach minimizes identity-specific information and maximizes emotion-dependent information.
Survey examines public views on facial recognition technology.
problem Public acceptance and privacy concerns with facial recognition.
method Cross-national survey of 4 countries.
result Public views vary significantly across countries.
New approach improves human activity recognition with wearables.
problem Improving human activity recognition with wearables.
method Exploiting latent relationships between multi-channel sensor modalities, data-agnostic augmentation, and a classification loss criterion.
result Achieves new state-of-the-art performance on four diverse activity recognition benchmarks.
Despite showing state-of-the-art performance, deep learning for speech recognition remains challenging to deploy in on-device edge scenarios such as mobile and other consumer devices. Recently, there have been greater efforts in the design of small, low-footprint deep neural networks (DNNs) that are more appropriate fo…
Deep neural network architectures designed for application domains other than sound, especially image recognition, may not optimally harness the time-frequency representation when adapted to the sound recognition problem. In this work, we explore the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural N…
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open research questions. Current research suggests using a simple temporal feature pooling…
Model improves emotion recognition using multiple physiological signals.
problem Single physiological signal is insufficient for accurate emotion recognition.
method Fused multiple modal physiological signals (EEG, EMG, EOG) for emotion classification.
result Best classification accuracy of 94.42% on arousal and 94.02% on valence in two-class tasks.
We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking blocks of frequency channels, and masking blocks of time steps. …
Automatic speech recognition can potentially benefit from the lip motion patterns, complementing acoustic speech to improve the overall recognition performance, particularly in noise. In this paper we propose an audio-visual fusion strategy that goes beyond simple feature concatenation and learns to automatically align…
We present the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural Network (MCLNN) designed for temporal signal recognition. The CLNN takes into consideration the temporal nature of the sound signal and the MCLNN extends upon the CLNN through a binary mask to preserve the spatial locality of the feature…
Speech emotion recognition system using features and text.
problem Improving accuracy in emotion recognition from speech.
method Used speech features (Spectrogram, MFCC) and text, trained Deep Neural Networks.
result Combined MFCC-Text CNN model achieved highest accuracy.
Paper introduces Balanced Meta-Softmax for better long-tailed visual recognition.
problem Long-tailed distribution mismatch between training and testing data.
method Balanced Meta-Softmax, an unbiased extension of Softmax, using a Meta Sampler.
result Balanced Meta-Softmax outperforms state-of-the-art solutions on visual recognition and instance segmentation.
New dataset for evaluating speech recognition fairness across demographics.
problem Lack of fairness metrics in speech recognition datasets.
method Developed Fair-Speech dataset with diverse demographic information.
result Helps evaluate ASR models for fairness across demographics.
This paper improves speech recognition by distilling knowledge from acoustic models.
problem Improving speech recognition accuracy using ensemble models.
method Proposes multi-teacher distillation strategies for joint CTC-attention end-to-end ASR systems, integrating error rate metric for optimization.
result Reports state-of-the-art error rates on various datasets and languages.
HW2MP-GAN tackles ancient handwritten text recognition.
problem Automatic text recognition from ancient handwritten records.
method Conditional Generative Adversarial Network (HW2MP-GAN) with Sliced Wasserstein distance and U-Net architectures.
result HW2MP-GAN outperforms state-of-the-art models in image-to-image translation and handwritten recognition.
End-to-end audio recognition system improves accuracy.
problem Improving accuracy in auditory object recognition.
method Proposes an end-to-end deep neural network with an 'inception nucleus' to learn features from raw waveforms.
result Bests current state-of-the-art approaches by 10.4 percentage points on Urbansound8k dataset.
In this work, we demonstrate the existence of universal adversarial audio perturbations that cause mis-transcription of audio signals by automatic speech recognition (ASR) systems. We propose an algorithm to find a single quasi-imperceptible perturbation, which when added to any arbitrary speech signal, will most likel…
Bayesian units improve speech recognition with minimal parameters.
problem Improving speech recognition models with fewer parameters.
method Derived Bayesian recurrent units integrated into deep learning frameworks.
result Adding Bayesian units improves speech recognition performance.
Develops STC for sequential data with missing labels.
problem Learning from partially labeled and unsegmented sequential data.
method Introduces Star Temporal Classification (STC) using a star token and GTN framework.
result Recover most of supervised baseline performance with up to 70% missing labels.
Automated surgical workflow analysis and understanding can assist surgeons to standardize procedures and enhance post-surgical assessment and indexing, as well as, interventional monitoring. Computer-assisted interventional (CAI) systems based on video can perform workflow estimation through surgical instruments' recog…
Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs with Hidden Markov Models/Gaussian Mixture Models (HMMs/GMMs) have achieved the …
SVM with local features improves human action recognition.
problem Improving human action recognition in videos.
method Local appearance and motion features extracted using CNNs, concatenated, and used with SVM for classification.
result SVM with local features outperforms previous methods on benchmark datasets.
Study finds PLI functional connectivity feature superior for depression recognition.
problem Effective detection of depression remains a public health challenge.
method Resting state EEG data collected from MDD and normal controls; various feature types and selection methods evaluated.
result PLI functional connectivity feature superior to linear and nonlinear features; highest classification accuracy 82.31%.
Technological development aims to produce generations of increasingly efficient robots able to perform complex tasks. This requires considerable efforts, from the scientific community, to find new algorithms that solve computer vision problems, such as object recognition. The diffusion of RGB-D cameras directed the stu…
Despite the remarkable progress in face recognition related technologies, reliably recognizing faces across ages still remains a big challenge. The appearance of a human face changes substantially over time, resulting in significant intra-class variations. As opposed to current techniques for age-invariant face recogni…