Survey of open set recognition techniques and their limitations.
problem Recognition tasks with unknown classes during testing.
method Comprehensive review of techniques, datasets, and evaluation criteria.
result Highlighting the limitations and future directions in open set recognition.
DGP learns speech recognition by modeling complex relationships between utterances.
problem Modeling complex relationships in speech recognition without relational data.
method Bayesian nonparametric deep learning method (DGP) that generates infinite probabilistic graphs.
result DGP successfully infers relationships among utterances without relational data during training.
This is a survey article on recognition problem of frontal singularities. We specify geometrically several frontal singularities and then we solve the recognition problem of such singularities, giving explicit normal forms. We combine the recognition results by K. Saji and several arguments on openings, which was perfo…
End-to-end model detects articulatory features from speech data.
problem Detecting articulatory features from speech data for various applications.
method Apply Listen, Attend and Spell (LAS) architecture and attention models.
result End-to-end training of manners and places of articulation detectors.
With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to scale the recognition to a large number of classes with few or now training samp…
New approach uses graphs for sign language recognition.
problem Challenges in recognizing sign language for deaf individuals.
method Spatial-Temporal Graph Convolutional Network.
result Improved sign language recognition using human skeletal movements.
Paper proposes a CNN for speech emotion recognition using center loss and reconstruction.
problem Speech emotion recognition (SER) in audio signals.
method Convolutional Neural Network (CNN) with center loss and reconstruction as regularizers.
result Proposed method achieves highly discriminative features for SER.
Neural network based architectures used for sound recognition are usually adapted from other application domains, which may not harness sound related properties. The ConditionaL Neural Network (CLNN) is designed to consider the relational properties across frames in a temporal signal, and its extension the Masked Condi…
System helps engineers with concept recognition for SEVA.
problem Recognizing systems engineering concepts for SEVA.
method Token classification task, domain expert labeling, pre-trained model fine-tuning, essential datasets creation, knowledge graph construction.
result System successfully recognizes systems engineering concepts.
Paper proposes using synthetic data to improve face recognition accuracy.
problem Improving face recognition accuracy using real data alone.
method Proposes a GAN that disentangles identity attributes and generates photo-realistic synthetic images.
result Synthetic images generated by the model are photo-realistic and can increase face recognition accuracy.
Transfer learning does not improve character recognition performance.
problem Improving character recognition performance using transfer learning.
method Performed experiments with varying levels of similarity between source and target tasks, transferring both parameters and features.
result No significant advantage gained by transfer learning over traditional machine learning.
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.
Quaternion neural networks improve speech recognition efficiency.
problem Improving speech recognition systems with fewer parameters.
method Investigating quaternion-valued convolutional and recurrent neural networks.
result Quaternion neural networks outperform real-valued models with fewer parameters.
This work tackles domain shift in speech emotion recognition by proposing class-wise adversarial domain adaptation.
problem Domain shift between corpora poses a challenge for speech emotion recognition, especially for positive/negative emotions.
method Class-wise adversarial domain adaptation to reduce shift between different corpora.
result Our method is effective even with limited target labeled examples, as demonstrated on EMODB and Aibo corpora.
A novel procedure is presented in this paper, for training a deep convolutional and recurrent neural network, taking into account both the available training data set and some information extracted from similar networks trained with other relevant data sets. This information is included in an extended loss function use…
Deep learning improves human affect recognition in natural settings.
problem Automatic recognition of human emotions in real-world scenarios.
method Review and analysis of 233 studies using deep neural networks.
result Deep learning significantly enhances affect recognition from multimodal sensor data.
QLSTM improves speech recognition by considering internal quaternion dependencies.
problem Weak internal dependencies in traditional RNNs for speech recognition.
method Proposes QLSTM, a quaternion-based LSTM that considers both external and internal dependencies.
result QLSTM achieves better performance with up to 2.8 times fewer parameters.
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.
Unified framework improves cross-corpus EEG emotion recognition by aligning prototypes and refining decision boundaries.
problem Cross-corpus EEG emotion recognition suffers from performance degradation due to physiological variability and device inconsistencies.
method Prototype-driven Adversarial Alignment (PAA) framework with three configurations: local, contrastive, and boundary-aware.
result State-of-the-art performance improvements across four cross-corpus evaluation protocols.
The problem of domain generalization is to take knowledge acquired from a number of related domains where training data is available, and to then successfully apply it to previously unseen domains. We propose a new feature learning algorithm, Multi-Task Autoencoder (MTAE), that provides good generalization performance …
Optimal ANN pre-training with SDA reduces handwritten Bengali digit recognition error to 2.34%
problem Optimizing ANN architecture for Bengali handwritten digit recognition
method Pre-training ANN with stacked denoising autoencoder (SDA)
result Minimum validation error of 2.34% on handwritten Bengali dataset
Study improves recognition of long-tail visual relationships.
problem Improving recognition of structured visual relationships from long-tail classes.
method Developed two benchmarks, introduced VilHub loss, and applied RelMix augmentation.
result Simple techniques significantly improved performance on tail classes.
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…
Quaternion neural networks improve distant speech recognition.
problem Challenges in distant speech recognition due to noise and reverberation.
method Quaternion neural networks process multi-channel audio signals as quaternion entities, capturing internal and external dependencies.
result QLSTM outperforms real-valued LSTM on multi-channel distant speech recognition tasks.
A new multi-layer attention mechanism improves speech keyword recognition accuracy.
problem Inaccurate attention weights in LSTM networks for speech keyword recognition.
method Introducing information from layers prior to feature extraction into attention weights calculations.
result The proposed multi-layer attention mechanism leads to more accurate attention weights and improved keyword spotting performance.
End-to-end solution for recognizing handwritten numerals, avoiding traditional preprocessing steps.
problem Handwritten numeral string recognition with traditional preprocessing steps.
method YoLo-based model for automatic detection and recognition, avoiding heuristic-based preprocessing and segmentation.
result Proposed method reduces complexity and is a feasible end-to-end solution for numeral string recognition.
Neural network based architectures used for sound recognition are usually adapted from other application domains such as image recognition, which may not harness the time-frequency representation of a signal. The ConditionaL Neural Networks (CLNN) and its extension the Masked ConditionaL Neural Networks (MCLNN) are des…
Online structure learning approaches, such as those stemming from Statistical Relational Learning, enable the discovery of complex relations in noisy data streams. However, these methods assume the existence of fully-labelled training data, which is unrealistic for most real-world applications. We present a novel appro…
We study large-scale kernel methods for acoustic modeling and compare to DNNs on performance metrics related to both acoustic modeling and recognition. Measuring perplexity and frame-level classification accuracy, kernel-based acoustic models are as effective as their DNN counterparts. However, on token-error-rates DNN…
This article provides a unifying Bayesian network view on various approaches for acoustic model adaptation, missing feature, and uncertainty decoding that are well-known in the literature of robust automatic speech recognition. The representatives of these classes can often be deduced from a Bayesian network that exten…
Morph accelerates 3D CNNs for video recognition, reducing energy consumption and improving performance.
problem Efficiently accelerating 3D CNNs for video recognition is challenging due to their large memory footprint and higher dimensionality.
method Designing a flexible accelerator called Morph that adapts to different spatial and temporal tiling strategies, and codesigning a software infrastructure to control the hardware.
result Morph achieves up to 3.4x reduction in energy consumption and up to 5.1x improvement in performance/watt compared to a baseline 3D CNN accelerator.
Paper proposes redundancy-free features for zero-shot object recognition.
problem Redundant visual features degrade zero-shot object recognition.
method Project original features into a new, statistically independent space.
result RFF-GZSL achieves competitive results on benchmark datasets.
Learning, taking into account full distribution of the data, referred to as generative, is not feasible with deep neural networks (DNNs) because they model only the conditional distribution of the outputs given the inputs. Current solutions are either based on joint probability models facing difficult estimation proble…
Image understanding using deep convolutional network has reached human-level performance, yet a closely related problem of video understanding especially, action recognition has not reached the requisite level of maturity. We combine multi-kernels based support-vector-machines (SVM) with a multi-stream deep convolution…
Vehicle recognition and classification have broad applications, ranging from traffic flow management to military target identification. We demonstrate an unsupervised method for automated identification of moving vehicles from roadside audio sensors. Using a short-time Fourier transform to decompose audio signals, we t…
Pattern recognition in neuroimaging distinguishes between two types of models: encoding- and decoding models. This distinction is based on the insight that brain state features, that are found to be relevant in an experimental paradigm, carry a different meaning in encoding- than in decoding models. In this paper, we a…
Develops a deep learning framework to predict future tech directions for high-tech companies.
problem Difficult task in predicting future R&D trends for high-tech companies due to complexity and variety of factors.
method Deep Technology Forecasting (DTF) framework with three components: PCR, CTR, and DTT neural network.
result DTF framework precisely predicts future tech emphasis of companies using hybrid factors.
Paper presents IPRC for robust tumor recognition using sparse representation.
problem Sparse representation methods struggle with insufficient test samples and instability.
method Proposes IPRC, a stable inverse projection representation method.
result Demonstrates competitive robust tumor recognition using IPRC.
Deep Fusion improves audio-video emotion recognition accuracy.
problem Challenges in automatic emotion recognition due to abstract concept and multiple expressions of emotion.
method Introduces factorized bilinear pooling (FBP) with embedded attention mechanism to integrate audio and video features.
result Achieves an accuracy of 62.48% on AFEW database, outperforming state-of-the-art results.
ChemGrapher uses deep learning to automatically convert chemical compound images into accurate graphs.
problem Automatically converting chemical compound images into accurate graphs with correct bond multiplicity and stereochemical information.
method Developed a deep neural network model for optical compound recognition, including segmentation and classification models.
result Significant error reductions in bond multiplicity and stereochemical information compared to existing tools.
The study improves the assessment of fairness in face recognition using ROC curves and statistical guarantees.
problem Improving the assessment of fairness in face recognition systems.
method Proves asymptotic guarantees for empirical ROC curves and fairness metrics, and introduces a recentering technique to avoid bootstrap pitfalls.
result Demonstrates the practical relevance of the methods for assessing fairness in face recognition systems.
Survey on deep learning for malware classification, including unknown threats.
problem Classifying and recognizing unknown malware variants.
method Review of deep learning techniques and OSR solutions.
result Deep learning can effectively classify known malware and recognize unknown threats.
Revisited Lmser for image recognition with convolutional layers.
problem Lmser's limitations in one-hidden-layer implementation and lack of computing resources.
method Developed Lmser network using multiple convolutional layers for image-related tasks.
result Lmser functions are confirmed with preliminary demonstrations on image recognition and reconstruction.
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.
This paper addresses image classification through learning a compact and discriminative dictionary efficiently. Given a structured dictionary with each atom (columns in the dictionary matrix) related to some label, we propose cross-label suppression constraint to enlarge the difference among representations for differe…
Complex activity recognition is challenging due to the inherent uncertainty and diversity of performing a complex activity. Normally, each instance of a complex activity has its own configuration of atomic actions and their temporal dependencies. We propose in this paper an atomic action-based Bayesian model that const…
Improved speech recognition using EEG and video.
problem Enhancing continuous speech recognition systems.
method Implemented a CTC-based ASR model using EEG features.
result EEG features improve continuous visual speech recognition.
SA-GAN improves HAR model performance across new users.
problem Poor performance of HAR models on new user data.
method Generative Adversarial Network (GAN) for cross-subject transfer learning.
result SA-GAN outperformed other methods in HAR tasks.